# Learning with Label Noise for Image Retrieval by Selecting Interactions

Source: [Learning with Label Noise for Image Retrieval by Selecting Interactions](<https://www.sota2.com/research/paper/68fa6b801e209131cea2ea94>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:50:06.694Z

Authors: Sarah Ibrahimi, Arnaud Sors, Rafael Sampaio de Rezende, St\\'ephane Clinchant

Published: 2021-12-20T11:27:48.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2112.10453>)

[PDF](<https://arxiv.org/pdf/2112.10453.pdf>)