mlsanityData to 7 Oct 2026

Self-Supervised Visual Representation Learning from Hierarchical Grouping

arXiv 2012.03044 ↗First posted 5 Dec 2020cs.CVcited by 63

Not on the map. Why?

Abstract (arXiv)

We create a framework for bootstrapping visual representation learning from a primitive visual grouping capability. We operationalize grouping via a contour detector that partitions an image into regions, followed by merging of those regions into a tree hierarchy. A small supervised dataset suffices for training this grouping primitive. Across a large unlabeled dataset, we apply this learned primitive to automatically predict hierarchical region structure. These predictions serve as guidance for self-supervised contrastive feature learning: we task a deep network with producing per-pixel embeddings whose pairwise distances respect the region hierarchy. Experiments demonstrate that our approach can serve as state-of-the-art generic pre-training, benefiting downstream tasks. We additionally explore applications to semantic region search and video-based object instance tracking.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 21; 2023: 11; 2024: 10; 2025: 5; 2026: 4.

63 papers.

Sort:

By area:

  1. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  2. 2021Efficient Visual Pretraining with Contrastive Detectioncited by 150
  3. 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
  4. 2022ReCo: Retrieve and Co-segment for Zero-shot Transfercited by 115
  5. 2021MST: Masked Self-Supervised Transformer for Visual Representationcited by 114
  6. 2022Self-Supervised Learning of Object Parts for Semantic Segmentationcited by 90
  7. 2024A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Datacited by 88
  8. 2021Divide and Contrast: Self-supervised Learning from Uncurated Datacited by 85
  9. 2024Compositional Entailment Learning for Hyperbolic Vision-Language Modelscited by 72
  10. 2022Self-Supervised Visual Representation Learning with Semantic Groupingcited by 70
  11. 2022Discovering Object Masks with Transformers for Unsupervised Semantic Segmentationcited by 54
  12. 2021Revisiting Contrastive Methods for Unsupervised Learning of Visual Representationscited by 48
38 more
  1. 2023Training neural operators to preserve invariant measures of chaotic attractorscited by 43
  2. 2022ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentationcited by 42
  3. 2022Point-Level Region Contrast for Object Detection Pre-Trainingcited by 41
  4. 2022Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinitycited by 41
  5. 2022Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformerscited by 39
  6. 2023CLIP-S4: Language-Guided Self-Supervised Semantic Segmentationcited by 34
  7. 2024An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixelscited by 32
  8. 2021Self-Supervised Visual Representations Learning by Contrastive Mask Predictioncited by 31
  9. 2021Jigsaw Clustering for Unsupervised Visual Representation Learningcited by 30
  10. 2022UniVIP: A Unified Framework for Self-Supervised Visual Pre-trainingcited by 30
  11. 2024EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentationcited by 27
  12. 2022Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillationcited by 19
  13. 2022Learning Hierarchical Image Segmentation For Recognition and By Recognitioncited by 16
  14. 2021Contextualized Spatio-Temporal Contrastive Learning with Self-Supervisioncited by 15
  15. 2023R-MAE: Regions Meet Masked Autoencoderscited by 13
  16. 2022Probing Visual-Audio Representation for Video Highlight Detection via Hard-Pairs Guided Contrastive Learningcited by 9
  17. 2023Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervisioncited by 8
  18. 2023Optical Flow boosts Unsupervised Localization and Segmentationcited by 7
  19. 2022Self-supervised Semantic Segmentation Grounded in Visual Conceptscited by 6
  20. 2022Unsupervised Contrastive Domain Adaptation for Semantic Segmentationcited by 6
  21. 2021Exploring Pixel-level Self-supervision for Weakly Supervised Semantic Segmentationcited by 5
  22. 2022Embed and Emulate: Learning to estimate parameters of dynamical systems with uncertainty quantificationcited by 5
  23. 2024LaneCorrect: Self-supervised Lane Detectioncited by 5
  24. 2021Deep Neural Networks Learn Meta-Structures from Noisy Labels in Semantic Segmentationcited by 4
  25. 2021ViCE: Improving Dense Representation Learning by Superpixelization and Contrasting Cluster Assignmentcited by 4
  26. 2023Learning Neural Eigenfunctions for Unsupervised Semantic Segmentationcited by 4
  27. 2023Zero-shot Unsupervised Transfer Instance Segmentationcited by 4
  28. 2024ALPS: An Auto-Labeling and Pre-training Scheme for Remote Sensing Segmentation With Segment Anything Modelcited by 4
  29. 2024Scaling Up Single Image Dehazing Algorithm by Cross-Data Vision Alignment for Richer Representation Learning and Beyondcited by 3
  30. 2024Embed and Emulate: Contrastive representations for simulation-based inferencecited by 3
  31. 2022MSR: Making Self-supervised learning Robust to Aggressive Augmentationscited by 2
  32. 2023Structural Adversarial Objectives for Self-Supervised Representation Learningcited by 2
  33. 2025HCCM: Hierarchical Cross-Granularity Contrastive and Matching Learning for Natural Language-Guided Dronescited by 2
  34. 2022CYBORGS: Contrastively Bootstrapping Object Representations by Grounding in Segmentationcited by 1
  35. 2023Factorized Diffusion Architectures for Unsupervised Image Generation and Segmentationcited by 1
  36. 2023A Lightweight Clustering Framework for Unsupervised Semantic Segmentationcited by 1
  37. 2024Improving Object Detection via Local-global Contrastive Learningcited by 1
  38. 2025SketchYourSeg: Mask-Free Subjective Image Segmentation via Freehand Sketchescited by 1

50 most cited of 63 All 63 (JSON)