mlsanityData to 7 Oct 2026

Weakly Supervised Keypoint Discovery

arXiv 2109.13423 ↗First posted 28 Sep 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a method for keypoint discovery from a 2D image using image-level supervision. Recent works on unsupervised keypoint discovery reliably discover keypoints of aligned instances. However, when the target instances have high viewpoint or appearance variation, the discovered keypoints do not match the semantic correspondences over different images. Our work aims to discover keypoints even when the target instances have high viewpoint and appearance variation by using image-level supervision. Motivated by the weakly-supervised learning approach, our method exploits image-level supervision to identify discriminative parts and infer the viewpoint of the target instance. To discover diverse parts, we adopt a conditional image generation approach using a pair of images with structural deformation. Finally, we enforce a viewpoint-based equivariance constraint using the keypoints from the image-level supervision to resolve the spatial correlation problem that consistently appears in the images taken from various viewpoints. Our approach achieves state-of-the-art performance for the task of keypoint estimation on the limited supervision scenarios. Furthermore, the discovered keypoints are directly applicable to downstream tasks without requiring any keypoint labels.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 30 of its 50 references that are in the map. First posted on arXiv 28 Sep 2021.

Builds on

30 of 50 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  6. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  7. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  8. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  9. 2016Convolutional Pose Machinescited by 325
  10. 2017Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localizationcited by 207
  11. 2018Markerless tracking of user-defined features with deep learningcited by 203
  12. 2020Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Predictioncited by 132
18 more
  1. 2018Unsupervised Learning of Object Landmarks through Conditional Image Generationcited by 113
  2. 2019Cross-Domain Adaptation for Animal Pose Estimationcited by 108
  3. 2015Constrained Convolutional Neural Networks for Weakly Supervised Segmentationcited by 100
  4. 2018PCL: Proposal Cluster Learning for Weakly Supervised Object Detectioncited by 97
  5. 2017Pose-driven Deep Convolutional Model for Person Re-identificationcited by 86
  6. 2020Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loopcited by 81
  7. 2018Unsupervised Discovery of Object Landmarks as Structural Representationscited by 73
  8. 2019Unsupervised Part-Based Disentangling of Object Shape and Appearancecited by 67
  9. 2017Unsupervised learning of object landmarks by factorized spatial embeddingscited by 64
  10. 2018Multi-Attention Multi-Class Constraint for Fine-grained Image Recognitioncited by 58
  11. 2014Bird Species Categorization Using Pose Normalized Deep Convolutional Netscited by 50
  12. 2017Deep Self-Taught Learning for Weakly Supervised Object Localizationcited by 27
  13. 2019Anchor Loss: Modulating Loss Scale based on Prediction Difficultycited by 14
  14. 2014Articulated motion discovery using pairs of trajectoriescited by 13
  15. 2017AnchorNet: A Weakly Supervised Network to Learn Geometry-sensitive Features For Semantic Matchingcited by 13
  16. 2018Comparator Networkscited by 13
  17. 2018Aligned to the Object, not to the Image: A Unified Pose-aligned Representation for Fine-grained Recognitioncited by 10
  18. 2019Unsupervised Part Mining for Fine-grained Image Classificationcited by 5

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 0; 2024: 1; 2025: 1.

5 papers.

  1. 2021Self-Supervised Keypoint Discovery in Behavioral Videoscited by 23
  2. 2022BKinD-3D: Self-Supervised 3D Keypoint Discovery from Multi-View Videoscited by 10
  3. 2022Demystifying Unsupervised Semantic Correspondence Estimationcited by 9
  4. 2024Learning Keypoints for Multi-Agent Behavior Analysis using Self-Supervisioncited by 2
  5. 2025SAVeD: Learning to Denoise Low-SNR Video for Improved Downstream Performancecited by 1