mlsanityData to 7 Oct 2026

Region Similarity Representation Learning

arXiv 2103.12902 ↗First posted 24 Mar 2021cs.CVcited by 96

Not on the map. Why?

Abstract (arXiv)

We present Region Similarity Representation Learning (ReSim), a new approach to self-supervised representation learning for localization-based tasks such as object detection and segmentation. While existing work has largely focused on solely learning global representations for an entire image, ReSim learns both regional representations for localization as well as semantic image-level representations. ReSim operates by sliding a fixed-sized window across the overlapping area between two views (e.g., image crops), aligning these areas with their corresponding convolutional feature map regions, and then maximizing the feature similarity across views. As a result, ReSim learns spatially and semantically consistent feature representation throughout the convolutional feature maps of a neural network. A shift or scale of an image region, e.g., a shift or scale of an object, has a corresponding change in the feature maps; this allows downstream tasks to leverage these representations for localization. Through object detection, instance segmentation, and dense pose estimation experiments, we illustrate how ReSim learns representations which significantly improve the localization and classification performance compared to a competitive MoCo-v2 baseline: +2.7 APbb75 VOC, +1.1 APbb75 COCO, and +1.9 APmk Cityscapes. Code and pre-trained models are released at: urlhttps://github.com/Tete-Xiao/ReSim

Key facts. Cited by 96 papers in the map (data through 7 Oct 2026). Builds on 44 of its 58 references that are in the map. First posted on arXiv 24 Mar 2021.

Builds on

44 of 58 references.

References · 44

  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. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2017Mask R-CNNcited by 7,259
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  9. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  10. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  11. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  12. 2015Fast R-CNNcited by 2,930
32 more
  1. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  2. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  3. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  4. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  5. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  6. 2019Contrastive Multiview Codingcited by 1,297
  7. 2016Colorful Image Colorizationcited by 1,113
  8. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  9. 2020What Makes for Good Views for Contrastive Learning?cited by 843
  10. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 806
  11. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
  12. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 672
  13. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  14. 2020A Survey on Contrastive Self-supervised Learningcited by 553
  15. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  16. 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 422
  17. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  18. 2014Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networkscited by 299
  19. 2019Learning Correspondence from the Cycle-Consistency of Timecited by 269
  20. 2019Unsupervised Embedding Learning via Invariant and Spreading Instance Featurecited by 231
  21. 2020What Should Not Be Contrastive in Contrastive Learningcited by 224
  22. 2021DetCo: Unsupervised Contrastive Learning for Object Detectioncited by 205
  23. 2019Scaling and Benchmarking Self-Supervised Visual Representation Learningcited by 201
  24. 2018Acquisition of Localization Confidence for Accurate Object Detectioncited by 174
  25. 2018Tracking Emerges by Colorizing Videoscited by 166
  26. 2020Unsupervised Learning of Dense Visual Representationscited by 147
  27. 2021Instance Localization for Self-supervised Detection Pretrainingcited by 99
  28. 2019Unsupervised Learning of Object Structure and Dynamics from Videoscited by 92
  29. 2019Joint-task Self-supervised Learning for Temporal Correspondencecited by 80
  30. 2020Learning Representations by Predicting Bags of Visual Wordscited by 73
  31. 2017MegDet: A Large Mini-Batch Object Detectorcited by 66
  32. 2020SelfAugment: Automatic Augmentation Policies for Self-Supervised Learningcited by 32

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 34; 2023: 27; 2024: 13; 2025: 7; 2026: 4.

96 papers.

Sort:

By area:

  1. 2022Benchmarking Self-Supervised Learning on Diverse Pathology Datasetscited by 148
  2. 2022VICRegL: Self-Supervised Learning of Local Visual Featurescited by 118
  3. 2021Aligning Pretraining for Detection via Object-Level Contrastive Learningcited by 110
  4. 2022FreeSOLO: Learning to Segment Objects without Annotationscited by 102
  5. 2022BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotationscited by 99
  6. 2023Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformerscited by 91
  7. 2021Class-agnostic Object Detection with Multi-modal Transformercited by 85
  8. 2021DETReg: Unsupervised Pretraining with Region Priors for Object Detectioncited by 76
  9. 2021Unsupervised Object-Level Representation Learning from Scene Imagescited by 72
  10. 2022Patch-level Representation Learning for Self-supervised Vision Transformerscited by 60
  11. 2023LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matchingcited by 60
  12. 2023MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Featurescited by 53
38 more
  1. 2022Green Hierarchical Vision Transformer for Masked Image Modelingcited by 50
  2. 2021Revisiting Contrastive Methods for Unsupervised Learning of Visual Representationscited by 48
  3. 2023CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understandingcited by 48
  4. 2022Masked Image Modeling with Denoising Contrastcited by 45
  5. 2022SimPer: Simple Self-Supervised Learning of Periodic Targetscited by 44
  6. 2022Point-Level Region Contrast for Object Detection Pre-Trainingcited by 41
  7. 2023Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Trainingcited by 39
  8. 2021A Survey of Self-Supervised and Few-Shot Object Detectioncited by 35
  9. 2022Learning Where to Learn in Cross-View Self-Supervised Learningcited by 31
  10. 2022Architecture-Agnostic Masked Image Modeling -- From ViT back to CNNcited by 31
  11. 2023Contrastive Feature Masking Open-Vocabulary Vision Transformercited by 31
  12. 2022UniVIP: A Unified Framework for Self-Supervised Visual Pre-trainingcited by 30
  13. 2021Exploring Set Similarity for Dense Self-supervised Representation Learningcited by 29
  14. 2023CrOC: Cross-View Online Clustering for Dense Visual Representation Learningcited by 21
  15. 2022Location-Aware Self-Supervised Transformers for Semantic Segmentationcited by 20
  16. 2023Top-Down Visual Attention from Analysis by Synthesiscited by 19
  17. 2023Multi-Label Self-Supervised Learning with Scene Imagescited by 17
  18. 2022Panoramic Panoptic Segmentation: Insights Into Surrounding Parsing for Mobile Agents via Unsupervised Contrastive Learningcited by 14
  19. 2023Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learningcited by 14
  20. 2023R-MAE: Regions Meet Masked Autoencoderscited by 13
  21. 2024ContrastAlign: Toward Robust BEV Feature Alignment via Contrastive Learning for Multi-Modal 3D Object Detectioncited by 13
  22. 2024Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability, Composability, and Decomposability from Anatomy via Self-Supervisioncited by 12
  23. 2023Correlational Image Modeling for Self-Supervised Visual Pre-Trainingcited by 11
  24. 2021Exploring Localization for Self-supervised Fine-grained Contrastive Learningcited by 9
  25. 2023FLSL: Feature-level Self-supervised Learningcited by 9
  26. 2022InsCon:Instance Consistency Feature Representation via Self-Supervised Learningcited by 8
  27. 2022Dense Siamese Network for Dense Unsupervised Learningcited by 8
  28. 2022Self-supervised Learning with Local Contrastive Loss for Detection and Semantic Segmentationcited by 8
  29. 2022Semantics-Consistent Feature Search for Self-Supervised Visual Representation Learningcited by 8
  30. 2023Region-centric Image-Language Pretraining for Open-Vocabulary Detectioncited by 8
  31. 2023Learning Anatomically Consistent Embedding for Chest Radiographycited by 8
  32. 2024GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised Learningcited by 8
  33. 2025Cyclic Contrastive Knowledge Transfer for Open-Vocabulary Object Detectioncited by 8
  34. 2021Multi-source Few-shot Domain Adaptationcited by 7
  35. 2022Self-Supervised Image Representation Learning with Geometric Set Consistencycited by 7
  36. 2021GenURL: A General Framework for Unsupervised Representation Learningcited by 6
  37. 2022Multi-Task Learning for Visual Scene Understandingcited by 6
  38. 2022Unsupervised Contrastive Domain Adaptation for Semantic Segmentationcited by 6

50 most cited of 96 All 96 (JSON)