In this paper, we propose a patch-based architecture for multi-label classification problems where only a single positive label is observed in images of the dataset. Our contributions are twofold. First, we introduce a light patch architecture based on the attention mechanism. Next, leveraging on patch embedding self-similarities, we provide a novel strategy for estimating negative examples and deal with positive and unlabeled learning problems. Experiments demonstrate that our architecture can be trained from scratch, whereas pre-training on similar databases is required for related methods from the literature.
@article{arxiv.2209.06530,
title = {A patch-based architecture for multi-label classification from single label annotations},
author = {Warren Jouanneau and Aurélie Bugeau and Marc Palyart and Nicolas Papadakis and Laurent Vézard},
journal= {arXiv preprint arXiv:2209.06530},
year = {2022}
}