ADE20K

Dataset Information
Languages
Chinese
Introduced
2017
Homepage

Overview

The ADE20K semantic segmentation dataset contains more than 20K scene-centric images exhaustively annotated with pixel-level objects and object parts labels. There are totally 150 semantic categories, which include stuffs like sky, road, grass, and discrete objects like person, car, bed.

Source: Cooperative Image Segmentation and Restoration in Adverse Environmental Conditions
Image Source: https://groups.csail.mit.edu/vision/datasets/ADE20K/

Variants: ADE20K-847, ADE20K-150, ADE20K 1/32 labeled, ADE20K 1/16 labeled, ADE20K-Outdoor Labels-to-Photos, ADE20K val, ADE20K Labels-to-Photos, ADE20K

Associated Benchmarks

This dataset is used in 7 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
Semi-Supervised Instance Segmentation CAST CAST: Contrastive Adaptation and Distillation … 2025-05-28
Semantic Segmentation ViT-P (InternImage-H) The Missing Point in Vision … 2025-05-26
Semantic Segmentation ViT-P (OneFormer, DiNAT-L) The Missing Point in Vision … 2025-05-26
Semantic Segmentation ViT-P (OneFormer, InternImage-H) The Missing Point in Vision … 2025-05-26
Semantic Segmentation EoMT (DINOv2-L, single-scale, 512x512) Your ViT is Secretly an … 2025-03-24
Semantic Segmentation DeBiFormer-B (IN1k pretrain, Upernet 160k) DeBiFormer: Vision Transformer with Deformable … 2024-10-11
Open Vocabulary Panoptic Segmentation MAFT+ Collaborative Vision-Text Representation Optimizing for … 2024-08-01
Semantic Segmentation ColorMAE-Green-ViTB-1600 ColorMAE: Exploring data-independent masking strategies … 2024-07-17
Semantic Segmentation PIIP-LH6B(UperNet) Parameter-Inverted Image Pyramid Networks 2024-06-06
Open Vocabulary Panoptic Segmentation PosSAM PosSAM: Panoptic Open-vocabulary Segment Anything 2024-03-14
Semantic Segmentation SERNet-Former SERNet-Former: Semantic Segmentation by Efficient … 2024-01-28
Open Vocabulary Panoptic Segmentation UMG-CLIP-L/14 UMG-CLIP: A Unified Multi-Granularity Vision … 2024-01-12
Open Vocabulary Panoptic Segmentation UMG-CLIP-E/14 UMG-CLIP: A Unified Multi-Granularity Vision … 2024-01-12
Semantic Segmentation MetaPrompt-SD Harnessing Diffusion Models for Visual … 2023-12-22
Semantic Segmentation TransNeXt-Tiny (IN-1K pretrain, Mask2Former, 512) TransNeXt: Robust Foveal Visual Perception … 2023-11-28
Semantic Segmentation TransNeXt-Base (IN-1K pretrain, Mask2Former, 512) TransNeXt: Robust Foveal Visual Perception … 2023-11-28
Semantic Segmentation TransNeXt-Small (IN-1K pretrain, Mask2Former, 512) TransNeXt: Robust Foveal Visual Perception … 2023-11-28
Semantic Segmentation UniRepLKNet-XL UniRepLKNet: A Universal Perception Large-Kernel … 2023-11-27
Semantic Segmentation UniRepLKNet-B++ UniRepLKNet: A Universal Perception Large-Kernel … 2023-11-27
Semantic Segmentation UniRepLKNet-S UniRepLKNet: A Universal Perception Large-Kernel … 2023-11-27

Research Papers

Recent papers with results on this dataset: