mlsanityData to 7 Oct 2026

Semantic Understanding of Scenes through the ADE20K Dataset

arXiv 1608.05442 ↗First posted 18 Aug 2016cs.CVcited by 1,063

Not on the map. Why?

Cited by 79 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Scene parsing, or recognizing and segmenting objects and stuff in an image, is one of the key problems in computer vision. Despite the community's efforts in data collection, there are still few image datasets covering a wide range of scenes and object categories with dense and detailed annotations for scene parsing. In this paper, we introduce and analyze the ADE20K dataset, spanning diverse annotations of scenes, objects, parts of objects, and in some cases even parts of parts. A generic network design called Cascade Segmentation Module is then proposed to enable the segmentation networks to parse a scene into stuff, objects, and object parts in a cascade. We evaluate the proposed module integrated within two existing semantic segmentation networks, yielding significant improvements for scene parsing. We further show that the scene parsing networks trained on ADE20K can be applied to a wide variety of scenes and objects.

Key facts. Cited by 1,063 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Aug 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 92; 2022: 166; 2023: 217; 2024: 246; 2025: 186; 2026: 155.

1,063 papers.

Sort:

By area:

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2023Segment Anythingcited by 8,158
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  4. 2022A ConvNet for the 2020scited by 3,545
  5. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  6. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  7. 2022Visual Prompt Tuningcited by 1,674
  8. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  9. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,147
  10. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,051
  11. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  12. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
38 more
  1. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 822
  2. 2022Language-driven Semantic Segmentationcited by 711
  3. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  4. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 685
  5. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 640
  6. 2022Open-Vocabulary Semantic Segmentation with Mask-adapted CLIPcited by 560
  7. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 530
  8. 2022Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Taskscited by 510
  9. 2025VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understandingcited by 502
  10. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 495
  11. 2021Scaling Open-Vocabulary Image Segmentation with Image-Level Labelscited by 471
  12. 2021VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Expertscited by 424
  13. 2024OmniGen: Unified Image Generationcited by 388
  14. 2024Hallucination of Multimodal Large Language Models: A Surveycited by 380
  15. 2023EVA-02: A Visual Representation for Neon Genesiscited by 377
  16. 2023Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Modelscited by 371
  17. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
  18. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 361
  19. 2021LAVT: Language-Aware Vision Transformer for Referring Image Segmentationcited by 347
  20. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 338
  21. 2022OneFormer: One Transformer to Rule Universal Image Segmentationcited by 327
  22. 2022Diffusion Models already have a Semantic Latent Spacecited by 324
  23. 2023Emu Edit: Precise Image Editing via Recognition and Generation Taskscited by 321
  24. 2022Images Speak in Images: A Generalist Painter for In-Context Visual Learningcited by 317
  25. 2023Recognize Anything: A Strong Image Tagging Modelcited by 305
  26. 2022BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizerscited by 298
  27. 2022Vision Transformer with Deformable Attentioncited by 293
  28. 2021DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effortcited by 264
  29. 2023MagicDrive: Street View Generation with Diverse 3D Geometry Controlcited by 250
  30. 2022EfficientFormer: Vision Transformers at MobileNet Speedcited by 240
  31. 2024LocalMamba: Visual State Space Model with Windowed Selective Scancited by 235
  32. 2024Rotary Position Embedding for Vision Transformercited by 226
  33. 2023PixelLM: Pixel Reasoning with Large Multimodal Modelcited by 220
  34. 2021ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Biascited by 216
  35. 2023CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentationcited by 215
  36. 2023Sequential Modeling Enables Scalable Learning for Large Vision Modelscited by 212
  37. 2021K-Net: Towards Unified Image Segmentationcited by 211
  38. 2022Visual Attention Networkcited by 210

50 most cited of 1,063 All 1,063 (JSON)