Densely Connected Convolutional Networks
2016/08/25 by Gao Huang, Huang, Gao, Zhuang Liu +5 · 3 voices · 577 citations
Computer Science · #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning #Multimodal Machine Learning Applications
paper · pdf · doi:10.48550/arxiv.1608.06993
Abstract
Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections - one between each layer and its subsequent layer - our network has L(L+1)/2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less computation to achieve high performance. Code and pre-trained models are available at https://github.com/liuzhuang13/DenseNet .
Citations
Cited by
- Test Case Prioritization for DNNs via Neural Collapse Instability
- PhenSPINE: A Standardized Benchmark for Spine Pathology Diagnosis
- From Classification to Localization and Clinical Validation: Large-Scale Development of a Deep Learning System for Thoracic Disease Detection on Chest Radiographs in Thailand
- DECIS: Dual-Evidence Corrective Verification for Interpretable Strabismus Diagnostic Decision-Making
- mHC-GNN: Manifold-Constrained Hyper-Connections for Graph Neural Networks
- Position: Explanation Stability Is a Property of the Model Method Pair, Not the Model
- Distributed solar generation forecasting using attention-based deep neural networks for cloud movement prediction
- Disentangling Model and Human Data Uncertainty in Apparent Facial Age Estimation
- Improving Backward Conformal Prediction via Non-Conformity Score Transformation
- Prospective clinical indication, post-hoc report leakage, and fusion design in multi-image chest radiograph classification: a patient-clustered evaluation
- ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors
- xHC: Expanded Hyper-Connections
- GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification
- Representation recycling for streaming video analysis
- Do Machines Fail Like Humans? A Human-Centred Out-of-Distribution Spectrum for Mapping Error Alignment
- mHC: Manifold-Constrained Hyper-Connections
- Advancements in automated nuclei segmentation for histopathology using you only look once-driven approaches: A systematic review
- ILIAS: Instance-Level Image retrieval At Scale
- Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More
- EIR: Enhanced Image Representations for Medical Report Generation
- Certifying the Right to Be Forgotten: Primal-Dual Optimization for Sample and Label Unlearning in Vertical Federated Learning
- Spatial Interpolation of Room Impulse Responses based on Deeper Physics-Informed Neural Networks with Residual Connections
- Improved cystic hygroma detection from prenatal imaging using ultrasound-specific self-supervised representation learning
- Multi-objective hybrid knowledge distillation for efficient deep learning in smart agriculture
- A CNN-Based Malaria Diagnosis from Blood Cell Images with SHAP and LIME Explainability
- Attention Residuals
- Multi‐angle, cross‐domain fusion strategy enhances automated insect identification and hierarchical categorization: a case study on assassin bugs (Hemiptera: Reduviidae)
- Vehicle-to-Everything Cooperative Perception for Autonomous Driving
- Balanced Soft mixture-of-expert model for Glaucoma Detection
- Anti-Backdoor Coreset Selection via Cumulative Entropy
- ReLATE: Reliability-Guided Evidence Fusion for Robust UAV--Satellite cross-view Geo-Localization
- OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis
- CrossSpine: Multi-scale Cross-sequence Attention with Anatomical Priors for Automated Pfirrmann Grading
- Benchmarking the Domain Gap: Model Selection Instability Under Domain Shift in Video Capsule Endoscopy
- Benchmarking deep learning models for Raman spectroscopy across open-source datasets
- Fixed-Threshold Evaluation of a Hybrid CNN-ViT for AI-Generated Image Detection Across Photos and Art
- animal2vec and MeerKAT: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacoustics
- A Tool Bottleneck Framework for Clinically-Informed and Interpretable Medical Image Understanding
- Detection of Lensed Gravitational Waves in the Millihertz Band Using Frequency-Domain Lensing Feature Extraction Network
- Granular-ball Guided Masking: Structure-aware Data Augmentation
- Defending against adversarial attacks using mixture of experts
- PEDESTRIAN: An Egocentric Vision Dataset for Obstacle Detection on Pavements
- VizDefender: Unmasking Visualization Tampering through Proactive Localization and Intent Inference
- Generating Risky Samples with Conformity Constraints via Diffusion Models
- brat: Aligned Multi-View Embeddings for Brain MRI Analysis
- NASTaR: NovaSAR Automated Ship Target Recognition Dataset
- MeniMV: A Multi-view Benchmark for Meniscus Injury Severity Grading
- Domain-Aware Quantum Circuit for QML
- Latent-space variational data assimilation in two-dimensional turbulence
- Stylized Synthetic Augmentation further improves Corruption Robustness
- Packed Malware Detection Using Grayscale Binary-to-Image Representations
- Machine learning-based prediction of magnet errors in storage ring light sources
- Cross-modal ultra-scale learning with tri-modalities of renal biopsy images for glomerular multi-disease auxiliary diagnosis
- SCR2-ST: Combine Single Cell with Spatial Transcriptomics for Efficient Active Sampling via Reinforcement Learning
- Self-Supervised Ultrasound Representation Learning for Renal Anomaly Prediction in Prenatal Imaging
- Revisiting 2D Foundation Models for Scalable 3D Medical Image Classification
- DL3M: A Vision-to-Language Framework for Expert-Level Medical Reasoning through Deep Learning and Large Language Models
- Optimized Architectures for Kolmogorov-Arnold Networks
- ALERT Open Dataset and Input-Size-Agnostic Vision Transformer for Driver Activity Recognition using IR-UWB
- Type II and Type III Solar Radio Burst Classification Using Transfer Learning
- On the Bayes Inconsistency of Disagreement Discrepancy Surrogates
- Surveillance Video-Based Traffic Accident Detection Using Transformer Architecture
- MetaVoxel: Joint Diffusion Modeling of Imaging and Clinical Metadata
- QuanvNeXt: An end-to-end quanvolutional neural network for EEG-based detection of major depressive disorder
- Representation Invariance and Allocation: When Subgroup Balance Matters
- FBA2D: Frequency-based Black-box Attack for AI-generated Image Detection
- KD-OCT: Efficient Knowledge Distillation for Clinical-Grade Retinal OCT Classification
- Meta Lattice: Model Space Redesign for Cost-Effective Industry-Scale Ads Recommendations
- Quasi-Recurrent Neural Networks
- DOCTOR: A Simple Method for Detecting Misclassification Errors
- See More, Change Less: Anatomy-Aware Diffusion for Contrast Enhancement
- Enhanced Chest Disease Classification Using an Improved CheXNet Framework with EfficientNetV2-M and Optimization-Driven Learning
- Precise Liver Tumor Segmentation in CT Using a Hybrid Deep Learning-Radiomics Framework
- Integrating Multi-scale and Multi-filtration Topological Features for Medical Image Classification
- R2MF-Net: A Recurrent Residual Multi-Path Fusion Network for Robust Multi-directional Spine X-ray Segmentation
- Deep Back-Projection Networks For Super-Resolution
- A Closer Look at Spatiotemporal Convolutions for Action Recognition
- Leveraging Pre-trained Neural Network Models for the Classification of Tumor Cells Analyzed by Label-free Phase Holotomographic Microscopy
- Embodied Referring Expression Comprehension in Human-Robot Interaction
- Neural expressiveness for beyond importance model compression
- Automated Deep Learning Estimation of Anthropometric Measurements for Preparticipation Cardiovascular Screening
- Phase-OTDR Event Detection Using Image-Based Data Transformation and Deep Learning
- CLUENet: Cluster Attention Makes Neural Networks Have Eyes
- Bridging spatial awareness and global context in medical image segmentation
- Wasserstein distance based semi-supervised manifold learning and application to GNSS multi-path detection
- Performance Evaluation of Deep Learning for Tree Branch Segmentation in Autonomous Forestry Systems
- CNN on `Top': In Search of Scalable & Lightweight Image-based Jet Taggers
- Reconstructing KV Caches with Cross-layer Fusion For Enhanced Transformers
- Parameter-Efficient Augment Plugin for Class-Incremental Learning
- A Hybrid Deep Learning Framework with Explainable AI for Lung Cancer Classification with DenseNet169 and SVM
- Defense That Attacks: How Robust Models Become Better Attackers
- Conformal Correction for Efficiency May be at Odds with Entropy
- TGDD: Trajectory Guided Dataset Distillation with Balanced Distribution
- Uncertainty Reasoning with Photonic Bayesian Machines
- GRASP: Guided Residual Adapters with Sample-wise Partitioning
- ViT3: Unlocking Test-Time Training in Vision
- Neural Networks for Predicting Permeability Tensors of 2D Porous Media: Comparison of Convolution- and Transformer-based Architectures
- Directed evolution algorithm drives neural prediction
- VFM-ISRefiner: Towards Better Adapting Vision Foundation Models for Interactive Segmentation of Remote Sensing Images
- Rethinking Lung Cancer Screening: AI Nodule Detection and Diagnosis Outperforms Radiologists, Leading Models, and Standards Beyond Size and Growth
- MIMM-X: Disentangling Spurious Correlations for Medical Image Analysis
- Robust Image Self-Recovery against Tampering using Watermark Generation with Pixel Shuffling
- Relation-Aware Global Attention for Person Re-identification
- From Compound Figures to Composite Understanding: Developing a Multi-Modal LLM from Biomedical Literature with Medical Multiple-Image Benchmarking and Validation
- Stacked Ensemble of Fine-Tuned CNNs for Knee Osteoarthritis Severity Grading
- The Age-specific Alzheimer 's Disease Prediction with Characteristic Constraints in Nonuniform Time Span
- Temporal Generative Adversarial Nets with Singular Value Clipping
- PFF-Net: Patch Feature Fitting for Point Cloud Normal Estimation
- MetaRank: Task-Aware Metric Selection for Model Transferability Estimation
- Guaranteed Optimal Compositional Explanations for Neurons
- Open Vocabulary Compositional Explanations for Neuron Alignment
- Adversarial Multi-Task Learning for Liver Tumor Segmentation, Dynamic Enhancement Regression, and Classification
- HVAdam: A Full-Dimension Adaptive Optimizer
- LLM-Driven Transient Stability Assessment: From Automated Simulation to Neural Architecture Design
- LiMT: A Multi-task Liver Image Benchmark Dataset
- Frequency Bias Matters: Diving into Robust and Generalized Deep Image Forgery Detection
- An Anatomy Aware Hybrid Deep Learning Framework for Lung Cancer Tumor Stage Classification
- Development of a fully deep learning model to improve the reproducibility of sector classification systems for predicting unerupted maxillary canine likelihood of impaction
- GRIT-LP: Graph Transformer with Long-Range Skip Connection and Partitioned Spatial Graphs for Accurate Ice Layer Thickness Prediction
- Optimize transfer learning for lung diseases in bronchoscopy using a new concept: sequential fine-tuning
- DL-CapsNet: A Deep and Light Capsule Network
- Compact neural networks for astronomy with optimal transport bias correction
- Cost-Sensitive Conformal Training with Provably Controllable Learning Bounds
- Dual-Path Knowledge-Augmented Contrastive Alignment Network for Spatially Resolved Transcriptomics
- A Priori Assessment of Rotational Invariance in Multiscale Convolutional Neural Network-Based Subgrid-Scale Model for Wall-Bounded Turbulent Flows
- A Diversity-optimized Deep Ensemble Approach for Accurate Plant Leaf Disease Detection
- Enhancing Adversarial Transferability through Block Stretch and Shrink
- MRI Super-Resolution with Deep Learning: A Comprehensive Survey
- Membership Inference Attacks Beyond Overfitting
- An Image Is Worth Ten Thousand Words: Verbose-Text Induction Attacks on VLMs
- FastSurfer-CC: A robust, accurate, and comprehensive framework for corpus callosum morphometry
- A Review of Machine Learning for Cavitation Intensity Recognition in Complex Industrial Systems
- FunnyNodules: A Customizable Medical Dataset Tailored for Evaluating Explainable AI
- Rotation Equivariant CNNs for Digital Pathology
- A Dataset and Baseline for Deep Learning-Based Visual Quality Inspection in Remanufacturing
- XNOR-Net++: Improved Binary Neural Networks
- Robust Client-Server Watermarking for Split Federated Learning
- Accuracy is Not Enough: Poisoning Interpretability in Federated Learning via Color Skew
- Semi-Supervised Multi-Task Learning for Interpretable Quality As- sessment of Fundus Images
- Efficient Neural Architecture Search via Parameter Sharing
- H-CNN-ViT: A Hierarchical Gated Attention Multi-Branch Model for Bladder Cancer Recurrence Prediction
- Spatially Adaptive Computation Time for Residual Networks
- SAGE: Saliency-Guided Contrastive Embeddings
- LAYA: Layer-wise Attention Aggregation for Interpretable Depth-Aware Neural Networks
- Neural Architecture Search with Reinforcement Learning
- Parallel Separable 3D Convolution for Video and Volumetric Data Understanding
- Progressive Neural Architecture Search
- A comparison of deep machine learning algorithms in COVID-19 disease\n diagnosis
- AGGRNet: Selective Feature Extraction and Aggregation for Enhanced Medical Image Classification
- MTMed3D: A Multi-Task Transformer-Based Model for 3D Medical Imaging
- Model Inversion Attack Against Deep Hashing
- Dynamic Parameter Optimization for Highly Transferable Transformation-Based Attacks
- Intelligent Collaborative Optimization for Rubber Tyre Film Production Based on Multi-path Differentiated Clipping Proximal Policy Optimization
- BackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-tuning
- FedSDA: Federated Stain Distribution Alignment for Non-IID Histopathological Image Classification
- D-GAP: Improving Out-of-Domain Robustness via Dataset-Agnostic and Gradient-Guided Augmentation in Amplitude and Pixel Spaces
- Virtual Width Networks
- Machine-Learning Based Detection of Coronary Artery Calcification Using Synthetic Chest X-Rays
- MPCGNet: A Multiscale Feature Extraction and Progressive Feature Aggregation Network Using Coupling Gates for Polyp Segmentation
- Algorithms Trained on Normal Chest X-rays Can Predict Health Insurance Types
- Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration
- 2.5D Transformer: An Efficient 3D Seismic Interpolation Method without Full 3D Training
- SMoFi: Step-wise Momentum Fusion for Split Federated Learning on Heterogeneous Data
- When Thinking Pays Off: Incentive Alignment for Human-AI Collaboration
- Federated Learning for Pediatric Pneumonia Detection: Enabling Collaborative Diagnosis Without Sharing Patient Data
- Improve Contrastive Clustering Performance by Multiple Fusing-Augmenting ViT Blocks
- Beyond One-Way Pruning: Bidirectional Pruning-Regrowth for Extreme Accuracy-Sparsity Tradeoff
- A Generative Adversarial Approach to Adversarial Attacks Guided by Contrastive Language-Image Pre-trained Model
- REASON: Probability map-guided dual-branch fusion framework for gastric content assessment
- Towards High Performance Video Object Detection for Mobiles
- Range Asymmetric Numeral Systems-Based Lightweight Intermediate Feature Compression for Split Computing of Deep Neural Networks
- ChexFract: From General to Specialized -- Enhancing Fracture Description Generation
- Data Descriptions from Large Language Models with Influence Estimation
- Misaligned by Design: Incentive Failures in Machine Learning
- EvoPS: Evolutionary Patch Selection for Whole Slide Image Analysis in Computational Pathology
- SelectScale: Mining More Patterns from Images via Selective and Soft Dropout
- Fair Bayesian Data Selection via Generalized Discrepancy Measures
- Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation
- Preparation of Fractal-Inspired Computational Architectures for Advanced Large Language Model Analysis
- Identity Card Presentation Attack Detection: A Systematic Review
- MACMD: Multi-dilated Contextual Attention and Channel Mixer Decoding for Medical Image Segmentation
- Sharing the Learned Knowledge-base to Estimate Convolutional Filter Parameters for Continual Image Restoration
- Multi-period Learning for Financial Time Series Forecasting
- NeuroFlex: Column-Exact ANN-SNN Co-Execution Accelerator with Cost-Guided Scheduling
- Learning Fourier shapes to probe the geometric world of deep neural networks
- Comparative Study of CNN Architectures for Binary Classification of Horses and Motorcycles in the VOC 2008 Dataset
- MedDChest: A Content-Aware Multimodal Foundational Vision Model for Thoracic Imaging
- Convolutional Fully-Connected Capsule Network (CFC-CapsNet): A Novel and Fast Capsule Network
- SAAIPAA: Optimizing aspect-angles-invariant physical adversarial attacks on SAR target recognition models
- C3-Diff: Super-resolving Spatial Transcriptomics via Cross-modal Cross-content Contrastive Diffusion Modelling
- Purrturbed but Stable: Human-Cat Invariant Representations Across CNNs, ViTs and Self-Supervised ViTs
- GAFD-CC: Global-Aware Feature Decoupling with Confidence Calibration for OOD Detection
- VesSAM: Efficient Multi-Prompting for Segmenting Complex Vessel
- Transformers as Intrinsic Optimizers: Forward Inference through the Energy Principle
- Weakly Supervised Pneumonia Localization from Chest X-Rays Using Deep Neural Network and Grad-CAM Explanations
- Enhancing Adversarial Transferability by Balancing Exploration and Exploitation with Gradient-Guided Sampling
- Melanoma Classification Through Deep Ensemble Learning and Explainable AI
- CASR-Net: An Image Processing-focused Deep Learning-based Coronary Artery Segmentation and Refinement Network for X-ray Coronary Angiogram
- ODP-Bench: Benchmarking Out-of-Distribution Performance Prediction
- Exploring Landscapes for Better Minima along Valleys
- Lightweight CNN Model Hashing with Higher-Order Statistics and Chaotic Mapping for Piracy Detection and Tamper Localization
- SYNAPSE-Net: A Unified Framework with Lesion-Aware Hierarchical Gating for Robust Segmentation of Heterogeneous Brain Lesions
- VISAT: Benchmarking Adversarial and Distribution Shift Robustness in Traffic Sign Recognition with Visual Attributes
- FaCT: Faithful Concept Traces for Explaining Neural Network Decisions
- Next-Step Conditioned Deep Convolutional Neural Networks Improve Protein Secondary Structure Prediction
- Multi-Residual Networks: Improving the Speed and Accuracy of Residual Networks
- Unsupervised Sparse Dirichlet-Net for Hyperspectral Image Super-Resolution
- FD-MobileNet: Improved MobileNet with a Fast Downsampling Strategy
- APE-GAN: Adversarial Perturbation Elimination with GAN
- Train on Validation: Squeezing the Data Lemon
- Extrapolation for Large-batch Training in Deep Learning
- An interpretable deep hierarchical semantic convolutional neural network for lung nodule malignancy classification
- Data augmentation using learned transformations for one-shot medical image segmentation
- Applications of machine learning in gravitational-wave research with current interferometric detectors
- Sequence-SOD: Bio-inspired Sequence-aware Spiking Object Detection for Event Cameras
- Dynamic Parameterization Is Not Dynamic Inference
- Gradually Updated Neural Networks for Large-Scale Image Recognition
- Deep Interest Network for Click-Through Rate Prediction
- Mixture-of-Depths Attention
- Highrisk Prediction from Electronic Medical Records via Deep Attention Networks
- Fine-Grained Neural Architecture Search
- Multimodal Emotion Recognition for One-Minute-Gradual Emotion Challenge
- Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
- Learning Channel Inter-dependencies at Multiple Scales on Dense Networks for Face Recognition
- PRISM-Net: Patient-specific reference-guided inter-breast symmetry matching for three-class breast DCE-MRI classification
- To understand deep learning we need to understand kernel learning
- Knowledge Concentration: Learning 100K Object Classifiers in a Single CNN
- Gated-SCNN: Gated Shape CNNs for Semantic Segmentation
- The Pitfalls of Simplicity Bias in Neural Networks
- A Statistical Approach to Assessing Neural Network Robustness
- Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
- MAPS: A Synthetic Dataset for Probing Vision Models in a Controlled 3D Scene Space
- Approximate Fisher Information Matrix to Characterise the Training of Deep Neural Networks
- ESFNet: Efficient Network for Building Extraction from High-Resolution Aerial Images
- Deep Gradient Projection Networks for Pan-sharpening
- MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
- FractalNet: Ultra-Deep Neural Networks without Residuals
- Deep Learning Seismic Substructure Detection using the Frozen Gaussian Approximation
- Self-Supervised Text-Vision Alignment for Automated Brain MRI Abnormality Detection: A Multicenter Study (ALIGN Study)
- Selective Diabetic Retinopathy Screening with Accuracy-Weighted Deep Ensembles and Entropy-Guided Abstention
- Training Across Reservoirs: Using Numerical Differentiation To Couple Trainable Networks With Black-Box Reservoirs
- FT-ARM: Fine-Tuned Agentic Reflection Multimodal Language Model for Pressure Ulcer Severity Classification with Reasoning
- Aggregation Hides Out-of-Distribution Generalization Failures from Spurious Correlations
- SESR: Single Image Super Resolution with Recursive Squeeze and Excitation Networks
- Adversarial Attacks with Time-Scale Representations
- Send Less, Save More: Energy-Efficiency Benchmark of Embedded CNN Inference vs. Data Transmission in IoT
- Deep Feature Optimization for Enhanced Fish Freshness Assessment
- Do Convolutional Networks need to be Deep for Text Classification ?
- ResNet: Enabling Deep Convolutional Neural Networks through Residual Learning
- PLDC‐Net: A Domain‐Specific Base Model for Plant Leaf Disease Classification Domain Adaptation Tasks
- Adversarial Policy Gradient for Deep Learning Image Augmentation
- CURVETE: Curriculum Learning and Progressive Self-supervised Training for Medical Image Classification
- Model-Behavior Alignment under Flexible Evaluation: When the Best-Fitting Model Isn't the Right One
- Implicit Modeling for Transferability Estimation of Vision Foundation Models
- UGAE: Unified Geometry and Attribute Enhancement for G-PCC Compressed Point Clouds
- What Do We Understand About Convolutional Networks?
- Robust Atypical Mitosis Classification with DenseNet121: Stain-Aware Augmentation and Hybrid Loss for Domain Generalization
- Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation
- Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries
- Image Restoration Using Deep Regulated Convolutional Networks
- MAGIC-Flow: Multiscale Adaptive Conditional Flows for Generation and Interpretable Classification
- WhaleVAD-BPN: Improving Baleen Whale Call Detection with Boundary Proposal Networks and Post-processing Optimisation
- Neural Mutual Information Estimation with Vector Copulas
- Do Vision Models Encode Object-Level Semantic Relatedness? A Cognitive Psychology-Inspired Benchmark
- Deep Learning Based Domain Adaptation Methods in Remote Sensing: A Comprehensive Survey
- Attentive Convolution: Unifying the Expressivity of Self-Attention with Convolutional Efficiency
- Dynamic Weight Adjustment for Knowledge Distillation: Leveraging Vision Transformer for High-Accuracy Lung Cancer Detection and Real-Time Deployment
- The Tail Tells All: Estimating Model-Level Membership Inference Vulnerability Without Reference Models
- Revisiting the Relation Between Robustness and Universality
- Automatic 3D Cardiovascular MR Segmentation with Densely-Connected Volumetric ConvNets
- FedMicro-IDA: A Federated Learning and Microservices-based Framework for IoT Data Analytics
- Towards Strong Certified Defense with Universal Asymmetric Randomization
- Explainable Deep Learning in Medical Imaging: Brain Tumor and Pneumonia Detection
- Learning Task-Agnostic Representations through Multi-Teacher Distillation
- Towards In-Situ Failure Assessment: Deep Learning on DIC Results for Laminated Composites
- Hybrid Deep Learning Framework for Enhanced Diabetic Retinopathy Detection: Integrating Traditional Features with AI-driven Insights
- AWSPNet: Attention-based Dual-Tree Wavelet Scattering Prototypical Network for MIMO Radar Target Recognition and Jamming Suppression
- Black-Box Evasion Attacks on Data-Driven Open RAN Apps: Tailored Design and Experimental Evaluation
- Adaptive transfer learning for surgical tool presence detection in laparoscopic videos through gradual freezing fine-tuning
- Automatic Classification of Circulating Blood Cell Clusters based on Multi-channel Flow Cytometry Imaging
- Enhancing Cross-Patient Generalization in AI-Based Parkinson s Disease Detection
- Benchmarking Out-of-Distribution Detection for Plankton Recognition: A Systematic Evaluation of Advanced Methods in Marine Ecological Monitoring
- ZACH-ViT: A Zero-Token Vision Transformer with ShuffleStrides Data Augmentation for Robust Lung Ultrasound Classification
- The Impact of Concept Explanations and Interventions on Human-Machine Collaboration
- Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads
- SGDR: Stochastic Gradient Descent with Warm Restarts
- First Attentions Last: Better Exploiting First Attentions for Efficient Transformer Training
- Selective Labeling with False Discovery Rate Control
- BinCtx: Multi-Modal Representation Learning for Robust Android App Behavior Detection
- When Flatness Does (Not) Guarantee Adversarial Robustness
- Optical Computation-in-Communication enables low-latency, high-fidelity perception in telesurgery
- Generalist++: A Meta-learning Framework for Mitigating Trade-off in Adversarial Training
- MS-GAGA: Metric-Selective Guided Adversarial Generation Attack
- Metronome: Efficient Scheduling for Periodic Traffic Jobs with Network and Priority Awareness
- Local Background Features Matter in Out-of-Distribution Detection
- SDGraph: Multi-Level Sketch Representation Learning by Sparse-Dense Graph Architecture
- MultiFoodhat: A potential new paradigm for intelligent food quality inspection
- PanoTPS-Net: Panoramic Room Layout Estimation via Thin Plate Spline Transformation
- Benchmarking Deep Learning Models for Laryngeal Cancer Staging Using the LaryngealCT Dataset
- MCE: Towards a General Framework for Handling Missing Modalities under Imbalanced Missing Rates
- Learning from Disagreement: A Group Decision Simulation Framework for Robust Medical Image Segmentation
- LocalViT: Analyzing Locality in Vision Transformers
- Mathematical Modeling and Convergence Analysis of Deep Neural Networks with Dense Layer Connectivities in Deep Learning
- A Novel lightweight Convolutional Neural Network, ExquisiteNetV2
- Provable Watermarking for Data Poisoning Attacks
- MambaH-Fit: Rethinking Hyper-surface Fitting-based Point Cloud Normal Estimation via State Space Modelling
- Online Topological Localization for Navigation Assistance in Bronchoscopy
- Non-Rigid Structure-from-Motion via Differential Geometry with Recoverable Conformal Scale
- Structured Output Regularization: a framework for few-shot transfer learning
- Deep Neural Networks Inspired by Differential Equations
- MeSH: Memory-as-State-Highways for Recursive Transformers
- How NOT to benchmark your SITE metric: Beyond Static Leaderboards and Towards Realistic Evaluation
- TreeNet: Layered Decision Ensembles
- Machine Learning Detection of Road Surface Conditions: A Generalizable Model using Traffic Cameras and Weather Data
- Knowledge Distillation Detection for Open-weights Models
- Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation
- Multimodal Learning with Augmentation Techniques for Natural Disaster Assessment
- ELMF4EggQ: Ensemble Learning with Multimodal Feature Fusion for Non-Destructive Egg Quality Assessment
- Non-Local Representation based Mutual Affine-Transfer Network for Photorealistic Stylization
- Advances in Medical Image Segmentation: A Comprehensive Survey with a Focus on Lumbar Spine Applications
- MultiFair: Multimodal Balanced Fairness-Aware Medical Classification with Dual-Level Gradient Modulation
- Guiding Mixture-of-Experts with Temporal Multimodal Interactions
- MetaChest: Generalized few-shot learning of pathologies from chest X-rays
- AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs
- Traumatic Brain Injury Segmentation using an Ensemble of Encoder-decoder Models
- VNODE: A Piecewise Continuous Volterra Neural Network
- BERT Bi-modal self-supervised learning for crop classification using Sentinel-2 and Planetscope
- Latent Transformations for Object View Points Synthesis
- NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image
- LORT: Locally Refined Convolution and Taylor Transformer for Monaural Speech Enhancement
- PVTAdpNet: Polyp Segmentation using Pyramid vision transformer with a novel Adapter block
- Virtual Nodes based Heterogeneous Graph Convolutional Neural Network for Efficient Long-Range Information Aggregation
- Evaluating the Impact of Radiographic Noise on Chest X-ray Semantic Segmentation and Disease Classification Using a Scalable Noise Injection Framework
- Imaging-Based Mortality Prediction in Patients with Systemic Sclerosis
- Temporal Generalization: A Reality Check
- S3F-Net: A Multi-Modal Approach to Medical Image Classification via Spatial-Spectral Summarizer Fusion Network
- Graph Your Own Prompt
- Deep Learning for Oral Health: Benchmarking ViT, DeiT, BEiT, ConvNeXt, and Swin Transformer
- AudioFuse: Unified Spectral-Temporal Learning via a Hybrid ViT-1D CNN Architecture for Robust Phonocardiogram Classification
- Targeted perturbations reveal brain-like local coding axes in robustified, but not standard, ANN-based brain models
- Hemorica: A Comprehensive CT Scan Dataset for Automated Brain Hemorrhage Classification, Segmentation, and Detection
- Seeing Isn't Believing: Context-Aware Adversarial Patch Synthesis via Conditional GAN
- TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses
- Generalized Bayesian Posterior Expectation Distillation for Deep Neural Networks
- Adaptive Dual-Mode Distillation with Incentive Schemes for Scalable, Heterogeneous Federated Learning on Non-IID Data
- HierLight-YOLO: A Hierarchical and Lightweight Object Detection Network for UAV Photography
- Ground-Truthing AI Energy Consumption: Validating CodeCarbon Against External Measurements
- Mammo-CLIP Dissect: A Framework for Analysing Mammography Concepts in Vision-Language Models
- Single Image Depth Estimation Trained via Depth from Defocus Cues
- Generative Model Inversion Through the Lens of the Manifold Hypothesis
- Spectral Norm Regularization for Improving the Generalizability of Deep Learning
- Don't Trust the AI Ecosystem: Analyzing Privacy Leakage in Compromised Open-Source Components
- Towards Practical Algorithm Selection for Unsupervised Domain Adaptation in Medical Imaging
- DS@GT ARC at ImageCLEFmedical 2026: Architectural Diversity for Concept Detection and Foundation-Model Scaling for Caption Prediction in Medical Image Analysis
- Lets keep it simple, Using simple architectures to outperform deeper and\n more complex architectures
- Multi-Head Attention Residuals
- Learning from Compressed CT: Feature Attention Style Transfer and Structured Factorized Projections for Resource-Efficient Medical Image Analysis
- mHC-lite: You Don't Need 20 Sinkhorn-Knopp Iterations
- EinsteinNet and state-of-the-art ML models for android-based orange classification: Integration, evaluation, and deployment
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- A transformer-based multi-task deep learning model for urban livability evaluation by fusing remote sensing and textual geospatial data
- Detecting Positive Selection by Modeling Structure Within Images of Genetic Variation
- Unbounded Output Networks for Classification
- Two-Layer Neural Networks for Partial Differential Equations: Optimization and Generalization Theory
- MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation
- Not All Ops Are Created Equal!
- Predicting ventilation from single breathing phase non‐contrast CT using Swin Transformers
- Orthogonal and Idempotent Transformations for Learning Deep Neural Networks
- A Multi-Objective Evaluation Framework for Analyzing Utility-Fairness Trade-Offs in Machine Learning Systems
- Imaging through glass diffusers using densely connected convolutional networks
- Fast Neural Architecture Construction using EnvelopeNets
- Assessing the Alignment of Popular CNNs to the Brain for Valence Appraisal
- A Validation Strategy for Deep Learning Models: Evaluating and Enhancing Robustness
- Spectral Signature Mapping from RGB Imagery for Terrain-Aware Navigation
- MolMark: Safeguarding Molecular Structures through Learnable Atom-Level Watermarking
- MER-Inspector: Assessing model extraction risks from an attack-agnostic perspective
- FloraSyntropy-Net: Scalable Deep Learning with Novel FloraSyntropy Archive for Large-Scale Plant Disease Diagnosis
- Latent Danger Zone: Distilling Unified Attention for Cross-Architecture Black-box Attacks
- Beyond Diagnosis: Evaluating Multimodal LLMs for Pathology Localization in Chest Radiographs
- Joint Memory Frequency and Computing Frequency Scaling for Energy-efficient DNN Inference
- Automatic breast cancer grading in lymph nodes using a deep neural network
- Deep Clustering for Unsupervised Learning of Visual Features
- Multiscale Hierarchical Convolutional Networks
- 3DContextNet: K-d Tree Guided Hierarchical Learning of Point Clouds Using Local and Global Contextual Cues
- RADE for Land Mobile Radio: A Neural Codec for Transmission of Speech over Baseband FM Radio Channels
- The SAGES Critical View of Safety Challenge: A Global Benchmark for AI-Assisted Surgical Quality Assessment
- IPF-RDA: An Information-Preserving Framework for Robust Data Augmentation
- Explainable Deep Learning for Cataract Detection in Retinal Images: A Dual-Eye and Knowledge Distillation Approach
- A multi-temporal multi-spectral attention-augmented deep convolution neural network with contrastive learning for crop yield prediction
- Generating Part-Based Global Explanations Via Correspondence
- Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception
- Leveraging Geometric Visual Illusions as Perceptual Inductive Biases for Vision Models
- Limitations of Public Chest Radiography Datasets for Artificial Intelligence: Label Quality, Domain Shift, Bias and Evaluation Challenges
- Interleaved Group Convolutions for Deep Neural Networks
- Self Identity Mapping
- DiracNets: Training Very Deep Neural Networks Without Skip-Connections
- On the Out-of-Distribution Backdoor Attack for Federated Learning
- Natural Language Inference over Interaction Space: ICLR 2018 Reproducibility Report
- Robot-Assisted Feeding: Generalizing Skewering Strategies across Food Items on a Realistic Plate
- HQCNN: A Hybrid Quantum-Classical Neural Network for Medical Image Classification
- IrisNet: Deep Learning for Automatic and Real-time Tongue Contour Tracking in Ultrasound Video Data using Peripheral Vision
- Sparse Attentive Backtracking: Temporal CreditAssignment Through Reminding
- GhostNetV3-Small: A Tailored Architecture and Comparative Study of Distillation Strategies for Tiny Images
- The Quest for Universal Master Key Filters in DS-CNNs
- GraphDerm: Fusing Imaging, Physical Scale, and Metadata in a Population-Graph Classifier for Dermoscopic Lesions
- Self-Attention Capsule Networks for Object Classification
- The Impact of Skin Tone Label Granularity on the Performance and Fairness of AI Based Dermatology Image Classification Models
- Gaze Authentication: Factors Influencing Authentication Performance
- A Comparison of Selected Image Transformation Techniques for Malware Classification
- Learning to Write Stylized Chinese Characters by Reading a Handful of Examples
- FedBiF: Communication-Efficient Federated Learning via Bits Freezing
- An Autoencoder and Vision Transformer-based Interpretability Analysis of the Differences in Automated Staging of Second and Third Molars
- Exploring Weight Symmetry in Deep Neural Networks
- Multigrid Neural Architectures
- NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability
- MetaLLMix : An XAI Aided LLM-Meta-learning Based Approach for Hyper-parameters Optimization
- CoAtNeXt:An Attention-Enhanced ConvNeXtV2-Transformer Hybrid Model for Gastric Tissue Classification
- CoSwin: Convolution Enhanced Hierarchical Shifted Window Attention For Small-Scale Vision
- Adversarial Examples Make Strong Poisons
- MultiGrain: a unified image embedding for classes and instances
- Combining Audio and Non-Audio Inputs in Evolved Neural Networks for Ovenbird
- RoentMod: A Synthetic Chest X-Ray Modification Model to Identify and Correct Image Interpretation Model Shortcuts
- VRAE: Vertical Residual Autoencoder for License Plate Denoising and Deblurring
- Label Smoothing++: Enhanced Label Regularization for Training Neural Networks
- Data Augmentation Generative Adversarial Networks
- Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning
- Generating Transferrable Adversarial Examples via Local Mixing and Logits Optimization for Remote Sensing Object Recognition
- Spectral and Rhythm Feature Performance Evaluation for Category and Class Level Audio Classification with Deep Convolutional Neural Networks
- AI Oriented Large-Scale Video Management for Smart City: Technologies, Standards and Beyond
- XBusNet: Text-Guided Breast Ultrasound Segmentation via Multimodal Vision-Language Learning
- Automated Radiographic Total Sharp Score (ARTSS) in Rheumatoid Arthritis: A Solution to Reduce Inter-Intra Reader Variation and Enhancing Clinical Practice
- Imitative Membership Inference Attack
- MRI-Based Brain Tumor Detection through an Explainable EfficientNetV2 and MLP-Mixer-Attention Architecture
- Detection of trade in products derived from threatened species using machine learning and a smartphone
- Tackling the Noisy Elephant in the Room: Label Noise-robust Out-of-Distribution Detection via Loss Correction and Low-rank Decomposition
- IGAff: Benchmarking Adversarial Iterative and Genetic Affine Algorithms on Deep Neural Networks
- A general framework for knowledge integration in machine learning for electromagnetic scattering using quasinormal modes
- Challenges in Deep Learning-Based Small Organ Segmentation: A Benchmarking Perspective for Medical Research with Limited Datasets
- High Utilization Energy-Aware Real-Time Inference Deep Convolutional Neural Network Accelerator
- Surformer v2: A Multimodal Classifier for Surface Understanding from Touch and Vision
- Deep Gamblers: Learning to Abstain with Portfolio Theory
- NSML: A Machine Learning Platform That Enables You to Focus on Your Models
- Insights from Gradient Dynamics: Gradient Autoscaled Normalization
- Prototype-Guided Robust Learning against Backdoor Attacks
- Deep Learning for High Speed Optical Coherence Elastography with a Fiber Scanning Endoscope
- Deep Learning for Low-Dose CT Denoising
- Agile Amulet: Real-Time Salient Object Detection with Contextual Attention
- Silent Until Sparse: Backdoor Attacks on Semi-Structured Sparsity
- DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling
- Residual Squeeze VGG16
- BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization
- An Investigation of Visual Foundation Models Robustness
- A Continuous Encoding-Based Representation for Efficient Multi-Fidelity Multi-Objective Neural Architecture Search
- HydroVision: Predicting Optically Active Parameters in Surface Water Using Computer Vision
- Systematic Integration of Attention Modules into CNNs for Accurate and Generalizable Medical Image Diagnosis
- A Multimodal Cross-View Model for Predicting Postoperative Neck Pain in Cervical Spondylosis Patients
- Towards deep-learning based detection and quantification of intestinal metaplasia on digitized gastric biopsies: a multi-expert comparative study
- Handling imbalance and few-sample size in ML based Onion disease classification
- Challenges and Lessons from MIDOG 2025: A Two-Stage Approach to Domain-Robust Mitotic Figure Detection
- Expandable Residual Approximation for Knowledge Distillation
- Investigating Transfer Learning Capabilities of Vision Transformers and CNNs by Fine-Tuning a Single Trainable Block
- Lung cancer identification: a review on detection and classification
- Why Pool When You Can Flow? Active Learning with GFlowNets
- Application of discrete Ricci curvature in pruning randomly wired neural networks: A case study with chest x-ray classification of COVID-19
- Re-ID done right: towards good practices for person re-identification
- MSSInvNet: a multi-component surface-wave dispersion spectrogram inversion network
- MoE-Health: A Mixture of Experts Framework for Robust Multimodal Healthcare Prediction
- Solutions for Mitotic Figure Detection and Atypical Classification in MIDOG 2025
- Activation Subspaces for Out-of-Distribution Detection
- Multi-Method Ensemble for Out-of-Distribution Detection
- Scalable Equilibrium Propagation via Intermediate Error Signals for Deep Convolutional CRNNs
- A Simple Cache Model for Image Recognition
- Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models
- E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections
- Domain Adaptation Techniques for Natural and Medical Image Classification
- Digital Scale: Open-Source On-Device BMI Estimation from Smartphone Camera Images Trained on a Large-Scale Real-World Dataset
- The End-of-End-to-End: A Video Understanding Pentathlon Challenge (2020)
- RadGS-Reg: Registering Spine CT with Biplanar X-rays via Joint 3D Radiative Gaussians Reconstruction and 3D/3D Registration
- Exploring Machine Learning and Language Models for Multimodal Depression Detection
- Mix, Align, Distil: Reliable Cross-Domain Atypical Mitosis Classification
- Coresets from Trajectories: Selecting Data via Correlation of Loss Differences
- NM-Hebb: Coupling Local Hebbian Plasticity with Metric Learning for More Accurate and Interpretable CNNs
- The Art of Hide and Seek: Making Pickle-Based Model Supply Chain Poisoning Stealthy Again
- EffNetViTLoRA: An Efficient Hybrid Deep Learning Approach for Alzheimer's Disease Diagnosis
- M3HG: Multimodal, Multi-scale, and Multi-type Node Heterogeneous Graph for Emotion Cause Triplet Extraction in Conversations
- A Deep Learning Application for Psoriasis Detection
- Bladder Cancer Diagnosis with Deep Learning: A Multi-Task Framework and Online Platform
- FCR: Investigating Generative AI models for Forensic Craniofacial Reconstruction
- Statistical Arbitrage in Options Markets by Graph Learning and Synthetic Long Positions
- Img2ST-Net: Efficient High-Resolution Spatial Omics Prediction from Whole Slide Histology Images via Fully Convolutional Image-to-Image Learning
- Mitigating Data Exfiltration Attacks through Layer-Wise Learning Rate Decay Fine-Tuning
- Maintaining Discrimination and Fairness in Class Incremental Learning
- Large Batch Training Does Not Need Warmup
- One Shot vs. Iterative: Rethinking Pruning Strategies for Model Compression
- CLoE: Curriculum Learning on Endoscopic Images for Robust MES Classification
- Skin Cancer Classification: Hybrid CNN-Transformer Models with KAN-Based Fusion
- Make Thunderbolts Less Frightening -- Predicting Extreme Weather Using\n Deep Learning
- Hierarchical knowledge guided fault intensity diagnosis of complex industrial systems
- TriQDef: Disrupting Semantic and Gradient Alignment to Prevent Adversarial Patch Transferability in Quantized Neural Networks
- Mitigating Adversarial Effects Through Randomization
- Hierarchical Graph Feature Enhancement with Adaptive Frequency Modulation for Visual Recognition
- NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models
- Analysis on DeepLabV3+ Performance for Automatic Steel Defects Detection
- Privacy-enhancing Sclera Segmentation Benchmarking Competition: SSBC 2025
- Understanding the Disharmony between Dropout and Batch Normalization by Variance Shift
- Lameness detection in dairy cows using pose estimation and bidirectional LSTMs
- EvTurb: Event Camera Guided Turbulence Removal
- Alternating Approach-Putt Models for Multi-Stage Speech Enhancement
- Hierarchical Representations for Efficient Architecture Search
- Explainable AI Technique in Lung Cancer Detection Using Convolutional Neural Networks
- Reverse Convolution and Its Applications to Image Restoration
- MUJICA: Reforming SISR Models for PBR Material Super-Resolution via Cross-Map Attention
- Context Encoding for Semantic Segmentation
- WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localization
- Large-Small Model Collaborative Framework for Federated Continual Learning
- Automatic and standardized surgical reporting for central nervous system tumors
- Subjective and Objective Quality Assessment of Banding Artifacts on Compressed Videos
- Improving GAN Training via Binarized Representation Entropy (BRE)\n Regularization
- Deep Neural Network Calibration by Reducing Classifier Shift with Stochastic Masking
- A Classification-Aware Super-Resolution Framework for Ship Targets in SAR Imagery
- Mask & Match: Learning to Recognize Handwritten Math with Self-Supervised Attention
- Learning Geometric-Aware Quadrature Rules for Functional Minimization
- Don't Reach for the Stars: Rethinking Topology for Resilient Federated Learning
- ULU: A Unified Activation Function
- Learning from Oblivion: Predicting Knowledge Overflowed Weights via Retrodiction of Forgetting
- Advanced Multi-Architecture Deep Learning Framework for BIRADS-Based Mammographic Image Retrieval: Comprehensive Performance Analysis with Super-Ensemble Optimization
- Visual Bias and Interpretability in Deep Learning for Dermatological Image Analysis
- Automated ultrasound doppler angle estimation using deep learning
- Boosting Adversarial Transferability via Residual Perturbation Attack
- Deep learning framework for crater detection and identification on the Moon and Mars
- AttZoom: Attention Zoom for Better Visual Features
- A Non-Technical Survey on Deep Convolutional Neural Network Architectures
- Pseudo-label Induced Subspace Representation Learning for Robust Out-of-Distribution Detection
- T2UE: Generating Unlearnable Examples from Text Descriptions
- Hydra: Accurate Multi-Modal Leaf Wetness Sensing with mm-Wave and Camera Fusion
- FAIR-Pruner: Leveraging Tolerance of Difference for Flexible Automatic Layer-Wise Neural Network Pruning
- FedAPTA: Federated Multi-task Learning for Heterogeneous Devices with Adaptive Layer-wise Pruning and Task-aware Aggregation
- Tackling Ill-posedness of Reversible Image Conversion with Well-posed Invertible Network
- InfoSyncNet: Information Synchronization Temporal Convolutional Network for Visual Speech Recognition
- Forecasting West Nile virus with deep graph encoders
- M3AD: Multi-task Multi-gate Mixture of Experts for Alzheimer's Disease Diagnosis with Conversion Pattern Modeling
- Eigen Neural Network: Unlocking Generalizable Vision with Eigenbasis
- Uncertainty Quantification for Large-Scale Deep Networks via Post-StoNet Modeling
- Deep Learning for Pavement Condition Evaluation Using Satellite Imagery
- Synthesis of High-Quality Visible Faces from Polarimetric Thermal Faces using Generative Adversarial Networks
- Fusion Sampling Validation in Data Partitioning for Machine Learning
- Rethinking Backbone Design for Lightweight 3D Object Detection in LiDAR
- Towards Deeper Generative Architectures for GANs using Dense connections
- Machine learning and machine learned prediction in chest X-ray images
- Stress-Aware Resilient Neural Training
- Advancing Fetal Ultrasound Image Quality Assessment in Low-Resource Settings
- Crowding in humans is unlike that in convolutional neural networks
- Agentic Privacy-Preserving Machine Learning
- CaliMatch: Adaptive Calibration for Improving Safe Semi-supervised Learning
- Cyst-X: A Federated AI System Outperforms Clinical Guidelines to Detect Pancreatic Cancer Precursors and Reduce Unnecessary Surgery
- AI in Agriculture: A Survey of Deep Learning Techniques for Crops, Fisheries and Livestock
- MetaLab: Few-Shot Game Changer for Image Recognition
- Exposure Interpolation by Combining Model-driven and Data-driven Methods
- Convolutional-LSTM for Multi-Image to Single Output Medical Prediction
- Unlocking Interpretability for RF Sensing: A Complex-Valued White-Box Transformer
- Cascading and Proxy Membership Inference Attacks
- Evaluating Deep Learning Models for African Wildlife Image Classification: From DenseNet to Vision Transformers
- Graph neural networks for residential location choice: connection to classical logit models
- Can Foundation Models Predict Fitness for Duty?
- SuperNet -- An efficient method of neural networks ensembling
- Multi-Attention Stacked Ensemble for Lung Cancer Detection in CT Scans
- Dual-Stream Global-Local Feature Collaborative Representation Network for Scene Classification of Mining Area
- HoneyImage: Verifiable, Harmless, and Stealthy Dataset Ownership Verification for Image Models
- SkinDualGen: Prompt-Driven Diffusion for Simultaneous Image-Mask Generation in Skin Lesions
- ForCenNet: Foreground-Centric Network for Document Image Rectification
- DARTS: DenseUnet-based Automatic Rapid Tool for brain Segmentation
- EA-ViT: Efficient Adaptation for Elastic Vision Transformer
- Extreme Cardiac MRI Analysis under Respiratory Motion: Results of the CMRxMotion Challenge
- YOLO for Knowledge Extraction from Vehicle Images: A Baseline Study
- SIDE: Sparse Information Disentanglement for Explainable Artificial Intelligence
- MGHFT: Multi-Granularity Hierarchical Fusion Transformer for Cross-Modal Sticker Emotion Recognition
- Functional Gradient Boosting based on Residual Network Perception
- Deep Neural Network Architectures for Modulation Classification
- Autonomous Deep Learning: A Genetic DCNN Designer for Image Classification
- Protein Secondary Structure Prediction Using Deep Multi-scale Convolutional Neural Networks and Next-Step Conditioning
Discussions
Related