Learning with noisy labels is an active research area for image classification. However, the effect of noisy labels on image retrieval has been less studied. In this work, we propose a noise-resistant method for image retrieval named Teacher-based Selection of Interactions, T-SINT, which identifies noisy interactions, ie. elements in the distance matrix, and selects correct positive and negative interactions to be considered in the retrieval loss by using a teacher-based training setup which contributes to the stability. As a result, it consistently outperforms state-of-the-art methods on high noise rates across benchmark datasets with synthetic noise and more realistic noise.
@article{arxiv.2112.10453,
title = {Learning with Label Noise for Image Retrieval by Selecting Interactions},
author = {Sarah Ibrahimi and Arnaud Sors and Rafael Sampaio de Rezende and Stéphane Clinchant},
journal= {arXiv preprint arXiv:2112.10453},
year = {2021}
}