# Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks

arXiv: https://arxiv.org/abs/1706.00038 · HTML: https://mlsanity.com/paper/1706.00038/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 May 2017.

## Built on by (most cited first, 30 of 78)

- [Partial success in closing the gap between human and machine vision](https://mlsanity.com/paper/2106.07411/) (2021)
- [Learning with Feature-Dependent Label Noise: A Progressive Approach](https://mlsanity.com/paper/2103.07756/) (2021)
- [Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels](https://mlsanity.com/paper/2105.04522/) (2021)
- [The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation](https://mlsanity.com/paper/2206.03014/) (2022)
- [Part-based Pseudo Label Refinement for Unsupervised Person Re-identification](https://mlsanity.com/paper/2203.14675/) (2022)
- [ProMix: Combating Label Noise via Maximizing Clean Sample Utility](https://mlsanity.com/paper/2207.10276/) (2022)
- [Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning](https://mlsanity.com/paper/2502.01968/) (2025)
- [Faster Meta Update Strategy for Noise-Robust Deep Learning](https://mlsanity.com/paper/2104.15092/) (2021)
- [Joint Negative and Positive Learning for Noisy Labels](https://mlsanity.com/paper/2104.06574/) (2021)
- [Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network](https://mlsanity.com/paper/2105.13001/) (2021)
- [Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.04618/) (2021)
- [Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation](https://mlsanity.com/paper/2112.07431/) (2021)
- [BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency](https://mlsanity.com/paper/2303.12419/) (2023)
- [Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models](https://mlsanity.com/paper/2311.11202/) (2023)
- [Unified Robust Training for Graph NeuralNetworks against Label Noise](https://mlsanity.com/paper/2103.03414/) (2021)
- [NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation](https://mlsanity.com/paper/2207.13316/) (2022)
- [SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels](https://mlsanity.com/paper/2308.12064/) (2023)
- [Consistency Regularization Can Improve Robustness to Label Noise](https://mlsanity.com/paper/2110.01242/) (2021)
- [Exponentiated Gradient Reweighting for Robust Training Under Label Noise and Beyond](https://mlsanity.com/paper/2104.01493/) (2021)
- [AQuA: A Benchmarking Tool for Label Quality Assessment](https://mlsanity.com/paper/2306.09467/) (2023)
- [Generalized Data Weighting via Class-level Gradient Manipulation](https://mlsanity.com/paper/2111.00056/) (2021)
- [Scalable Penalized Regression for Noise Detection in Learning with Noisy Labels](https://mlsanity.com/paper/2203.07788/) (2022)
- [Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videos](https://mlsanity.com/paper/2203.13704/) (2022)
- [Boosting Facial Expression Recognition by A Semi-Supervised Progressive Teacher](https://mlsanity.com/paper/2205.14361/) (2022)
- [Is your noise correction noisy? PLS: Robustness to label noise with two stage detection](https://mlsanity.com/paper/2210.04578/) (2022)
- [L2B: Learning to Bootstrap Robust Models for Combating Label Noise](https://mlsanity.com/paper/2202.04291/) (2022)
- [CCMN: A General Framework for Learning with Class-Conditional Multi-Label Noise](https://mlsanity.com/paper/2105.07338/) (2021)
- [Noisy Annotation Refinement for Object Detection](https://mlsanity.com/paper/2110.10456/) (2021)
- [Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Features](https://mlsanity.com/paper/2212.09321/) (2022)
- [Latent Class-Conditional Noise Model](https://mlsanity.com/paper/2302.09595/) (2023)

## Abstract (arXiv)

Collecting large training datasets, annotated with high-quality labels, is costly and time-consuming. This paper proposes a novel framework for training deep convolutional neural networks from noisy labeled datasets that can be obtained cheaply. The problem is formulated using an undirected graphical model that represents the relationship between noisy and clean labels, trained in a semi-supervised setting. In our formulation, the inference over latent clean labels is tractable and is regularized during training using auxiliary sources of information. The proposed model is applied to the image labeling problem and is shown to be effective in labeling unseen images as well as reducing label noise in training on CIFAR-10 and MS COCO datasets.