Towards Improved Proxy-based Deep Metric Learning Via Data-augmented Domain Adaptation

Abstract

Deep Metric Learning (DML) plays an important role in modern computer vision research, where we learn a distance metric for a set of image representations. Recent DML techniques utilize the proxy to interact with the corresponding image samples in the embedding space. However, existing proxy-based DML methods focus on learning individual proxy-to-sample distance while the overall distribution of samples and proxies lacks attention. In this paper, we present a novel proxy-based DML framework that focuses on aligning the sample and proxy distributions to improve the efficiency of proxy-based DML losses. Specifically, we propose the Data-Augmented Domain Adaptation (DADA) method to adapt the domain gap between the group of samples and proxies. To the best of our knowledge, we are the first to leverage domain adaptation to boost the performance of proxy-based DML. We show that our method can be easily plugged into existing proxy-based DML losses. Our experiments on benchmarks, including th

Stats

• citations6
• S2 citations—
• github stars0
• HF likes0
• heat score6.34
• arxiv keyren2024towards

Related papers

• Deep Metric Learning With Soft Orthogonal Proxies (2023)0.00
• Multi-head Deep Metric Learning Using Global And Local Representations (2021)6.77
• Guided Deep Metric Learning (2022)6.77
• DAS: Densely-anchored Sampling For Deep Metric Learning (2022)9.76
• No Fuss Distance Metric Learning Using Proxies (2017)20.03
• A Framework To Enhance Generalization Of Deep Metric Learning Methods Using General Discriminative Feature Learning And Class Adversarial Neural Networks (2021)7.50
• Improving Deep Metric Learning By Divide And Conquer (2021)8.09
• Hierarchical Proxy-based Loss For Deep Metric Learning (2021)10.85