DOST -- Domain Obedient Self-supervised Training for Multi Label Classification with Noisy Labels

TL;DR

This paper introduces DOST, a self-supervised training method that incorporates domain rules to improve multi-label classification accuracy and robustness against noisy annotations, especially in domain-sensitive tasks.

Contribution

The paper proposes the DOST paradigm, integrating domain rules into self-supervised learning to enhance multi-label classification and reduce the impact of noisy labels.

Findings

DOST improves key metrics across datasets.

It often counteracts the effects of label noise.

Enhances domain rule compliance in predictions.

Abstract

The enormous demand for annotated data brought forth by deep learning techniques has been accompanied by the problem of annotation noise. Although this issue has been widely discussed in machine learning literature, it has been relatively unexplored in the context of "multi-label classification" (MLC) tasks which feature more complicated kinds of noise. Additionally, when the domain in question has certain logical constraints, noisy annotations often exacerbate their violations, making such a system unacceptable to an expert. This paper studies the effect of label noise on domain rule violation incidents in the MLC task, and incorporates domain rules into our learning algorithm to mitigate the effect of noise. We propose the Domain Obedient Self-supervised Training (DOST) paradigm which not only makes deep learning models more aligned to domain rules, but also improves learning performance in key metrics and minimizes the effect of annotation noise. This novel approach uses domain guidance to detect offending annotations and deter rule-violating predictions in a self-supervised manner, thus making it more "data efficient" and domain compliant. Empirical studies, performed over two large scale multi-label classification datasets, demonstrate that our method results in improvement across the board, and often entirely counteracts the effect of noise.