# Training Convolutional Networks with Noisy Labels

arXiv: https://arxiv.org/abs/1406.2080 · HTML: https://mlsanity.com/paper/1406.2080/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2014.

## Built on by (most cited first, 30 of 48)

- [ZeroGen: Efficient Zero-shot Learning via Dataset Generation](https://mlsanity.com/paper/2202.07922/) (2022)
- [Learning with Neighbor Consistency for Noisy Labels](https://mlsanity.com/paper/2202.02200/) (2022)
- [DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotations](https://mlsanity.com/paper/2201.09637/) (2022)
- [Uncertainty-Aware Learning Against Label Noise on Imbalanced Datasets](https://mlsanity.com/paper/2207.05471/) (2022)
- [Estimating label quality and errors in semantic segmentation data via any model](https://mlsanity.com/paper/2307.05080/) (2023)
- [ObjectLab: Automated Diagnosis of Mislabeled Images in Object Detection Data](https://mlsanity.com/paper/2309.00832/) (2023)
- [Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/2210.07636/) (2022)
- [AdaCo: Overcoming Visual Foundation Model Noise in 3D Semantic Segmentation via Adaptive Label Correction](https://mlsanity.com/paper/2412.18255/) (2024)
- [ProSelfLC: Progressive Self Label Correction Towards A Low-Temperature Entropy State](https://mlsanity.com/paper/2207.00118/) (2022)
- [Compensation Learning in Semantic Segmentation](https://mlsanity.com/paper/2304.13428/) (2023)
- [Unified Risk Analysis for Weakly Supervised Learning](https://mlsanity.com/paper/2309.08216/) (2023)
- [UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning](https://mlsanity.com/paper/2103.10773/) (2021)
- [Co-matching: Combating Noisy Labels by Augmentation Anchoring](https://mlsanity.com/paper/2103.12814/) (2021)
- [Denoising Noisy Neural Networks: A Bayesian Approach with Compensation](https://mlsanity.com/paper/2105.10699/) (2021)
- [Rethinking Noisy Label Models: Labeler-Dependent Noise with Adversarial Awareness](https://mlsanity.com/paper/2105.14083/) (2021)
- [Ambiguous Annotations: When is a Pedestrian not a Pedestrian?](https://mlsanity.com/paper/2405.08794/) (2024)
- [One-Step Abductive Multi-Target Learning with Diverse Noisy Samples and Its Application to Tumour Segmentation for Breast Cancer](https://mlsanity.com/paper/2110.10325/) (2021)
- [Asymmetric error control under imperfect supervision: a label-noise-adjusted Neyman-Pearson umbrella algorithm](https://mlsanity.com/paper/2112.00314/) (2021)
- [Enhancing Noise-Robust Losses for Large-Scale Noisy Data Learning](https://mlsanity.com/paper/2306.05497/) (2023)
- [GenKL: An Iterative Framework for Resolving Label Ambiguity and Label Non-conformity in Web Images Via a New Generalized KL Divergence](https://mlsanity.com/paper/2307.09810/) (2023)
- [CHEF: A Cheap and Fast Pipeline for Iteratively Cleaning Label Uncertainties (Technical Report)](https://mlsanity.com/paper/2107.08588/) (2021)
- [Analysis of the performance of U-Net neural networks for the segmentation of living cells](https://mlsanity.com/paper/2210.01538/) (2022)
- [Robust and Explainable Fine-Grained Visual Classification with Transfer Learning: A Dual-Carriageway Framework](https://mlsanity.com/paper/2405.05853/) (2024)
- [Spring-block theory of feature learning in deep neural networks](https://mlsanity.com/paper/2407.19353/) (2024)
- [Breast Mass Detection with Faster R-CNN: On the Feasibility of Learning from Noisy Annotations](https://mlsanity.com/paper/2104.12218/) (2021)
- [WALNUT: A Benchmark on Semi-weakly Supervised Learning for Natural Language Understanding](https://mlsanity.com/paper/2108.12603/) (2021)
- [Regularization by Misclassification in ReLU Neural Networks](https://mlsanity.com/paper/2111.02154/) (2021)
- [One-shot Weakly-Supervised Segmentation in Medical Images](https://mlsanity.com/paper/2111.10773/) (2021)
- [Shuffle Augmentation of Features from Unlabeled Data for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2201.11963/) (2022)
- [Self-supervised Speaker Recognition Training Using Human-Machine Dialogues](https://mlsanity.com/paper/2202.03484/) (2022)

## Abstract (arXiv)

The availability of large labeled datasets has allowed Convolutional Network models to achieve impressive recognition results. However, in many settings manual annotation of the data is impractical; instead our data has noisy labels, i.e. there is some freely available label for each image which may or may not be accurate. In this paper, we explore the performance of discriminatively-trained Convnets when trained on such noisy data. We introduce an extra noise layer into the network which adapts the network outputs to match the noisy label distribution. The parameters of this noise layer can be estimated as part of the training process and involve simple modifications to current training infrastructures for deep networks. We demonstrate the approaches on several datasets, including large scale experiments on the ImageNet classification benchmark.