Papers
Topics
Authors
Recent
Search
2000 character limit reached

Catching Image Retrieval Generalization

Published 23 Jun 2023 in cs.LG and cs.CV | (2306.13357v1)

Abstract: The concepts of overfitting and generalization are vital for evaluating machine learning models. In this work, we show that the popular Recall@K metric depends on the number of classes in the dataset, which limits its ability to estimate generalization. To fix this issue, we propose a new metric, which measures retrieval performance, and, unlike Recall@K, estimates generalization. We apply the proposed metric to popular image retrieval methods and provide new insights about deep metric learning generalization.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (22)
  1. Spectrally-normalized margin bounds for neural networks. Advances in neural information processing systems, 30, 2017.
  2. Robustness and generalization for metric learning. Neurocomputing, 151:259–267, 2015.
  3. On the generalization mystery in deep learning. arXiv preprint arXiv:2203.10036, 2022.
  4. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.  770–778, 2016.
  5. Deep metric learning: The generalization analysis and an adaptive algorithm. In IJCAI, pp.  2535–2541, 2019.
  6. Generalization error in deep learning. In Compressed Sensing and Its Applications: Third International MATHEON Conference 2017, pp.  153–193. Springer, 2019.
  7. Generalization in deep learning. arXiv preprint arXiv:1710.05468, 2017.
  8. 3d object representations for fine-grained categorization. In 4th International IEEE Workshop on 3D Representation and Recognition (3dRR-13), Sydney, Australia, 2013.
  9. Sphereface: Deep hypersphere embedding for face recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.  212–220, 2017.
  10. Deepfashion: Powering robust clothes recognition and retrieval with rich annotations. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016.
  11. Maharaj, T. Generalizing in the real world with representation learning. arXiv preprint arXiv:2210.09925, 2022.
  12. Sharing matters for generalization in deep metric learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(1):416–427, 2020.
  13. A metric learning reality check. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXV 16, pp.  681–699. Springer, 2020.
  14. Neyshabur, B. Implicit regularization in deep learning. arXiv preprint arXiv:1709.01953, 2017.
  15. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830, 2011.
  16. Roelofs, R. Measuring Generalization and overfitting in Machine learning. University of California, Berkeley, 2019.
  17. Revisiting training strategies and generalization performance in deep metric learning. In International Conference on Machine Learning, pp. 8242–8252. PMLR, 2020.
  18. The singular values of convolutional layers. arXiv preprint arXiv:1805.10408, 2018.
  19. Cub196. Technical Report CNS-TR-2011-001, California Institute of Technology, 2011.
  20. Cutmix: Regularization strategy to train strong classifiers with localizable features. In Proceedings of the IEEE/CVF international conference on computer vision, pp.  6023–6032, 2019.
  21. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412, 2017.
  22. Zhang, J. Estimating confidence intervals on accuracy in classification in machine learning. 2019.

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Authors (2)

Collections

Sign up for free to add this paper to one or more collections.