Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/ADE20K

ADE20K

Custom (research-only, non-commercial)Introduced 2017-01-01

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/

Benchmarks

10-shot image generation/Validation mIoU 10-shot image generation/Test Score 10-shot image generation/Params (M)10-shot image generation/GFLOPs (512 x 512)10-shot image generation/GFLOPs 10-shot image generation/Mean IoU (class)10-shot image generation/PQ 10-shot image generation/Mean IoU (val)10-shot image generation/mIoU 10-shot image generation/Mean IoU (test) 10-shot image generation/mAP 2D Semantic Segmentation/Top 1 Accuracy 2D Semantic Segmentation/mIoU 2D Semantic Segmentation/Mean IoU (test)3D/mIoU 3D Character Animation From A Single Photo/Top 1 Accuracy 3D Face Modelling/mIoU 3D Face Reconstruction/mIoU Animation/Top 1 Accuracy Class Incremental Learning/mIoU Class Incremental Learning/Mean IoU (test) Class-Incremental Semantic Segmentation/mIoU Class-Incremental Semantic Segmentation/Mean IoU (test) Continual Learning/mIoU Continual Learning/Mean IoU (test) Continual Semantic Segmentation/mIoU Continual Semantic Segmentation/Mean IoU (test)Face Detection/mIoU Face Reconstruction/mIoU Facial Recognition and Modelling/mIoU Image Generation/FID Open Vocabulary Panoptic Segmentation/PQ Panoptic Segmentation/PQ Reconstruction/PSNR Scene Parsing/Top 1 Accuracy Semantic Segmentation/Validation mIoU Semantic Segmentation/Test Score Semantic Segmentation/Params (M)Semantic Segmentation/GFLOPs (512 x 512)Semantic Segmentation/GFLOPs Semantic Segmentation/Mean IoU (class)Semantic Segmentation/PQ Semantic Segmentation/Mean IoU (val)Semantic Segmentation/mIoU Semantic Segmentation/Mean IoU (test) Semantic Segmentation/mAP Semi-Supervised Instance Segmentation/AP Unsupervised Semantic Segmentation/Mean IoU (val)

Related Benchmarks

ADE20K 1/16 labeled/10-shot image generation/Validation mIoU ADE20K 1/16 labeled/Semantic Segmentation/Validation mIoU ADE20K 1/32 labeled/10-shot image generation/Validation mIoU ADE20K 1/32 labeled/Semantic Segmentation/Validation mIoU ADE20K Labels-to-Photos/1 Image, 2*2 Stitching/Accuracy ADE20K Labels-to-Photos/1 Image, 2*2 Stitching/FID ADE20K Labels-to-Photos/1 Image, 2*2 Stitching/LPIPS ADE20K Labels-to-Photos/1 Image, 2*2 Stitching/mIoU ADE20K Labels-to-Photos/Image Generation/Accuracy ADE20K Labels-to-Photos/Image Generation/FID ADE20K Labels-to-Photos/Image Generation/LPIPS ADE20K Labels-to-Photos/Image Generation/mIoU ADE20K Labels-to-Photos/Image-to-Image Translation/Accuracy ADE20K Labels-to-Photos/Image-to-Image Translation/FID ADE20K Labels-to-Photos/Image-to-Image Translation/LPIPS ADE20K Labels-to-Photos/Image-to-Image Translation/mIoU ADE20K training-free zero-shot segmentation/Zero Shot Segmentation/mIoU ADE20K val/10-shot image generation/AP ADE20K val/10-shot image generation/PQ ADE20K val/10-shot image generation/Pixel Accuracy ADE20K val/10-shot image generation/mIoU ADE20K val/2D Semantic Segmentation/Mean IoU ADE20K val/Instance Segmentation/AP ADE20K val/Instance Segmentation/APL ADE20K val/Instance Segmentation/APM ADE20K val/Instance Segmentation/APS ADE20K val/Panoptic Segmentation/AP ADE20K val/Panoptic Segmentation/PQ ADE20K val/Panoptic Segmentation/mIoU ADE20K val/Scene Parsing/Mean IoU ADE20K val/Scene Understanding/Mean IoU ADE20K val/Semantic Segmentation/AP ADE20K val/Semantic Segmentation/PQ ADE20K val/Semantic Segmentation/Pixel Accuracy ADE20K val/Semantic Segmentation/mIoU ADE20K-150/Open Vocabulary Semantic Segmentation/mIoU ADE20K-847/Open Vocabulary Semantic Segmentation/mIoU ADE20K-847/Zero-Shot Semantic Segmentation/unseen mIoU ADE20K-Outdoor Labels-to-Photos/1 Image, 2*2 Stitching/Accuracy ADE20K-Outdoor Labels-to-Photos/1 Image, 2*2 Stitching/FID ADE20K-Outdoor Labels-to-Photos/1 Image, 2*2 Stitching/mIoU ADE20K-Outdoor Labels-to-Photos/Image Generation/Accuracy ADE20K-Outdoor Labels-to-Photos/Image Generation/FID ADE20K-Outdoor Labels-to-Photos/Image Generation/mIoU ADE20K-Outdoor Labels-to-Photos/Image-to-Image Translation/Accuracy ADE20K-Outdoor Labels-to-Photos/Image-to-Image Translation/FID ADE20K-Outdoor Labels-to-Photos/Image-to-Image Translation/mIoU

Statistics

Papers: 1,213
Benchmarks: 48

Links

Tasks

10-shot image generation 2D Semantic Segmentation 3D 3D Character Animation From A Single Photo 3D Face Modelling 3D Face Reconstruction Animation Class Incremental Learning Class-Incremental Semantic Segmentation Continual Learning Continual Semantic Segmentation Face Detection Face Reconstruction Facial Recognition and Modelling Image Generation Image-to-Image Translation Instance Segmentation Open Vocabulary Panoptic Segmentation Open Vocabulary Semantic Segmentation Open-Vocabulary Semantic Segmentation Overlapped 100-10 Overlapped 100-5 Overlapped 100-50 Overlapped 25-25 Overlapped 50-50 Panoptic Segmentation Pose Transfer Reconstruction Scene Parsing Scene Recognition Scene Understanding Semantic Segmentation Semi-Supervised Instance Segmentation Semi-Supervised Semantic Segmentation Sound Prompted Semantic Segmentation Speech Prompted Semantic Segmentation Unsupervised Semantic Segmentation Unsupervised Semantic Segmentation with Language-image Pre-training Weakly-Supervised Semantic Segmentation Zero-Shot Semantic Segmentation