# Robust Inference via Generative Classifiers for Handling Noisy Labels

arXiv: https://arxiv.org/abs/1901.11300 · HTML: https://mlsanity.com/paper/1901.11300/

## Key facts

- Cited by 68 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2019.

## Built on by (most cited first, 30 of 68)

- [Selective-Supervised Contrastive Learning with Noisy Labels](https://mlsanity.com/paper/2203.04181/) (2022)
- [GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models](https://mlsanity.com/paper/2210.02025/) (2022)
- [FINE Samples for Learning with Noisy Labels](https://mlsanity.com/paper/2102.11628/) (2021)
- [Sample Selection with Uncertainty of Losses for Learning with Noisy Labels](https://mlsanity.com/paper/2106.00445/) (2021)
- [Learning Fast Sample Re-weighting Without Reward Data](https://mlsanity.com/paper/2109.03216/) (2021)
- [Open-set Label Noise Can Improve Robustness Against Inherent Label Noise](https://mlsanity.com/paper/2106.10891/) (2021)
- [NGC: A Unified Framework for Learning with Open-World Noisy Data](https://mlsanity.com/paper/2108.11035/) (2021)
- [LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environment](https://mlsanity.com/paper/2103.04173/) (2021)
- [Data Valuation Without Training of a Model](https://mlsanity.com/paper/2301.00930/) (2023)
- [OpenCoS: Contrastive Semi-supervised Learning for Handling Open-set Unlabeled Data](https://mlsanity.com/paper/2107.08943/) (2021)
- [From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model](https://mlsanity.com/paper/2205.00690/) (2022)
- [Why is SAM Robust to Label Noise?](https://mlsanity.com/paper/2405.03676/) (2024)
- [PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels](https://mlsanity.com/paper/2110.11809/) (2021)
- [Self-Contrastive Forward-Forward Algorithm](https://mlsanity.com/paper/2409.11593/) (2024)
- [BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learning](https://mlsanity.com/paper/2305.18377/) (2023)
- [Scalable Penalized Regression for Noise Detection in Learning with Noisy Labels](https://mlsanity.com/paper/2203.07788/) (2022)
- [An Instance-Dependent Simulation Framework for Learning with Label Noise](https://mlsanity.com/paper/2107.11413/) (2021)
- [ScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learning](https://mlsanity.com/paper/2103.11395/) (2021)
- [SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise](https://mlsanity.com/paper/2111.11288/) (2021)
- [FedNoisy: Federated Noisy Label Learning Benchmark](https://mlsanity.com/paper/2306.11650/) (2023)
- [Investigating the Learning Behaviour of In-context Learning: A Comparison with Supervised Learning](https://mlsanity.com/paper/2307.15411/) (2023)
- [NLPrompt: Noise-Label Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2412.01256/) (2024)
- [Improving Medical Image Classification in Noisy Labels Using Only Self-supervised Pretraining](https://mlsanity.com/paper/2308.04551/) (2023)
- [Regularly Truncated M-estimators for Learning with Noisy Labels](https://mlsanity.com/paper/2309.00894/) (2023)
- [FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning](https://mlsanity.com/paper/2403.16561/) (2024)
- [Noisy Label Processing for Classification: A Survey](https://mlsanity.com/paper/2404.04159/) (2024)
- [Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels](https://mlsanity.com/paper/2210.08826/) (2022)
- [ProSelfLC: Progressive Self Label Correction Towards A Low-Temperature Entropy State](https://mlsanity.com/paper/2207.00118/) (2022)
- [Generative Reasoning Integrated Label Noise Robust Deep Image Representation Learning](https://mlsanity.com/paper/2212.01261/) (2022)
- [Rethinking the impact of noisy labels in graph classification: A utility and privacy perspective](https://mlsanity.com/paper/2406.07314/) (2024)

## Abstract (arXiv)

Large-scale datasets may contain significant proportions of noisy (incorrect) class labels, and it is well-known that modern deep neural networks (DNNs) poorly generalize from such noisy training datasets. To mitigate the issue, we propose a novel inference method, termed Robust Generative classifier (RoG), applicable to any discriminative (e.g., softmax) neural classifier pre-trained on noisy datasets. In particular, we induce a generative classifier on top of hidden feature spaces of the pre-trained DNNs, for obtaining a more robust decision boundary. By estimating the parameters of generative classifier using the minimum covariance determinant estimator, we significantly improve the classification accuracy with neither re-training of the deep model nor changing its architectures. With the assumption of Gaussian distribution for features, we prove that RoG generalizes better than baselines under noisy labels. Finally, we propose the ensemble version of RoG to improve its performance by investigating the layer-wise characteristics of DNNs. Our extensive experimental results demonstrate the superiority of RoG given different learning models optimized by several training techniques to handle diverse scenarios of noisy labels.