4.8 Article

Deep Metric Learning With Adaptively Composite Dynamic Constraints

出版社

IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2023.3234536

关键词

Measurement; Training; Generators; Adaptation models; Task analysis; Learning systems; Vehicle dynamics; Metric learning; deep learning; image retrieval; meta-learning; dynamic constraints

向作者/读者索取更多资源

This paper proposes a deep metric learning method called DML-DC, which utilizes adaptively generated dynamic constraints for image retrieval and clustering. The method employs a learnable constraint generator to produce dynamic constraints and trains the metric towards better generalization. It formulates the deep metric learning objective under a proxy collection, pair sampling, tuple construction, and tuple weighting paradigm.
In this paper, we propose a deep metric learning with adaptively composite dynamic constraints (DML-DC) method for image retrieval and clustering. Most existing deep metric learning methods impose pre-defined constraints on the training samples, which might not be optimal at all stages of training. To address this, we propose a learnable constraint generator to adaptively produce dynamic constraints to train the metric towards good generalization. We formulate the objective of deep metric learning under a proxy Collection, pair Sampling, tuple Construction, and tuple Weighting (CSCW) paradigm. For proxy collection, we progressively update a set of proxies using a cross-attention mechanism to integrate information from the current batch of samples. For pair sampling, we employ a graph neural network to model the structural relations between sample-proxy pairs to produce the preservation probabilities for each pair. Having constructed a set of tuples based on the sampled pairs, we further re-weight each training tuple to adaptively adjust its effect on the metric. We formulate the learning of the constraint generator as a meta-learning problem, where we employ an episode-based training scheme and update the generator at each iteration to adapt to the current model status. We construct each episode by sampling two subsets of disjoint labels to simulate the procedure of training and testing and use the performance of the one-gradient-updated metric on the validation subset as the meta-objective of the assessor. We conducted extensive experiments on five widely used benchmarks under two evaluation protocols to demonstrate the effectiveness of the proposed framework.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.8
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据