On the Stability and Generalization of Triplet Learning
Triplet learning, i.e. learning from triplet data, has attracted much attention in computer vision tasks with an extremely large number of categories, e.g., face recognition and person re-identification. Albeit with rapid progress in designing and applying triplet learning algorithms, there is a lacking study on the theoretical understanding of their generalization performance. To fill this gap, this paper investigates the generalization guarantees of triplet learning by leveraging the stability analysis. Specifically, we establish the first general high-probability generalization bound for the triplet learning algorithm satisfying the uniform stability, and then 1 obtain the excess risk bounds of the order O(n logn) for both stochastic gradient descent (SGD) and regularized risk minimization (RRM), where 2n is approximately equal to the number of training samples. Moreover, an optimistic generalization bound in expectation as fast as O(n) is derived for RRM in a low noise case via the on-average stability analysis. Finally, our results are applied to triplet metric learning to characterize its theoretical underpinning.
|Document Type||Conference paper|
|Department||Department of Computer Science and Engineering|
1.College of Informatics,Huazhong Agricultural University,Wuhan,430070,China
2.College of Science,Huazhong Agricultural University,Wuhan,430070,China
3.Engineering Research Center of Intelligent Technology for Agriculture,Ministry of Education,Wuhan,430070,China
4.Key Laboratory of Smart Farming for Agricultural Animals,Wuhan,430070,China
5.Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,518055,China
6.Mohamed bin Zayed University of Artificial Intelligence,Abu Dhabi,United Arab Emirates
7.School of Computer Science and Technology,Xi’an Jiaotong University,Xi’an,710049,China
8.Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering,Ministry of Education,Xi’an,710049,China
Chen，Jun,Chen，Hong,Jiang，Xue,et al. On the Stability and Generalization of Triplet Learning[C],2023:7033-7041.
|Files in This Item:||There are no files associated with this item.|
|Recommend this item|
|Export to Endnote|
|Export to Excel|
|Export to Csv|
|Similar articles in Google Scholar|
|Similar articles in Baidu Scholar|
|Similar articles in Bing Scholar|
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.