Robust Calibrate Proxy Loss for Deep Metric Learning
This work addresses a specific limitation in deep metric learning for retrieval tasks, offering an incremental improvement over existing proxy-based methods.
The paper tackles the problem of proxy-based deep metric learning methods struggling to accurately represent class feature distributions, proposing a Calibrate Proxy structure that uses real sample information and a calibration loss to improve similarity calculations and constrain proxy optimization. The results show the approach effectively improves performance of proxy-based losses on three public datasets and synthetic label-noise datasets.
The mainstream researche in deep metric learning can be divided into two genres: proxy-based and pair-based methods. Proxy-based methods have attracted extensive attention due to the lower training complexity and fast network convergence. However, these methods have limitations as the poxy optimization is done by network, which makes it challenging for the proxy to accurately represent the feature distrubtion of the real class of data. In this paper, we propose a Calibrate Proxy (CP) structure, which uses the real sample information to improve the similarity calculation in proxy-based loss and introduces a calibration loss to constraint the proxy optimization towards the center of the class features. At the same time, we set a small number of proxies for each class to alleviate the impact of intra-class differences on retrieval performance. The effectiveness of our method is evaluated by extensive experiments on three public datasets and multiple synthetic label-noise datasets. The results show that our approach can effectively improve the performance of commonly used proxy-based losses on both regular and noisy datasets.