Multi-label learning is an emerging extension of the multi-class classification where an image contains multiple labels. Not only acquiring a clean and fully labeled dataset in multi-label learning is extremely expensive, but also many of the actual labels are corrupted or missing due to the automated or non-expert annotation techniques. Noisy label data decrease the prediction performance drastically. In this paper, we propose a novel Gold Asymmetric Loss Correction with Single-Label Regulators (GALC-SLR) that operates robust against noisy labels. GALC-SLR estimates the noise confusion matrix using single-label samples, then constructs an asymmetric loss correction via estimated confusion matrix to avoid overfitting to the noisy labels. Empirical results show that our method outperforms the state-of-the-art original asymmetric loss multi-label classifier under all corruption levels, showing mean average precision improvement up to 28.67% on a real world dataset of MS-COCO, yielding a better generalization of the unseen data and increased prediction performance.
@article{arxiv.2108.02032,
title = {Multi-Label Gold Asymmetric Loss Correction with Single-Label Regulators},
author = {Cosmin Octavian Pene and Amirmasoud Ghiassi and Taraneh Younesian and Robert Birke and Lydia Y. Chen},
journal= {arXiv preprint arXiv:2108.02032},
year = {2021}
}