Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Piecewise-Linear Manifolds for Deep Metric Learning (2403.14977v1)

Published 22 Mar 2024 in cs.CV, cs.AI, cs.LG, and eess.IV

Abstract: Unsupervised deep metric learning (UDML) focuses on learning a semantic representation space using only unlabeled data. This challenging problem requires accurately estimating the similarity between data points, which is used to supervise a deep network. For this purpose, we propose to model the high-dimensional data manifold using a piecewise-linear approximation, with each low-dimensional linear piece approximating the data manifold in a small neighborhood of a point. These neighborhoods are used to estimate similarity between data points. We empirically show that this similarity estimate correlates better with the ground truth than the similarity estimates of current state-of-the-art techniques. We also show that proxies, commonly used in supervised metric learning, can be used to model the piecewise-linear manifold in an unsupervised setting, helping improve performance. Our method outperforms existing unsupervised metric learning approaches on standard zero-shot image retrieval benchmarks.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. Deep metric learning for open-set human action recognition in videos. Neural Comput. Appl., 33(4):1207–1220, feb 2021. ISSN 0941-0643. doi: 10.1007/s00521-020-05009-z. URL https://doi.org/10.1007/s00521-020-05009-z.
  2. The importance of metric learning for robotic vision: Open set recognition and active learning. In 2019 International Conference on Robotics and Automation (ICRA), pages 2924–2931, 2019. doi: 10.1109/ICRA.2019.8794188.
  3. No fuss distance metric learning using proxies. CoRR, abs/1703.07464, 2017. URL http://arxiv.org/abs/1703.07464.
  4. Softtriple loss: Deep metric learning without triplet sampling. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2019.
  5. Prototypical networks for few-shot learning. In I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017. URL https://proceedings.neurips.cc/paper/2017/file/cb8da6767461f2812ae4290eac7cbc42-Paper.pdf.
  6. Matching networks for one shot learning. Advances in neural information processing systems, 29, 2016.
  7. Discriminative deep metric learning for face verification in the wild. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014.
  8. Deep learning face representation by joint identification-verification. Advances in neural information processing systems, 27, 2014.
  9. Distance metric learning for large margin nearest neighbor classification. In Y. Weiss, B. Schölkopf, and J. Platt, editors, Advances in Neural Information Processing Systems, volume 18. MIT Press, 2005. URL https://proceedings.neurips.cc/paper/2005/file/a7f592cef8b130a6967a90617db5681b-Paper.pdf.
  10. Learning a similarity metric discriminatively, with application to face verification. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), volume 1, pages 539–546. IEEE, 2005.
  11. Multi-similarity loss with general pair weighting for deep metric learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019.
  12. 3D object representations for fine-grained categorization. In 4th International IEEE Workshop on 3D Representation and Recognition (3dRR-13), Sydney, Australia, 2013.
  13. The caltech-ucsd birds-200-2011 dataset. Technical Report CNS-TR-2011-001, California Institute of Technology, 2011.
  14. Deep metric learning via lifted structured feature embedding. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
  15. Unsupervised hyperbolic metric learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 12465–12474, June 2021.
  16. Unsupervised deep metric learning with transformed attention consistency and contrastive clustering loss. In Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm, editors, Computer Vision – ECCV 2020, pages 141–157, Cham, 2020. Springer International Publishing. ISBN 978-3-030-58621-8.
  17. Deep clustering for unsupervised learning of visual features. In Proceedings of the European Conference on Computer Vision (ECCV), September 2018.
  18. ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision (IJCV), 115(3):211–252, 2015. doi: 10.1007/s11263-015-0816-y.
  19. Self-taught metric learning without labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 7431–7441, June 2022.
  20. Kihyuk Sohn. Improved deep metric learning with multi-class n-pair loss objective. In D. Lee, M. Sugiyama, U. Luxburg, I. Guyon, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 29. Curran Associates, Inc., 2016. URL https://proceedings.neurips.cc/paper_files/paper/2016/file/6b180037abbebea991d8b1232f8a8ca9-Paper.pdf.
  21. Deep metric learning via facility location. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2206–2214, 2017. doi: 10.1109/CVPR.2017.237.
  22. Proxy anchor loss for deep metric learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020.
  23. Unsupervised deep metric learning via auxiliary rotation loss, 2019.
  24. Mining on manifolds: Metric learning without labels. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018.
  25. Unsupervised feature learning via non-parametric instance discrimination. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018.
  26. Unsupervised embedding learning via invariant and spreading instance feature. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 6210–6219, 2019.
  27. Augmentation invariant and instance spreading feature for softmax embedding. IEEE transactions on pattern analysis and machine intelligence, 44(2):924–939, 2020.
  28. A simple framework for contrastive learning of visual representations. In International conference on machine learning, pages 1597–1607. PMLR, 2020.
  29. Bootstrap your own latent-a new approach to self-supervised learning. Advances in neural information processing systems, 33:21271–21284, 2020.
  30. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9729–9738, 2020.
  31. Unsupervised learning of visual features by contrasting cluster assignments. Advances in neural information processing systems, 33:9912–9924, 2020.
  32. Vicreg: Variance-invariance-covariance regularization for self-supervised learning. arXiv preprint arXiv:2105.04906, 2021.
  33. Nonlinear dimensionality reduction by locally linear embedding. science, 290(5500):2323–2326, 2000.
  34. A global geometric framework for nonlinear dimensionality reduction. science, 290(5500):2319–2323, 2000.
  35. Proxynca++: Revisiting and revitalizing proxy neighborhood component analysis. In Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm, editors, Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXIV, volume 12369 of Lecture Notes in Computer Science, pages 448–464. Springer, 2020. doi: 10.1007/978-3-030-58586-0\_27. URL https://doi.org/10.1007/978-3-030-58586-0\_27.
  36. Relative order analysis and optimization for unsupervised deep metric learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 13999–14008, 2021.
  37. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1–9, 2015.
  38. Discriminative unsupervised feature learning with convolutional neural networks. In Z. Ghahramani, M. Welling, C. Cortes, N. Lawrence, and K.Q. Weinberger, editors, Advances in Neural Information Processing Systems, volume 27. Curran Associates, Inc., 2014. URL https://proceedings.neurips.cc/paper_files/paper/2014/file/07563a3fe3bbe7e3ba84431ad9d055af-Paper.pdf.
  39. Unsupervised deep learning by neighbourhood discovery. In International Conference on Machine Learning, pages 2849–2858. PMLR, 2019.
  40. Unsupervised metric learning with synthetic examples. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 3834–3841, 2020a.
  41. Unsupervised deep metric learning via orthogonality based probabilistic loss. IEEE Transactions on Artificial Intelligence, 1(1):74–84, 2020b.
  42. Probabilistic structural latent representation for unsupervised embedding. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 5457–5466, 2020.
  43. Spatial assembly networks for image representation learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13876–13885, 2021.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now