Learning With Label Noise for Image Retrieval by Selecting Interactions

Sarah Ibrahimi, Arnaud Sors, Rafael Sampaio de Rezende, Stéphane Clinchant; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022, pp. 2181-2190

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, i.e. 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.