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.
- Spectrally-normalized margin bounds for neural networks. Advances in neural information processing systems, 30, 2017.
- Robustness and generalization for metric learning. Neurocomputing, 151:259–267, 2015.
- On the generalization mystery in deep learning. arXiv preprint arXiv:2203.10036, 2022.
- Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778, 2016.
- Deep metric learning: The generalization analysis and an adaptive algorithm. In IJCAI, pp. 2535–2541, 2019.
- Generalization error in deep learning. In Compressed Sensing and Its Applications: Third International MATHEON Conference 2017, pp. 153–193. Springer, 2019.
- Generalization in deep learning. arXiv preprint arXiv:1710.05468, 2017.
- 3d object representations for fine-grained categorization. In 4th International IEEE Workshop on 3D Representation and Recognition (3dRR-13), Sydney, Australia, 2013.
- Sphereface: Deep hypersphere embedding for face recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 212–220, 2017.
- Deepfashion: Powering robust clothes recognition and retrieval with rich annotations. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016.
- Maharaj, T. Generalizing in the real world with representation learning. arXiv preprint arXiv:2210.09925, 2022.
- Sharing matters for generalization in deep metric learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(1):416–427, 2020.
- 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.
- Neyshabur, B. Implicit regularization in deep learning. arXiv preprint arXiv:1709.01953, 2017.
- Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830, 2011.
- Roelofs, R. Measuring Generalization and overfitting in Machine learning. University of California, Berkeley, 2019.
- Revisiting training strategies and generalization performance in deep metric learning. In International Conference on Machine Learning, pp. 8242–8252. PMLR, 2020.
- The singular values of convolutional layers. arXiv preprint arXiv:1805.10408, 2018.
- Cub196. Technical Report CNS-TR-2011-001, California Institute of Technology, 2011.
- 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.
- mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412, 2017.
- Zhang, J. Estimating confidence intervals on accuracy in classification in machine learning. 2019.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.