DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

2013/10/05 by Jeff Donahue, Donahue, Jeff, Yangqing Jia +11 · 358 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Multimodal Machine Learning Applications #cs.CV

paper · pdf · doi:10.48550/arxiv.1310.1531

openalex publication_date 2013/10/05 · arxiv created 2013/10/06 · arxiv updated 2013/10/08 · openalex created_date 2025/10/24 · openalex updated_date 2026/07/28

Abstract

We evaluate whether features extracted from the activation of a deep convolutional network trained in a fully supervised fashion on a large, fixed set of object recognition tasks can be re-purposed to novel generic tasks. Our generic tasks may differ significantly from the originally trained tasks and there may be insufficient labeled or unlabeled data to conventionally train or adapt a deep architecture to the new tasks. We investigate and visualize the semantic clustering of deep convolutional features with respect to a variety of such tasks, including scene recognition, domain adaptation, and fine-grained recognition challenges. We compare the efficacy of relying on various network levels to define a fixed feature, and report novel results that significantly outperform the state-of-the-art on several important vision challenges. We are releasing DeCAF, an open-source implementation of these deep convolutional activation features, along with all associated network parameters to enable vision researchers to be able to conduct experimentation with deep representations across a range of visual concept learning paradigms.

Citations

• Gradient-based learning applied to document recognition
• Backpropagation Applied to Handwritten Zip Code Recognition
• ImageNet Large Scale Visual Recognition Challenge

Cited by

• Greedy dynamical meta-learning
• Data-Centric Visual Development for Self-Driving Labs
• Bridging Lifelong and Multi-Task Representation Learning via Algorithm and Complexity Measure
• Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balance
• Feature Stylization and Domain-aware Contrastive Learning for Domain Generalization
• Point Prompting: Counterfactual Tracking with Video Diffusion Models
• Mutual Learning for Hashing: Unlocking Strong Hash Functions from Weak Supervision
• Tent: Fully Test-time Adaptation by Entropy Minimization
• Accelerating Deep Neural Networks with Spatial Bottleneck Modules
• Unsupervised Domain Adaptation by Backpropagation
• Shared Neural Space: Unified Precomputed Feature Encoding for Multi-Task and Cross Domain Vision
• PAC-Bayes Analysis of Sentence Representation
• Learning to see across Domains and Modalities
• Leveraging Visual Question Answering for Image-Caption Ranking
• Convolutional Channel Features
• Weakly-Supervised Spatial Context Networks
• Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark
• Context-Aware Multipath Networks
• Joint calibration of Ensemble of Exemplar SVMs
• From handcrafted to deep local features
• Make Your Bone Great Again : A study on Osteoporosis Classification
• Hierarchical Retrieval: The Geometry and a Pretrain-Finetune Recipe
• Domain Generalization via Multidomain Discriminant Analysis
• Online Learning to Sample
• Embedding Label Structures for Fine-Grained Feature Representation
• RCoNet: Deformable Mutual Information Maximization and High-order Uncertainty-aware Learning for Robust COVID-19 Detection
• One-Shot Imitation Learning
• Unsupervised Deep Domain Adaptation for Pedestrian Detection
• Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy
• Temporal Attentive Alignment for Large-Scale Video Domain Adaptation
• Learning Transferable Features with Deep Adaptation Networks
• Learning Deep Representations of Fine-grained Visual Descriptions
• Bootstrap your own latent: A new approach to self-supervised Learning
• SpotTune: Transfer Learning through Adaptive Fine-tuning
• Recognizing American Sign Language Manual Signs from RGB-D Videos
• DISA at ImageCLEF 2014 Revised: Search-based Image Annotation with DeCAF Features
• Unlabeled Data Deployment for Classification of Diabetic Retinopathy Images Using Knowledge Transfer
• Latent Hinge-Minimax Risk Minimization for Inference from a Small Number of Training Samples
• Deep Learning for Generic Object Detection: A Survey
• CAGFuzz: Coverage-Guided Adversarial Generative Fuzzing Testing of Deep Learning Systems
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• An Extended Framework for Marginalized Domain Adaptation
• Strength from Weakness: Fast Learning Using Weak Supervision
• Analysing domain shift factors between videos and images for object detection
• Transferring GANs: generating images from limited data
• Deep Learning Face Attributes in the Wild
• Universality of Gradient Descent Neural Network Training
• Label Efficient Learning of Transferable Representations across Domains and Tasks
• CO-Optimal Transport
• LogME: Practical Assessment of Pre-trained Models for Transfer Learning
• Cross-convolutional-layer Pooling for Image Recognition
• Analyzing the Performance of Multilayer Neural Networks for Object Recognition
• Fine-grained pose prediction, normalization, and recognition
• Structured Sparse Convolutional Autoencoder
• Learning Optimal Linear Regularizers
• VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback
• MemeSequencer: Sparse Matching for Embedding Image Macros
• Regularization via Mass Transportation
• CoMET: A Contrastive-Masked Brain Foundation Model for Universal EEG Representation
• Brain-Inspired Deep Networks for Image Aesthetics Assessment
• Compositional Model based Fisher Vector Coding for Image Classification
• EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos
• Contrastively Smoothed Class Alignment for Unsupervised Domain Adaptation
• Material Classification using Neural Networks
• Deep Transfer Learning with Joint Adaptation Networks
• STAGNet: A Spatio-Temporal Graph and LSTM Framework for Accident Anticipation
• A Unified Semantic Embedding: Relating Taxonomies and Attributes
• Discriminative Noise Robust Sparse Orthogonal Label Regression-based Domain Adaptation
• Agent-Centric Representations for Multi-Agent Reinforcement Learning
• Open Set Domain Adaptation for Image and Action Recognition
• Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs
• Domain Adaptation and Image Classification via Deep Conditional Adaptation Network
• Differentially Private Continual Learning
• NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models
• The Effectiveness of Instance Normalization: a Strong Baseline for Single Image Dehazing
• ConFoc: Content-Focus Protection Against Trojan Attacks on Neural Networks
• Continual Learning in Neural Networks
• Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
• Partial Optimal Transport with Applications on Positive-Unlabeled Learning
• Compression of Deep Neural Networks on the Fly
• An Analysis of Human-centered Geolocation
• Mind the Nuisance: Gaussian Process Classification using Privileged Noise
• DART: Domain-Adversarial Residual-Transfer Networks for Unsupervised Cross-Domain Image Classification
• Defending Against Adversarial Attacks Using Random Forests
• Recovering 6D Object Pose: A Review and Multi-modal Analysis
• Robust Visual Knowledge Transfer via EDA
• Filtered Manifold Alignment
• Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time
• Deep Affordance-grounded Sensorimotor Object Recognition
• HyperSTAR: Task-Aware Hyperparameters for Deep Networks
• "Who is Driving around Me?" Unique Vehicle Instance Classification using Deep Neural Features
• GAN Memory with No Forgetting
• Fine-Grained Categorization via CNN-Based Automatic Extraction and Integration of Object-Level and Part-Level Features
• Video Summarization with Long Short-term Memory
• Learning Smooth Representation for Unsupervised Domain Adaptation
• Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation
• Rethinking Pre-training and Self-training
• Outlining the Design Space of Explainable Intelligent Systems for Medical Diagnosis
• Transferable Calibration with Lower Bias and Variance in Domain Adaptation
• On the Behavior of Convolutional Nets for Feature Extraction
• Double-level adversarial domain adaptation network for intelligent fault diagnosis
• On learning to localize objects with minimal supervision
• Understanding Black-box Predictions via Influence Functions
• SERIL: Noise Adaptive Speech Enhancement using Regularization-based Incremental Learning
• Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images
• Seeing the Big Picture: Deep Embedding with Contextual Evidences
• Patchy Image Structure Classification Using Multi-Orientation Region Transform
• Window-Object Relationship Guided Representation Learning for Generic Object Detections
• An Out-of-the-box Full-network Embedding for Convolutional Neural Networks
• cvpaper.challenge in 2016: Futuristic Computer Vision through 1,600 Papers Survey
• Group-wise Deep Co-saliency Detection
• Reconstructing A Large Scale 3D Face Dataset for Deep 3D Face Identification
• Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation
• Attention-Privileged Reinforcement Learning
• Marine Animal Classification with Correntropy Loss Based Multi-view Learning
• Pre-Training Graph Neural Networks for Generic Structural Feature Extraction
• Locality Preserving Joint Transfer for Domain Adaptation
• A transfer convolutional neural network for fault diagnosis based on ResNet-50
• Persistent Evidence of Local Image Properties in Generic ConvNets
• What makes ImageNet good for transfer learning?
• Never Stop Learning: The Effectiveness of Fine-Tuning in Robotic Reinforcement Learning
• Developing efficient transfer learning strategies for robust scene recognition in mobile robotics using pre-trained convolutional neural networks
• Zero-shot Domain Adaptation without Domain Semantic Descriptors
• Modeling Image Virality with Pairwise Spatial Transformer Networks
• Negative Margin Matters: Understanding Margin in Few-shot Classification
• CRL: Class Representative Learning for Image Classification
• Convolutional Neural Network-based Place Recognition
• Measuring and Understanding Sensory Representations within Deep Networks Using a Numerical Optimization Framework
• Visual Themes and Sentiment on Social Networks To Aid First Responders During Crisis Events
• Do Adversarially Robust ImageNet Models Transfer Better?
• Cross-domain error minimization for unsupervised domain adaptation
• From Captions to Visual Concepts and Back
• Group Based Deep Shared Feature Learning for Fine-grained Image Classification
• Interactive Knowledge Distillation
• Learning Mid-Level Features and Modeling Neuron Selectivity for Image Classification
• Deep Structured-Output Regression Learning for Computational Color Constancy
• Visual Language Modeling on CNN Image Representations
• Improve CAM with Auto-adapted Segmentation and Co-supervised Augmentation
• Visual Security Evaluation of Learnable Image Encryption Methods against Ciphertext-only Attacks
• Simple and Efficient Learning using Privileged Information
• Episodic Training for Domain Generalization
• Domain Adaptation by Maximizing Population Correlation with Neural Architecture Search
• Pretraining Techniques for Sequence-to-Sequence Voice Conversion
• From Images to Sentences through Scene Description Graphs using Commonsense Reasoning and Knowledge
• Multi-Scale Spatially-Asymmetric Recalibration for Image Classification
• End-to-End Deep Learning for Steering Autonomous Vehicles Considering Temporal Dependencies
• Multi-lingual agents through multi-headed neural networks
• Unsupervised Adversarial Graph Alignment with Graph Embedding
• OTCE: A Transferability Metric for Cross-Domain Cross-Task Representations
• Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-Time
• Towards Predicting the Likeability of Fashion Images
• Why Do Better Loss Functions Lead to Less Transferable Features?
• Engineering Deep Representations for Modeling Aesthetic Perception
• Matching Networks for One Shot Learning
• Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions
• Feature Evaluation of Deep Convolutional Neural Networks for Object Recognition and Detection
• Aggregated Residual Transformations for Deep Neural Networks
• DenseNet: Implementing Efficient ConvNet Descriptor Pyramids
• Deep Learning for Tactile Understanding From Visual and Haptic Data
• Pre-training without Natural Images
• Prior Knowledge about Attributes: Learning a More Effective Potential Space for Zero-Shot Recognition
• Look-into-Object: Self-supervised Structure Modeling for Object Recognition
• Deep Learning Techniques for Future Intelligent Cross-Media Retrieval
• Explain Images with Multimodal Recurrent Neural Networks
• Understanding Human Judgments of Causality
• Using Cross-Model EgoSupervision to Learn Cooperative Basketball Intention
• Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization
• DASC: Robust Dense Descriptor for Multi-modal and Multi-spectral Correspondence Estimation
• Cross-domain Image Retrieval with a Dual Attribute-aware Ranking Network
• Convolutional Kernel Networks
• A Primal-Dual Subgradient Approachfor Fair Meta Learning
• Expanding phenological insights: automated phenostage annotation with community science plant images
• Probability Weighted Compact Feature for Domain Adaptive Retrieval
• Domain Adaptation by Mixture of Alignments of Second- or Higher-Order Scatter Tensors
• Few-Shot Image Recognition by Predicting Parameters from Activations
• Deep Manifold Traversal: Changing Labels with Convolutional Features
• Combining Diverse Feature Priors
• Predicting the Future: A Jointly Learnt Model for Action Anticipation
• Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling
• Recent Advances in Zero-shot Recognition
• Compressive Sensing via Convolutional Factor Analysis
• SuperAnimal pretrained pose estimation models for behavioral analysis
• Knowledge Distillation in Generations: More Tolerant Teachers Educate Better Students
• TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning
• Boosting Few-Shot Learning With Adaptive Margin Loss
• Semantic Graph for Zero-Shot Learning
• Continual Learning Through Synaptic Intelligence
• Local Higher-Order Statistics (LHS) describing images with statistics of local non-binarized pixel patterns
• Category-Based Deep CCA for Fine-Grained Venue Discovery from Multimodal Data
• Drive Video Analysis for the Detection of Traffic Near-Miss Incidents
• Hardware-Driven Nonlinear Activation for Stochastic Computing Based Deep Convolutional Neural Networks
• Domain Generalization for Object Recognition with Multi-task Autoencoders
• A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation
• Subspace Clustering Based Tag Sharing for Inductive Tag Matrix Refinement with Complex Errors
• Local Area Transform for Cross-Modality Correspondence Matching and Deep Scene Recognition
• Bilinear Supervised Hashing Based on 2D Image Features
• FRODO: Free rejection of out-of-distribution samples: application to chest x-ray analysis
• Research Frontiers in Transfer Learning -- a systematic and bibliometric review
• Efficient Object Embedding for Spliced Image Retrieval
• Transfer Learning for Future Wireless Networks: A Comprehensive Survey
• Learning to Select Pre-Trained Deep Representations with Bayesian Evidence Framework
• A feasibility study of deep neural networks for the recognition of banknotes regarding central bank requirements
• CytoImageNet: A large-scale pretraining dataset for bioimage transfer learning
• Context Augmentation for Convolutional Neural Networks
• Structural Regularization
• Factors of Transferability for a Generic ConvNet Representation
• Multi-source Few-shot Domain Adaptation
• Correlation Alignment by Riemannian Metric for Domain Adaptation
• Meta-Learning to Improve Pre-Training
• Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation
• Discriminative and Geometry Aware Unsupervised Domain Adaptation
• GAPLE: Generalizable Approaching Policy LEarning for Robotic Object Searching in Indoor Environment
• Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning
• Transfer Learning in 4D for Breast Cancer Diagnosis using Dynamic Contrast-Enhanced Magnetic Resonance Imaging
• DELTA: DEep Learning Transfer using Feature Map with Attention for Convolutional Networks
• Towards Robust Pattern Recognition: A Review
• Learning Joint Representations of Videos and Sentences with Web Image Search
• Generalizing from a Few Examples: A Survey on Few-Shot Learning
• DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer
• Meta-learning with negative learning rates
• Learning to cluster in order to transfer across domains and tasks
• Certified Robustness to Label-Flipping Attacks via Randomized Smoothing
• Recent Advancements in Self-Supervised Paradigms for Visual Feature Representation
• Prosodic Structure Beyond Lexical Content: A Study of Self-Supervised Learning
• Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network
• Towards Recognizing New Semantic Concepts in New Visual Domains
• Towards Accurate and Robust Domain Adaptation under Noisy Environments
• Multi-source Domain Adaptation via Weighted Joint Distributions Optimal Transport
• Subset Feature Learning for Fine-Grained Category Classification
• Constructing Deep Neural Networks by Bayesian Network Structure Learning
• Geometric Neural Phrase Pooling: Modeling the Spatial Co-occurrence of Neurons
• Towards Robust Evaluations of Continual Learning
• Unsupervised Extraction of Video Highlights Via Robust Recurrent Auto-encoders
• From Anchor Generation to Distribution Alignment: Learning a Discriminative Embedding Space for Zero-Shot Recognition
• Return of Frustratingly Easy Domain Adaptation
• Multi-Task Incremental Learning for Object Detection
• Deep Learning in Information Security
• SASP: Strip-Aware Spatial Perception for Fine-Grained Bird Image Classification
• Adapting Convolutional Neural Networks for Geographical Domain Shift
• The Devil is in the Tails: Fine-grained Classification in the Wild
• Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment
• Learning Structured Inference Neural Networks with Label Relations
• Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT
• Toward Optimal Run Racing: Application to Deep Learning Calibration
• Multi-scale Orderless Pooling of Deep Convolutional Activation Features
• Local Color Contrastive Descriptor for Image Classification
• Unifying Unsupervised Domain Adaptation and Zero-Shot Visual Recognition
• Learning to Generate Chairs, Tables and Cars with Convolutional Networks
• Towards Understanding the Transferability of Deep Representations
• Meta-learning Transferable Representations with a Single Target Domain
• Transitive Hashing Network for Heterogeneous Multimedia Retrieval
• Domain-Specific Suppression for Adaptive Object Detection
• On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation
• Robust Deep Sensing Through Transfer Learning in Cognitive Radio
• Identifying and Exploiting Structures for Reliable Deep Learning
• Generic Deep Networks with Wavelet Scattering
• Improving Voice Separation by Incorporating End-to-end Speech Recognition
• Conformal retrofitting via Riemannian manifolds: distilling task-specific graphs into pretrained embeddings
• t-SNE-CUDA: GPU-Accelerated t-SNE and its Applications to Modern Data
• Understanding Locally Competitive Networks
• GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds
• Happy Travelers Take Big Pictures: A Psychological Study with Machine Learning and Big Data
• Efficient Inferencing of Compressed Deep Neural Networks
• Cross Modal Distillation for Supervision Transfer
• On Machine Learning and Structure for Mobile Robots
• Value of Temporal Dynamics Information in Driving Scene Segmentation
• A novel learning-based frame pooling method for Event Detection
• Self-Adaptive Partial Domain Adaptation
• Multi-component Image Translation for Deep Domain Generalization
• Machine Learning for Scent: Learning Generalizable Perceptual Representations of Small Molecules
• Refining Language Models with Compositional Explanations
• Fine-Grained Visual Categorization via Multi-stage Metric Learning
• Attention Transfer Network for Aspect-level Sentiment Classification
• Simultaneous Detection and Segmentation
• Do Convnets Learn Correspondence?
• Few-Shot Representation Learning for Out-Of-Vocabulary Words
• Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
• Encoding High Dimensional Local Features by Sparse Coding Based Fisher Vectors
• Time Matters: Multi-scale Temporalization of Social Media Popularity
• Accelerating Deep Unsupervised Domain Adaptation with Transfer Channel Pruning
• Representation as a Service
• Low-resource Deep Entity Resolution with Transfer and Active Learning
• PanRep: Graph neural networks for extracting universal node embeddings in heterogeneous graphs
• Deep Pyramidal Residual Networks
• Image Transformation Network for Privacy-Preserving Deep Neural Networks and Its Security Evaluation
• Saliency-Aware Class-Agnostic Food Image Segmentation
• Hard Class Rectification for Domain Adaptation
• Industrial Synthetic Segment Pre-training
• Deep Priority Hashing
• Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models
• Domain Generalization under Conditional and Label Shifts via Variational Bayesian Inference
• Image Annotation Incorporating Low-Rankness, Tag and Visual Correlation and Inhomogeneous Errors
• A Unified Perspective on Multi-Domain and Multi-Task Learning
• Towards Unsupervised Weed Scouting for Agricultural Robotics
• Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks
• HWNet v2: An Efficient Word Image Representation for Handwritten Documents
• Deep Learning for Surface Material Classification Using Haptic And Visual Information
• Learning Invariant Representations across Domains and Tasks
• A Two-Layer Local Constrained Sparse Coding Method for Fine-Grained Visual Categorization
• Deep Layer Aggregation
• Rethinking ImageNet Pre-training
• Online Convolutional Sparse Coding with Sample-Dependent Dictionary
• Distributed Deep Learning in Open Collaborations
• Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws
• How Transferable are Neural Networks in NLP Applications?
• Characterizing and Understanding the Generalization Error of Transfer Learning with Gibbs Algorithm
• Deep Convolutional Ranking for Multilabel Image Annotation
• SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network
• Third-Person Imitation Learning
• Discriminative Label Consistent Domain Adaptation
• STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification
• Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation
• Sample-level CNN Architectures for Music Auto-tagging Using Raw Waveforms
• Adaptive Compression-based Lifelong Learning
• Learning Deep Convolutional Features for MRI Based Alzheimer's Disease Classification
• Cross-Entropy Adversarial View Adaptation for Person Re-identification
• Adaptively-Accumulated Knowledge Transfer for Partial Domain Adaptation
• Part Detector Discovery in Deep Convolutional Neural Networks
• Object-Centric Representation Learning from Unlabeled Videos
• Semantics for Global and Local Interpretation of Deep Neural Networks
• Show and tell: A neural image caption generator
• Unsupervised Cross-Domain Recognition by Identifying Compact Joint Subspaces
• Low-Cost Transfer Learning of Face Tasks
• Beyond Sharing Weights for Deep Domain Adaptation
• DAG-Recurrent Neural Networks For Scene Labeling
• SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification
• Learning A Task-Specific Deep Architecture For Clustering
• SA-CNN: Dynamic Scene Classification using Convolutional Neural Networks
• Adversarial Cross-Domain Action Recognition with Co-Attention
• On the Performance of ConvNet Features for Place Recognition
• Unconstrained Face Verification using Deep CNN Features
• Cross-Modal Similarity Learning : A Low Rank Bilinear Formulation
• Scene Graph Parsing as Dependency Parsing
• Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?
• Transfer Learning with Sparse Associative Memories
• Deep Learning
• A Comparison of Dense Region Detectors for Image Search and Fine-Grained Classification
• Extrapolating Expected Accuracies for Large Multi-Class Problems
• Object Level Deep Feature Pooling for Compact Image Representation
• Advances in Deep Learning for Hyperspectral Image Analysis—Addressing Challenges Arising in Practical Imaging Scenarios
• Efficient Yet Deep Convolutional Neural Networks for Semantic Segmentation
• A Flexible Selection Scheme for Minimum-Effort Transfer Learning
• Kernel Manifold Alignment for Domain Adaptation
• Learned Indexes for Dynamic Workloads
• Prompt-Tuning SAM: From Generalist to Specialist with only 2048 Parameters and 16 Training Images
• Learning Effective Loss Functions Efficiently
• A Systematic Comparison of Deep Learning Architectures in an Autonomous Vehicle
• Heterogeneous Domain Adaptation via Soft Transfer Network
• Locally Supervised Deep Hybrid Model for Scene Recognition
• Minimum Class Confusion for Versatile Domain Adaptation
• Land Use Classification in Remote Sensing Images by Convolutional Neural Networks
• Action Segmentation with Mixed Temporal Domain Adaptation
• DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation by Transferring from GANs
• Video Summarization using Deep Semantic Features
• Representation Learning for Tabular Data: A Comprehensive Survey
• An Image is Worth K Topics: A Visual Structural Topic Model with Pretrained Image Embeddings
• BoTTA: Benchmarking on-device Test Time Adaptation
• Show and Tell: Lessons Learned from the 2015 MSCOCO Image Captioning Challenge

Related

• Deep Convolutional Neural Networks as Generic Feature Extractors
• Network Comparison Study of Deep Activation Feature Discriminability with Novel Objects
• CNN Features off-the-shelf: an Astounding Baseline for Recognition
• Factors of Transferability for a Generic ConvNet Representation
• A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends