ADE20K
Canonical25papers using it
2022first seen
A scene-parsing dataset with dense pixel annotations over 150 semantic categories.
Papers using ADE20K (25)
- PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised SegmentationActive Spatial Guidance: Eliminating Injected Positional Mechanisms in Vision TransformersLUMA: Benchmarking Segmentation via a Lightweight Universal Mask AdapterRethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware PerspectiveSparse Attention for Dense Open-Vocabulary Prediction in CLIPScene-Aware Urban Design: A Human-AI Recommendation Framework Using Co-Occurrence Embeddings and Vision-Language ModelsSub-Semantic Image SegmentationLocality-Attending Vision TransformerExploring Open-Vocabulary Object Recognition in Images using CLIPSeeing Through Clutter: Structured 3D Scene Reconstruction via Iterative Object RemovalDSeq-JEPA: Discriminative Sequential Joint-Embedding Predictive ArchitectureA Training-Free Framework for Open-Vocabulary Image Segmentation and Recognition with EfficientNet and CLIPEnhancing Transformer-Based Vision Models: Addressing Feature Map Anomalies Through Novel Optimization StrategiesThe Missing Point in Vision Transformers for Universal Image SegmentationLeMoRe: Learn More Details for Lightweight Semantic SegmentationCross-Domain Semantic Segmentation with Large Language Model-Assisted
Descriptor GenerationConv2Former: A Simple Transformer-Style ConvNet for Visual RecognitionA Unified View of Masked Image ModelingDecoder Denoising Pretraining for Semantic SegmentationUnderstanding Gaussian Attention Bias of Vision Transformers Using
Effective Receptive FieldsFeature Selective Transformer for Semantic Image SegmentationHCFormer: Unified Image Segmentation with Hierarchical ClusteringA Simple Latent Diffusion Approach for Panoptic Segmentation and Mask
InpaintingLow-Resolution Self-Attention for Semantic SegmentationTransformer Scale Gate for Semantic Segmentation