Deep Image Retrieval is not Robust to Label Noise
This addresses the problem of label noise in image retrieval datasets for researchers and practitioners, highlighting a vulnerability that could affect model reliability.
The study found that deep image retrieval methods are less robust to label noise compared to image classification, and it investigated specific types of label noise in retrieval tasks, showing performance degradation.
Large-scale datasets are essential for the success of deep learning in image retrieval. However, manual assessment errors and semi-supervised annotation techniques can lead to label noise even in popular datasets. As previous works primarily studied annotation quality in image classification tasks, it is still unclear how label noise affects deep learning approaches to image retrieval. In this work, we show that image retrieval methods are less robust to label noise than image classification ones. Furthermore, we, for the first time, investigate different types of label noise specific to image retrieval tasks and study their effect on model performance.