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

arXiv: https://arxiv.org/abs/2308.05101 · HTML: https://mlsanity.com/paper/2308.05101/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 44 references that are in the map.
- First posted on arXiv 9 Aug 2023.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [Robust Loss Functions under Label Noise for Deep Neural Networks](https://mlsanity.com/paper/1712.09482/) (2017)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise](https://mlsanity.com/paper/1802.05300/) (2018)
- [Deep learning with noisy labels: exploring techniques and remedies in medical image analysis](https://mlsanity.com/paper/1912.02911/) (2019)
- [Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks](https://mlsanity.com/paper/1706.00038/) (2017)
- [Multi-Label Classification with Label Graph Superimposing](https://mlsanity.com/paper/1911.09243/) (2019)
- [Coherent Hierarchical Multi-Label Classification Networks](https://mlsanity.com/paper/2010.10151/) (2020)
- [Residual Attention: A Simple but Effective Method for Multi-Label Recognition](https://mlsanity.com/paper/2108.02456/) (2021)
- [Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution](https://mlsanity.com/paper/2109.04712/) (2021)
- [Domain Knowledge Alleviates Adversarial Attacks in Multi-Label Classifiers](https://mlsanity.com/paper/2006.03833/) (2020)
- [Evaluating Multi-label Classifiers with Noisy Labels](https://mlsanity.com/paper/2102.08427/) (2021)
- [Multi-Label Learning from Medical Plain Text with Convolutional Residual Models](https://mlsanity.com/paper/1801.05062/) (2018)

## Built on by (most cited first, 1 of 1)

- [VALUED -- Vision and Logical Understanding Evaluation Dataset](https://mlsanity.com/paper/2311.12610/) (2023)

## Abstract (arXiv)

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.