mlsanityData to 14 Oct 2026

Object discovery and representation networks

arXiv 2203.08777 ↗First posted 16 Mar 2022cs.CV cs.AI cs.LGcited by 80

Not on the map. Why?

Abstract (arXiv)

The promise of self-supervised learning (SSL) is to leverage large amounts of unlabeled data to solve complex tasks. While there has been excellent progress with simple, image-level learning, recent methods have shown the advantage of including knowledge of image structure. However, by introducing hand-crafted image segmentations to define regions of interest, or specialized augmentation strategies, these methods sacrifice the simplicity and generality that makes SSL so powerful. Instead, we propose a self-supervised learning paradigm that discovers this image structure by itself. Our method, Odin, couples object discovery and representation networks to discover meaningful image segmentations without any supervision. The resulting learning paradigm is simpler, less brittle, and more general, and achieves state-of-the-art transfer learning results for object detection and instance segmentation on COCO, and semantic segmentation on PASCAL and Cityscapes, while strongly surpassing supervised pre-training for video segmentation on DAVIS.

Key facts. Cited by 80 papers in the map (data through 14 Oct 2026). Builds on 80 of its 101 references that are in the map. First posted on arXiv 16 Mar 2022.

Builds on

80 of 101 references.

References · 80

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  7. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  8. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  9. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  10. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  11. 2017Mask R-CNNcited by 7,277
  12. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
38 more
  1. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  3. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  5. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  6. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  7. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  8. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  9. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  10. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  11. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
  12. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  13. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  14. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  15. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  16. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  17. 2016Colorful Image Colorizationcited by 1,114
  18. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,066
  19. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,028
  20. 2019HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clipscited by 950
  21. 2020Object-Centric Learning with Slot Attentioncited by 876
  22. 2020What Makes for Good Views for Contrastive Learning?cited by 846
  23. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 734
  24. 2022data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Languagecited by 727
  25. 2019VideoBERT: A Joint Model for Video and Language Representation Learningcited by 703
  26. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 673
  27. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 540
  28. 2017Large Batch Training of Convolutional Networkscited by 535
  29. 2019Self-labelling via simultaneous clustering and representation learningcited by 528
  30. 2017Look, Listen and Learncited by 458
  31. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
  32. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 392
  33. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 360
  34. 2016Adversarial Feature Learningcited by 350
  35. 2018Audio-Visual Scene Analysis with Self-Supervised Multisensory Featurescited by 335
  36. 2021With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representationscited by 326
  37. 2014Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networkscited by 300
  38. 2020Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learningcited by 297

50 most cited of 80 All 80 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 17; 2023: 32; 2024: 19; 2025: 8; 2026: 4.

80 papers.

Sort:

By area:

  1. 2022Bridging the Gap to Real-World Object-Centric Learningcited by 220
  2. 2022SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videoscited by 166
  3. 2022VICRegL: Self-Supervised Learning of Local Visual Featurescited by 118
  4. 2026V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learningcited by 117
  5. 2023Object-Centric Slot Diffusioncited by 90
  6. 2023SlotDiffusion: Object-Centric Generative Modeling with Diffusion Modelscited by 85
  7. 2022Perceptual Grouping in Contrastive Vision-Language Modelscited by 82
  8. 2024DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splattingcited by 82
  9. 2022NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenescited by 71
  10. 2022Self-Supervised Visual Representation Learning with Semantic Groupingcited by 70
  11. 2023Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusioncited by 64
  12. 2022Improving Object-centric Learning with Query Optimizationcited by 60
38 more
  1. 2023MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Featurescited by 57
  2. 2022Unsupervised Semantic Segmentation with Self-supervised Object-centric Representationscited by 54
  3. 2023Self-supervised Object-Centric Learning for Videoscited by 49
  4. 2023SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformerscited by 49
  5. 2023Towards In-context Scene Understandingcited by 47
  6. 2023CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detectioncited by 46
  7. 2023Mixed Autoencoder for Self-supervised Visual Representation Learningcited by 38
  8. 2022Neural Systematic Bindercited by 37
  9. 2023Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representationscited by 35
  10. 2024Disentangled 3D Scene Generation with Layout Learningcited by 33
  11. 2024EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentationcited by 27
  12. 2024GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understandingcited by 26
  13. 2022Prompt Tuning for Parameter-efficient Medical Image Segmentationcited by 22
  14. 2023CrOC: Cross-View Online Clustering for Dense Visual Representation Learningcited by 21
  15. 2023Boosting Video Object Segmentation via Space-time Correspondence Learningcited by 21
  16. 2022Self-supervised video pretraining yields robust and more human-aligned visual representationscited by 20
  17. 2024VideoMAC: Video Masked Autoencoders Meet ConvNetscited by 20
  18. 2023Top-Down Visual Attention from Analysis by Synthesiscited by 19
  19. 2023SegPrompt: Boosting Open-world Segmentation via Category-level Prompt Learningcited by 17
  20. 2023CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrappingcited by 17
  21. 2022Promising or Elusive? Unsupervised Object Segmentation from Real-world Single Imagescited by 16
  22. 2023Contrastive Training of Complex-Valued Autoencoders for Object Discoverycited by 16
  23. 2023Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Surveycited by 16
  24. 2024Near, far: Patch-ordering enhances vision foundation models' scene understandingcited by 15
  25. 2023Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learningcited by 14
  26. 2023R-MAE: Regions Meet Masked Autoencoderscited by 13
  27. 2024Learning to Compose: Improving Object Centric Learning by Injecting Compositionalitycited by 13
  28. 2023Weakly-supervised Contrastive Learning for Unsupervised Object Discoverycited by 12
  29. 2024SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fieldscited by 12
  30. 2026INSID3: Training-Free In-Context Segmentation with DINOv3cited by 12
  31. 2023Object-Centric Learning with Slot Mixture Modulecited by 11
  32. 2023Self-Supervised Representation Learning from Temporal Ordering of Automated Driving Sequencescited by 9
  33. 2023What's in a Name? Beyond Class Indices for Image Recognitioncited by 9
  34. 2024Neural Language of Thought Modelscited by 9
  35. 2024PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformerscited by 9
  36. 2022Where Should I Spend My FLOPS? Efficiency Evaluations of Visual Pre-training Methodscited by 8
  37. 2023LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-trainingcited by 8
  38. 2023SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentationcited by 7

50 most cited of 80 All 80 (JSON)