mlsanityData to 7 Oct 2026

Unified Perceptual Parsing for Scene Understanding

arXiv 1807.10221 ↗First posted 26 Jul 2018cs.CVcited by 1,265

Not on the map. Why?

Cited by 58 in State-space sequence models (S4, Mamba), but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Humans recognize the visual world at multiple levels: we effortlessly categorize scenes and detect objects inside, while also identifying the textures and surfaces of the objects along with their different compositional parts. In this paper, we study a new task called Unified Perceptual Parsing, which requires the machine vision systems to recognize as many visual concepts as possible from a given image. A multi-task framework called UPerNet and a training strategy are developed to learn from heterogeneous image annotations. We benchmark our framework on Unified Perceptual Parsing and show that it is able to effectively segment a wide range of concepts from images. The trained networks are further applied to discover visual knowledge in natural scenes. Models are available at urlhttps://github.com/CSAILVision/unifiedparsing.

Key facts. Cited by 1,265 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 116; 2022: 232; 2023: 250; 2024: 285; 2025: 215; 2026: 167.

1,265 papers.

Sort:

By area:

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  3. 2022A ConvNet for the 2020scited by 3,545
  4. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  5. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  6. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  7. 2024Depth Anything V2cited by 1,385
  8. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  9. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  10. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,147
  11. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,051
  12. 2024VMamba: Visual State Space Modelcited by 955
38 more
  1. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 891
  2. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  3. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  4. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 690
  5. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  6. 2022Vision Transformer Adapter for Dense Predictionscited by 564
  7. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 530
  8. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  9. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 479
  10. 2022DeiT III: Revenge of the ViTcited by 417
  11. 2023Florence-2: Advancing a Unified Representation for a Variety of Vision Taskscited by 403
  12. 2023EVA-02: A Visual Representation for Neon Genesiscited by 377
  13. 2023Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Modelscited by 358
  14. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 338
  15. 2021XCiT: Cross-Covariance Image Transformerscited by 335
  16. 2022OneFormer: One Transformer to Rule Universal Image Segmentationcited by 327
  17. 2022Images Speak in Images: A Generalist Painter for In-Context Visual Learningcited by 317
  18. 2022Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learningcited by 302
  19. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 299
  20. 2022BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizerscited by 298
  21. 2022Context Autoencoder for Self-Supervised Representation Learningcited by 297
  22. 2022Vision Transformer with Deformable Attentioncited by 293
  23. 2022Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuningcited by 292
  24. 2022MultiMAE: Multi-modal Multi-task Masked Autoencoderscited by 287
  25. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 286
  26. 2023Unleashing Text-to-Image Diffusion Models for Visual Perceptioncited by 266
  27. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  28. 2023SpectralGPT: Spectral Remote Sensing Foundation Modelcited by 250
  29. 2022Neighborhood Attention Transformercited by 235
  30. 2024LocalMamba: Visual State Space Model with Windowed Selective Scancited by 235
  31. 2022CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformerscited by 229
  32. 2024Rotary Position Embedding for Vision Transformercited by 226
  33. 2024MambaVision: A Hybrid Mamba-Transformer Vision Backbonecited by 222
  34. 2021ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Biascited by 216
  35. 2022Omnivore: A Single Model for Many Visual Modalitiescited by 214
  36. 2021K-Net: Towards Unified Image Segmentationcited by 211
  37. 2022Visual Attention Networkcited by 210
  38. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206

50 most cited of 1,265 All 1,265 (JSON)