mlsanityData to 14 Oct 2026

SCOPS: Self-Supervised Co-Part Segmentation

arXiv 1905.01298 ↗First posted 3 May 2019cs.CVcited by 100

Not on the map. Why?

Abstract (arXiv)

Parts provide a good intermediate representation of objects that is robust with respect to the camera, pose and appearance variations. Existing works on part segmentation is dominated by supervised approaches that rely on large amounts of manual annotations and can not generalize to unseen object categories. We propose a self-supervised deep learning approach for part segmentation, where we devise several loss functions that aids in predicting part segments that are geometrically concentrated, robust to object variations and are also semantically consistent across different object instances. Extensive experiments on different types of image collections demonstrate that our approach can produce part segments that adhere to object boundaries and also more semantically consistent across object instances compared to existing self-supervised techniques.

Key facts. Cited by 100 papers in the map (data through 14 Oct 2026). First posted on arXiv 3 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 27; 2022: 23; 2023: 20; 2024: 14; 2025: 13; 2026: 3.

100 papers.

Sort:

By area:

  1. 2021Deep ViT Features as Dense Visual Descriptorscited by 330
  2. 2021Motion Representations for Articulated Animationcited by 255
  3. 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
  4. 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 112
  5. 2021PartImageNet: A Large, High-Quality Dataset of Partscited by 107
  6. 2022Self-Supervised Learning of Object Parts for Semantic Segmentationcited by 90
  7. 2021Repurposing GANs for One-shot Semantic Part Segmentationcited by 88
  8. 2023Telling Left from Right: Identifying Geometry-Aware Semantic Correspondencecited by 86
  9. 2021Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalizationcited by 83
  10. 2021Unsupervised Learning of 3D Object Categories from Videos in the Wildcited by 67
  11. 2022LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discoverycited by 66
  12. 2021DOVE: Learning Deformable 3D Objects by Watching Videoscited by 61
38 more
  1. 2021DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervisioncited by 59
  2. 2021Unsupervised Part Discovery from Contrastive Reconstructioncited by 57
  3. 2021Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objectscited by 50
  4. 2021Act the Part: Learning Interaction Strategies for Articulated Object Part Discoverycited by 45
  5. 2021The Emergence of Objectness: Learning Zero-Shot Segmentation from Videoscited by 45
  6. 2021Learning Generative Models of Textured 3D Meshes from Real-World Imagescited by 44
  7. 2021Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervisioncited by 39
  8. 2021Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwritingcited by 38
  9. 2022One-Shot Transfer of Affordance Regions? AffCorrs!cited by 31
  10. 2022Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemblecited by 31
  11. 2022Skeleton-free Pose Transfer for Stylized 3D Characterscited by 30
  12. 2021Unsupervised Part Segmentation through Disentangling Appearance and Shapecited by 29
  13. 2023ASIC: Aligning Sparse in-the-wild Image Collectionscited by 27
  14. 2021Dense Unsupervised Learning for Video Segmentationcited by 26
  15. 2022Virtual Correspondence: Humans as a Cue for Extreme-View Geometrycited by 25
  16. 2022DeepCut: Unsupervised Segmentation using Graph Neural Networks Clusteringcited by 25
  17. 2023PDiscoNet: Semantically consistent part discovery for fine-grained recognitioncited by 21
  18. 2021GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generationcited by 19
  19. 2023Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detectioncited by 19
  20. 2021Weakly supervised segmentation with cross-modality equivariant constraintscited by 18
  21. 2022Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networkscited by 18
  22. 2022AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypointscited by 17
  23. 2023Sketch2Saliency: Learning to Detect Salient Objects from Human Drawingscited by 17
  24. 2023Towards Open-World Segmentation of Partscited by 15
  25. 2023Unsupervised Keypoints from Pretrained Diffusion Modelscited by 15
  26. 2021Discovering 3D Parts from Image Collectionscited by 13
  27. 2025Adaptive Part Learning for Fine-Grained Generalized Category Discovery: A Plug-and-Play Enhancementcited by 13
  28. 2021Unsupervised Co-part Segmentation through Assemblycited by 12
  29. 2023Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attentioncited by 12
  30. 2023Compositor: Bottom-up Clustering and Compositing for Robust Part and Object Segmentationcited by 11
  31. 2024Improving Visual Recognition with Hyperbolical Visual Hierarchy Mappingcited by 11
  32. 2022Improving Few-Shot Part Segmentation using Coarse Supervisioncited by 10
  33. 2024How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval?cited by 10
  34. 2023Creative Birds: Self-Supervised Single-View 3D Style Transfercited by 9
  35. 2023SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Datacited by 9
  36. 2024PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformerscited by 9
  37. 2025Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Spacecited by 9
  38. 2022HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Networkcited by 7

50 most cited of 100 All 100 (JSON)