arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.09060cs.CVcs.LGstat.ML
收藏

基于机会约束的深度度量学习

Deep Metric Learning with Chance Constraints

MetaDialog;Cerebrate AI;OGAM;METU(中东技术大学)

Yeti Z. Gurbuz, Ogul Can, A. Aydin Alatan

AI总结:

本文将深度度量学习与有限机会约束的可行性问题相联系,提出一种通过迭代投影求解约束交集的算法,利用多个代理并反复重初始化以提升泛化性能。

摘要:

深度度量学习(DML)旨在最小化嵌入空间中成对类内/类间邻近度违反的经验期望损失。我们将DML与有限机会约束的可行性问题联系起来。我们证明了基于代理的DML的最小化器满足特定的机会约束,并且基于代理的方法的最坏情况泛化性能可以通过覆盖相应类样本整个域的类代理周围最小球的半径来表征,这表明每个类使用多个代理有助于提升性能。为了提供可扩展的算法并利用更多代理,我们考虑了基于代理的DML实例的最小化器所隐含的机会约束,并将DML重新表述为在这些约束的交集中寻找可行点,从而得到一个通过迭代投影近似求解的问题。简而言之,我们反复训练正则化的基于代理的损失,并使用精心挑选的新样本的嵌入重新初始化代理。我们将我们的方法应用于4种广泛接受的DML损失,并在4个流行的DML基准上进行了广泛评估,证明了其有效性。代码可在:https://github.com/yetigurbuz/ccp-dml 获取。

英文摘要:

Deep metric learning (DML) aims to minimize empirical expected loss of the pairwise intra-/inter- class proximity violations in the embedding space. We relate DML to feasibility problem of finite chance constraints. We show that minimizer of proxy-based DML satisfies certain chance constraints, and that the worst case generalization performance of the proxy-based methods can be characterized by the radius of the smallest ball around a class proxy to cover the entire domain of the corresponding class samples, suggesting multiple proxies per class helps performance. To provide a scalable algorithm as well as exploiting more proxies, we consider the chance constraints implied by the minimizers of proxy-based DML instances and reformulate DML as finding a feasible point in intersection of such constraints, resulting in a problem to be approximately solved by iterative projections. Simply put, we repeatedly train a regularized proxy-based loss and re-initialize the proxies with the embeddings of the deliberately selected new samples. We applied our method with 4 well-accepted DML losses and show the effectiveness with extensive evaluations on 4 popular DML benchmarks. Code is available at: https://github.com/yetigurbuz/ccp-dml

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑