mlsanityData to 7 Oct 2026

CrOC: Cross-View Online Clustering for Dense Visual Representation Learning

arXiv 2303.13245 ↗First posted 23 Mar 2023cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

Learning dense visual representations without labels is an arduous task and more so from scene-centric data. We propose to tackle this challenging problem by proposing a Cross-view consistency objective with an Online Clustering mechanism (CrOC) to discover and segment the semantics of the views. In the absence of hand-crafted priors, the resulting method is more generalizable and does not require a cumbersome pre-processing step. More importantly, the clustering algorithm conjointly operates on the features of both views, thereby elegantly bypassing the issue of content not represented in both views and the ambiguous matching of objects from one crop to the other. We demonstrate excellent performance on linear and unsupervised segmentation transfer tasks on various datasets and similarly for video object segmentation. Our code and pre-trained models are publicly available at https://github.com/stegmuel/CrOC.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 44 of its 56 references that are in the map. First posted on arXiv 23 Mar 2023.

Builds on

44 of 56 references.

References · 44

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  8. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  9. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  10. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  11. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  12. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
32 more
  1. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  2. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 942
  3. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
  4. 2018Panoptic Segmentationcited by 796
  5. 2019Self-labelling via simultaneous clustering and representation learningcited by 525
  6. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  7. 2020Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learningcited by 297
  8. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  9. 2021DetCo: Unsupervised Contrastive Learning for Object Detectioncited by 205
  10. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  11. 2017Colorization as a Proxy Task for Visual Understandingcited by 175
  12. 2021PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clusteringcited by 163
  13. 2021Efficient Visual Pretraining with Contrastive Detectioncited by 150
  14. 2021Efficient Self-supervised Vision Transformers for Representation Learningcited by 149
  15. 2020Unsupervised Learning of Dense Visual Representationscited by 147
  16. 2020Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biasescited by 143
  17. 2022VICRegL: Self-Supervised Learning of Local Visual Featurescited by 118
  18. 2021Aligning Pretraining for Detection via Object-Level Contrastive Learningcited by 110
  19. 2022FreeSOLO: Learning to Segment Objects without Annotationscited by 102
  20. 2021Region Similarity Representation Learningcited by 96
  21. 2022Self-Supervised Learning of Object Parts for Semantic Segmentationcited by 90
  22. 2022Object discovery and representation networkscited by 80
  23. 2021Unsupervised Object-Level Representation Learning from Scene Imagescited by 72
  24. 2020Self-EMD: Self-Supervised Object Detection without ImageNetcited by 70
  25. 2022Self-Supervised Visual Representation Learning with Semantic Groupingcited by 70
  26. 2020CASTing Your Model: Learning to Localize Improves Self-Supervised Representationscited by 63
  27. 2022Patch-level Representation Learning for Self-supervised Vision Transformerscited by 60
  28. 2021Revisiting Contrastive Methods for Unsupervised Learning of Visual Representationscited by 48
  29. 2021Object-aware Contrastive Learning for Debiased Scene Representationcited by 34
  30. 2021Exploring Set Similarity for Dense Self-supervised Representation Learningcited by 29
  31. 2022CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentationcited by 26
  32. 2022Global-Local Self-Distillation for Visual Representation Learningcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 7; 2025: 9; 2026: 2.

21 papers.

Sort:

By area:

  1. 2023Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representationscited by 35
  2. 2024VideoMAC: Video Masked Autoencoders Meet ConvNetscited by 20
  3. 2023CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrappingcited by 17
  4. 2024Near, far: Patch-ordering enhances vision foundation models' scene understandingcited by 15
  5. 2025Object-Centric Pretraining via Target Encoder Bootstrappingcited by 6
  6. 2025MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learningcited by 5
  7. 2024S3PT: Scene Semantics and Structure Guided Clustering to Boost Self-Supervised Pre-Training for Autonomous Drivingcited by 4
  8. 2025Exploring Structural Degradation in Dense Representations for Self-supervised Learningcited by 4
  9. 2023ActiveDC: Distribution Calibration for Active Finetuningcited by 3
  10. 2024A Simple Framework for Open-Vocabulary Zero-Shot Segmentationcited by 3
  11. 2025CleverDistiller: Simple and Spatially Consistent Cross-modal Distillationcited by 3
  12. 2025DIP: Unsupervised Dense In-Context Post-training of Visual Representationscited by 3
9 more
  1. 2025Semantic Concentration for Self-Supervised Dense Representations Learningcited by 3
  2. 2024Efficient Unsupervised Visual Representation Learning with Explicit Cluster Balancingcited by 1
  3. 2025Patch-Level Kernel Alignment for Dense Self-Supervised Learningcited by 1
  4. 2025Beyond Instance Consistency: Investigating View Diversity in Self-supervised Learningcited by 1
  5. 2024Dynamic in Static: Hybrid Visual Correspondence for Self-Supervised Video Object Segmentationcited by 0
  6. 2024Unsqueeze [CLS] Bottleneck to Learn Rich Representationscited by 0
  7. 2025Object-level Self-Distillation for Vision Pretrainingcited by 0
  8. 2026Information theoretic underpinning of self-supervised learning by clusteringcited by 0
  9. 2026Depth-Guided Contrastive Learning for 2D Representations with 3D Spatial Awarenesscited by 0