mlsanityData to 7 Oct 2026

Region-Based Representations Revisited

arXiv 2402.02352 ↗First posted 4 Feb 2024cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

We investigate whether region-based representations are effective for recognition. Regions were once a mainstay in recognition approaches, but pixel and patch-based features are now used almost exclusively. We show that recent class-agnostic segmenters like SAM can be effectively combined with strong unsupervised representations like DINOv2 and used for a wide variety of tasks, including semantic segmentation, object-based image retrieval, and multi-image analysis. Once the masks and features are extracted, these representations, even with linear decoders, enable competitive performance, making them well suited to applications that require custom queries. The compactness of the representation also makes it well-suited to video analysis and other problems requiring inference across many images.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 35 of its 62 references that are in the map. First posted on arXiv 4 Feb 2024.

Builds on

35 of 62 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  7. 2023Segment Anythingcited by 8,158
  8. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  9. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  10. 2020End-to-End Object Detection with Transformerscited by 7,384
  11. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  12. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
23 more
  1. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  3. 2015Fast R-CNNcited by 2,930
  4. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  5. 2017Billion-scale similarity search with GPUscited by 2,477
  6. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  7. 2017The Kinetics Human Action Video Datasetcited by 1,894
  8. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  9. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
  10. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 685
  11. 2021Extract Free Dense Labels from CLIPcited by 580
  12. 2022Vision Transformer Adapter for Dense Predictionscited by 564
  13. 2023Segment Everything Everywhere All at Oncecited by 546
  14. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 479
  15. 2023Segment Anything in High Qualitycited by 373
  16. 2023Faster Segment Anything: Towards Lightweight SAM for Mobile Applicationscited by 345
  17. 2022Frozen CLIP Models are Efficient Video Learnerscited by 181
  18. 2023AIM: Adapting Image Models for Efficient Video Action Recognitioncited by 145
  19. 2020Virtual Multi-view Fusion for 3D Semantic Segmentationcited by 99
  20. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
  21. 2022High-Quality Entity Segmentationcited by 93
  22. 2022SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videoscited by 17
  23. 2023What Can Simple Arithmetic Operations Do for Temporal Modeling?cited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 7; 2026: 6.

18 papers.

Sort:

  1. 2024Revisit Anything: Visual Place Recognition via Image Segment Retrievalcited by 19
  2. 2024RELOCATE: A Simple Training-Free Baseline for Visual Query Localization Using Region-Based Representationscited by 11
  3. 2025TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Modelscited by 7
  4. 2025O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Viewscited by 7
  5. 2024Tuning-free Universally-Supervised Semantic Segmentationcited by 6
  6. 2024Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learningcited by 6
  7. 2024Search and Detect: Training-Free Long Tail Object Detection via Web-Image Retrievalcited by 5
  8. 2025REN: Fast and Efficient Region Encodings from Patch-Based Image Encoderscited by 5
  9. 2025FORLA: Federated Object-centric Representation Learning with Slot Attentioncited by 3
  10. 2025FRAME: Pre-Training Video Feature Representations via Anticipation and Memorycited by 2
  11. 2026T-REN: Learning Text-Aligned Region Tokens Improves Dense Vision-Language Alignment and Scalabilitycited by 2
  12. 2025Experimental Evaluation of Static Image Sub-Region-Based Search Models Using CLIPcited by 0
6 more
  1. 2025Uncertainty-Gated Region-Level Retrieval for Robust Semantic Segmentationcited by 0
  2. 2026A Study on Real-time Object Detection using Deep Learningcited by 0
  3. 2026PlanaReLoc: Camera Relocalization in 3D Planar Primitives via Region-Based Structure Matchingcited by 0
  4. 2026Group-DINOmics: Incorporating People Dynamics into DINO for Self-supervised Group Activity Feature Learningcited by 0
  5. 2026Metric-Guided Feature Fusion of Visual Foundation Models for Segmentation Taskscited by 0
  6. 2026PeCA: Palette Context Assisted Inference for Test-Time Paint-Bucket Colourisation on Animation Videoscited by 0