Semantic Understanding of Scenes Through the ADE20K Dataset

2018/12/07 by Bolei Zhou, Hang Zhao, Xavier Puig +4 · 200 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Multimodal Machine Learning Applications

paper · pdf · doi:10.1007/s11263-018-1140-0

openalex publication_date 2018/12/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/31

Citations

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• The Pascal Visual Object Classes (VOC) Challenge
• LabelMe: A Database and Web-Based Tool for Image Annotation
• ImageNet Large Scale Visual Recognition Challenge
• ImageNet classification with deep convolutional neural networks
• Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

Cited by

• SAM-MI: A Mask-Injected Framework for Enhancing Open-Vocabulary Semantic Segmentation with SAM
• Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving
• Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens
• Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspective
• InfoCLIP: Bridging Vision-Language Pretraining and Open-Vocabulary Semantic Segmentation via Information-Theoretic Alignment Transfer
• Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling
• MaskAnyNet: Rethinking Masked Image Regions as Valuable Information in Supervised Learning
• NERVE: Neighbourhood & Entropy-guided Random-walk for training free open-Vocabulary sEgmentation
• Another BRIXEL in the Wall: Towards Cheaper Dense Features
• CPO: Condition Preference Optimization for Controllable Image Generation
• Differentiable Hierarchical Visual Tokenization
• Predicting Household Water Consumption Using Satellite and Street View Images in Two Indian Cities
• Unveiling the Spatial-temporal Effective Receptive Fields of Spiking Neural Networks
• Accelerating Vision Transformers with Adaptive Patch Sizes
• Segmentation as A Plug-and-Play Capability for Frozen Multimodal LLMs
• Latent Diffusion Model without Variational Autoencoder
• Neuro-Symbolic Spatial Reasoning in Segmentation
• Exploring Image Representation with Decoupled Classical Visual Descriptors
• AnyUp: Universal Feature Upsampling
• UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation
• Unified Open-World Segmentation with Multi-Modal Prompts
• SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation
• Synthetic Object Compositions for Scalable and Accurate Learning in Detection, Segmentation, and Grounding
• Datasets for Valence and Arousal Inference: A Survey
• GeoSURGE: Geo-localization using Semantic Fusion with Hierarchy of Geographic Embeddings
• Cutting the Skip: Training Residual-Free Transformers
• Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training
• Multi-modal Data Spectrum: Multi-modal Datasets are Multi-dimensional
• UniVid: Unifying Vision Tasks with Pre-trained Video Generation Models
• SiNGER: A Clearer Voice Distills Vision Transformers Further
• Edge Prediction for Roof Wireframe Reconstruction with Transformers
• Towards biologically plausible phosphene simulation for the differentiable optimization of visual cortical prostheses
• 3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation
• Learning to Detect Label Errors by Making Them: A Method for Segmentation and Object Detection Datasets
• BEiT: BERT Pre-Training of Image Transformers
• Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers
• Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few
• SPATIALGEN: Layout-guided 3D Indoor Scene Generation
• Survey on semantic segmentation using deep learning techniques
• From Pixels to Urban Policy-Intelligence: Recovering Legacy Effects of Redlining with a Multimodal LLM
• Lost in Translation? Vocabulary Alignment for Source-Free Adaptation in Open-Vocabulary Semantic Segmentation
• Improving Generalized Visual Grounding with Instance-aware Joint Learning
• Gaussian Alignment for Relative Camera Pose Estimation via Single-View Reconstruction
• SAGA: Selective Adaptive Gating for Efficient and Expressive Linear Attention
• Progressively Diffused Networks for Semantic Image Segmentation
• Text4Seg++: Advancing Image Segmentation via Generative Language Modeling
• CARDIE: clustering algorithm on relevant descriptors for image enhancement
• PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things
• Towards Open World Detection: A Survey
• Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks
• ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias
• EVA-02: A visual representation for neon genesis
• Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation
• CAD2DMD-SET: Synthetic Generation Tool of Digital Measurement Device CAD Model Datasets for fine-tuning Large Vision-Language Models
• E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections
• Plug-in Feedback Self-adaptive Attention in CLIP for Training-free Open-Vocabulary Segmentation
• Harnessing Meta-Learning for Controllable Full-Frame Video Stabilization
• FOCUS: Frequency-Optimized Conditioning of DiffUSion Models for mitigating catastrophic forgetting during Test-Time Adaptation
• ICNet for Real-Time Semantic Segmentation on High-Resolution Images
• Switchable Whitening for Deep Representation Learning
• DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
• UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding
• Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception
• EvTurb: Event Camera Guided Turbulence Removal
• Stable Diffusion Models are Secretly Good at Visual In-Context Learning
• Evaluating visual experience in heritage-rich areas: A case study of the Inner Ring Road of West Lake, Hangzhou
• UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale
• 3DFroMLLM: 3D Prototype Generation only from Pretrained Multimodal LLMs
• Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization
• Affective Image Content Analysis: Two Decades Review and New Perspectives
• Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation
• SynSeg: Feature Synergy for Multi-Category Contrastive Learning in End-to-End Open-Vocabulary Semantic Segmentation
• Adapting Vision-Language Models Without Labels: A Comprehensive Survey
• SPEX: A Vision-Language Model for Land Cover Extraction on Spectral Remote Sensing Images
• Discovering and using Spelke segments
• Context-based Motion Retrieval using Open Vocabulary Methods for Autonomous Driving
• Training-Free Class Purification for Open-Vocabulary Semantic Segmentation
• Self-Guided Masked Autoencoder
• Improving the HardNet Descriptor
• Implicit Integration of Superpixel Segmentation into Fully Convolutional Networks
• Iwin Transformer: Hierarchical Vision Transformer using Interleaved Windows
• Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation
• Indoor hierarchy relation graph construction method based on RGB‐D
• S-BEV: Semantic Birds-Eye View Representation for Weather and Lighting Invariant 3-DoF Localization
• A Picture May Be Worth a Hundred Words for Visual Question Answering
• Scale Your Instructions: Enhance the Instruction-Following Fidelity of Unified Image Generation Model by Self-Adaptive Attention Scaling
• Advancing Visual Large Language Model for Multi-granular Versatile Perception
• Multi-dataset Pretraining: A Unified Model for Semantic Segmentation
• Compact Vision Transformer by Reduction of Kernel Complexity
• Scale-aware Insertion of Virtual Objects in Monocular Videos
• Leveraging Depth and Language for Open-Vocabulary Domain-Generalized Semantic Segmentation
• Segment This Thing: Foveated Tokenization for Efficient Point-Prompted Segmentation
• All Tokens Matter: Token Labeling for Training Better Vision Transformers
• Leveraging Outdoor Webcams for Local Descriptor Learning
• Look at here : Utilizing supervision to attend subtle key regions
• Development of an Autonomous Mobile Robotic System for Efficient and Precise Disinfection
• Latent Diffusion Models with Masked AutoEncoders
• When Schrödinger Bridge Meets Real-World Image Dehazing with Unpaired Training
• Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation
• Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training
• MUXConv: Information Multiplexing in Convolutional Neural Networks
• Vision-Language Models Can't See the Obvious
• Medical Datasets Collections for Artificial Intelligence-based Medical Image Analysis
• From Pixels to Damage Severity: Estimating Earthquake Impacts Using Semantic Segmentation of Social Media Images
• High-Fidelity Differential-information Driven Binary Vision Transformer
• Depth Anything at Any Condition
• Perception-Oriented Latent Coding for High-Performance Compressed Domain Semantic Inference
• Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space
• GameTileNet: A Semantic Dataset for Low-Resolution Game Art in Procedural Content Generation
• CARAFE++: Unified Content-Aware ReAssembly of FEatures
• ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation
• Norm×Direction: Restoring the Missing Query Norm in Vision Linear Attention
• Sparse Spatial Attention Network for Semantic Segmentation
• Trajectory Prediction in Dynamic Object Tracking: A Critical Study
• Synthetic Visual Genome
• A Scaling Law for Synthetic-to-Real Transfer: How Much Is Your Pre-training Effective?
• Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
• LBMamba: Locally Bi-directional Mamba
• Rethinking Semantic Segmentation Evaluation for Explainability and Model Selection
• From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models
• Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment
• Interactive video retrieval in the age of effective joint embedding deep models: lessons from the 11th VBS
• Revisiting Transformers with Insights from Image Filtering and Boosting
• K-Net: Towards Unified Image Segmentation
• ELBO-T2IAlign: A Generic ELBO-Based Method for Calibrating Pixel-level Text-Image Alignment in Diffusion Models
• Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration
• Hyb-KAN ViT: Hybrid Kolmogorov-Arnold Networks Augmented Vision Transformer
• Histo-Miner: Deep Learning based Tissue Features Extraction Pipeline from H&E Whole Slide Images of Cutaneous Squamous Cell Carcinoma
• Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
• DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception
• OV-COAST: Cost Aggregation with Optimal Transport for Open-Vocabulary Semantic Segmentation
• AetherVision-Bench: An Open-Vocabulary RGB-Infrared Benchmark for Multi-Angle Segmentation across Aerial and Ground Perspectives
• ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads
• BargainNet: Background-Guided Domain Translation for Image Harmonization
• Attacking Attention of Foundation Models Disrupts Downstream Tasks
• MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping
• SAB3R: Semantic-Augmented Backbone in 3D Reconstruction
• Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation
• un²CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP
• MMAFFBen: A Multilingual and Multimodal Affective Analysis Benchmark for Evaluating LLMs and VLMs
• TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models
• Towards urban scenes understanding through polarization cues
• DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers
• CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation
• SIR: Self-supervised Image Rectification via Seeing the Same Scene from Multiple Different Lenses
• A Survey on Training-free Open-Vocabulary Semantic Segmentation
• SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation
• PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding
• Vision Transformers with Self-Distilled Registers
• Fully Transformer Networks for Semantic Image Segmentation
• LlamaSeg: Image Segmentation via Autoregressive Mask Generation
• EOVSAM: Efficient Open-Vocabulary Segmentation with SAM 3 in One Pass
• Automated River Substrate Mapping From Sonar Imagery With Machine Learning
• InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning
• REN: Fast and Efficient Region Encodings from Patch-Based Image Encoders
• LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision
• OpenSeg-R: Improving Open-Vocabulary Segmentation via Step-by-Step Visual Reasoning
• ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation
• Native Segmentation Vision Transformers
• Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels
• CoT-Edit: Let CoT Guide Instruction Video Editing
• FractalMamba++: Scaling Vision Mamba Across Resolutions via Hilbert Fractal Geometry
• SounDiT: Geo-Contextual Soundscape-to-Landscape Generation
• DeepLab2: A TensorFlow Library for Deep Labeling
• VA-RED²: Video Adaptive Redundancy Reduction
• Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization
• Unlocking the Full Potential of Small Data with Diverse Supervision
• UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model
• AdaDINO: Context-Adaptive DINO-Distilled Vision Foundation Models for Efficient Open-Vocabulary Edge Inference
• Local-to-Global Self-Attention in Vision Transformers
• RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization
• Neural Inverse Knitting: From Images to Manufacturing Instructions
• Image Harmonization Dataset iHarmony4: HCOCO, HAdobe5k, HFlickr, and Hday2night
• DeepPerimeter: Indoor Boundary Estimation from Posed Monocular Sequences
• Sim2Real for Self-Supervised Monocular Depth and Segmentation
• Better, Stronger, Faster, and Broader: Structured All-Mask Prediction for MLLM-Based Segmentation
• PixelUp: Zero-Shot Semantic Feature Upsampling for Fine-Grained Vision Tasks
• Is This The Right Place? Geometric-Semantic Pose Verification for Indoor Visual Localization
• Spiral RoPE: Rotate Your Rotary Positional Embeddings in the 2D Plane
• DeepLandscape: Adversarial Modeling of Landscape Video
• Environment Semantics Aided Wireless Communications: A Case Study of mmWave Beam Prediction and Blockage Prediction
• Calibrating Self-supervised Monocular Depth Estimation
• Vision Transformers Need More Than Registers
• SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data
• Routing the Lottery: Adaptive Subnetworks for Heterogeneous Data
• SynergyAmodal: Deocclude Anything with Text Control
• Pixel-Grounded Retrieval for Knowledgeable Large Multimodal Models
• C-RADIOv4 (Tech Report)
• Improving Open-World Object Localization by Discovering Background
• Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes
• Dense Semantic Forecasting in Video by Joint Regression of Features and Feature Motion
• SegICP: Integrated deep semantic segmentation and pose estimation
• Per-Pixel Feedback for improving Semantic Segmentation
• Evaluating the Impact of Semantic Segmentation and Pose Estimation on Dense Semantic SLAM
• Multi-Scale Tensorial Summation and Dimensional Reduction Guided Neural Network for Edge Detection
• M2GAN: A Multi-Stage Self-Attention Network for Image Rain Removal on Autonomous Vehicles
• CondNet: Conditional Classifier for Scene Segmentation
• SCI-CLIP: Segment-Centric Inference with Reference Memory for Training-Free Open-Vocabulary Segmentation
• How Infrastructure and Streetscape Shape E-Scooter Route Choice: Evidence from Washington, DC
• FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation
• Hypergraph Vision Transformers: Images are More than Nodes, More than Edges
• Distilling Knowledge from Heterogeneous Architectures for Semantic Segmentation
• ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness
• Studying Image Diffusion Features for Zero-Shot Video Object Segmentation
• 3DM-WeConvene: Learned Image Compression with 3D Multi-Level Wavelet-Domain Convolution and Entropy Model