# ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks

arXiv: https://arxiv.org/abs/2005.03788 · HTML: https://mlsanity.com/paper/2005.03788/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2020.

## Built on by (most cited first, 30 of 33)

- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)
- [Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors](https://mlsanity.com/paper/2403.07366/) (2024)
- [Large Loss Matters in Weakly Supervised Multi-Label Classification](https://mlsanity.com/paper/2206.03740/) (2022)
- [Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions](https://mlsanity.com/paper/2207.06825/) (2022)
- [Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network](https://mlsanity.com/paper/2105.13001/) (2021)
- [From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model](https://mlsanity.com/paper/2205.00690/) (2022)
- [PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels](https://mlsanity.com/paper/2110.11809/) (2021)
- [Label-Noise Robust Diffusion Models](https://mlsanity.com/paper/2402.17517/) (2024)
- [Fine-Grained Classification with Noisy Labels](https://mlsanity.com/paper/2303.02404/) (2023)
- [Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2208.03763/) (2022)
- [Not All Knowledge Is Created Equal: Mutual Distillation of Confident Knowledge](https://mlsanity.com/paper/2106.01489/) (2021)
- [Dynamics-Aware Loss for Learning with Label Noise](https://mlsanity.com/paper/2303.11562/) (2023)
- [Foster Adaptivity and Balance in Learning with Noisy Labels](https://mlsanity.com/paper/2407.02778/) (2024)
- [Underwater Object Detection in the Era of Artificial Intelligence: Current, Challenge, and Future](https://mlsanity.com/paper/2410.05577/) (2024)
- [DataCLUE: A Benchmark Suite for Data-centric NLP](https://mlsanity.com/paper/2111.08647/) (2021)
- [Semi-supervised Object Detection via Virtual Category Learning](https://mlsanity.com/paper/2207.03433/) (2022)
- [Class-Level Logit Perturbation](https://mlsanity.com/paper/2209.05668/) (2022)
- [Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training](https://mlsanity.com/paper/2308.16376/) (2023)
- [Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning](https://mlsanity.com/paper/2403.02690/) (2024)
- [Compensation Learning](https://mlsanity.com/paper/2107.11921/) (2021)
- [Learning from Noisy Labels with Coarse-to-Fine Sample Credibility Modeling](https://mlsanity.com/paper/2208.10683/) (2022)
- [Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems](https://mlsanity.com/paper/2209.10058/) (2022)
- [URL: Combating Label Noise for Lung Nodule Malignancy Grading](https://mlsanity.com/paper/2308.08772/) (2023)
- [An Action Is Worth Multiple Words: Handling Ambiguity in Action Recognition](https://mlsanity.com/paper/2210.04933/) (2022)
- [Learning with Instance-Dependent Noisy Labels by Anchor Hallucination and Hard Sample Label Correction](https://mlsanity.com/paper/2407.07331/) (2024)
- [DAC: 2D-3D Retrieval with Noisy Labels via Divide-and-Conquer Alignment and Correction](https://mlsanity.com/paper/2407.17779/) (2024)
- [Correcting Noisy Multilabel Predictions: Modeling Label Noise through Latent Space Shifts](https://mlsanity.com/paper/2502.14281/) (2025)
- [Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems](https://mlsanity.com/paper/2210.01000/) (2022)
- [Pairwise Similarity Distribution Clustering for Noisy Label Learning](https://mlsanity.com/paper/2404.01853/) (2024)
- [Revisiting Meta-Learning with Noisy Labels: Reweighting Dynamics and Theoretical Guarantees](https://mlsanity.com/paper/2510.12209/) (2025)

## Abstract (arXiv)

To train robust deep neural networks (DNNs), we systematically study several target modification approaches, which include output regularisation, self and non-self label correction (LC). Two key issues are discovered: (1) Self LC is the most appealing as it exploits its own knowledge and requires no extra models. However, how to automatically decide the trust degree of a learner as training goes is not well answered in the literature? (2) Some methods penalise while the others reward low-entropy predictions, prompting us to ask which one is better? To resolve the first issue, taking two well-accepted propositions--deep neural networks learn meaningful patterns before fitting noise [3] and minimum entropy regularisation principle [10]--we propose a novel end-to-end method named ProSelfLC, which is designed according to learning time and entropy. Specifically, given a data point, we progressively increase trust in its predicted label distribution versus its annotated one if a model has been trained for enough time and the prediction is of low entropy (high confidence). For the second issue, according to ProSelfLC, we empirically prove that it is better to redefine a meaningful low-entropy status and optimise the learner toward it. This serves as a defence of entropy minimisation. We demonstrate the effectiveness of ProSelfLC through extensive experiments in both clean and noisy settings. The source code is available at https://github.com/XinshaoAmosWang/ProSelfLC-CVPR2021. Keywords: entropy minimisation, maximum entropy, confidence penalty, self knowledge distillation, label correction, label noise, semi-supervised learning, output regularisation