English

Learning with Label Noise for Image Retrieval by Selecting Interactions

Computer Vision and Pattern Recognition 2021-12-22 v2

Abstract

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.

Keywords

Cite

@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}
}

Comments

Accepted at WACV 2022. 13 pages, 5 figures

R2 v1 2026-06-24T08:24:21.794Z