mlsanityData to 7 Oct 2026

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

arXiv 2005.03788 ↗First posted 7 May 2020cs.LG cs.CV stat.MLcited by 33

Not on the map. Why?

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

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 10; 2023: 4; 2024: 8; 2025: 2; 2026: 3.

33 papers.

Sort:

By area:

  1. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  2. 2024Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factorscited by 106
  3. 2022Large Loss Matters in Weakly Supervised Multi-Label Classificationcited by 38
  4. 2022Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditionscited by 31
  5. 2021Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Networkcited by 30
  6. 2022From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Modelcited by 21
  7. 2021PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labelscited by 17
  8. 2024Label-Noise Robust Diffusion Modelscited by 16
  9. 2023Fine-Grained Classification with Noisy Labelscited by 15
  10. 2022Label Semantic Knowledge Distillation for Unbiased Scene Graph Generationcited by 14
  11. 2021Not All Knowledge Is Created Equal: Mutual Distillation of Confident Knowledgecited by 9
  12. 2024Foster Adaptivity and Balance in Learning with Noisy Labelscited by 9
21 more
  1. 2023Dynamics-Aware Loss for Learning with Label Noisecited by 8
  2. 2024Underwater Object Detection in the Era of Artificial Intelligence: Current, Challenge, and Futurecited by 8
  3. 2021DataCLUE: A Benchmark Suite for Data-centric NLPcited by 6
  4. 2022Semi-supervised Object Detection via Virtual Category Learningcited by 6
  5. 2022Class-Level Logit Perturbationcited by 4
  6. 2023Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Trainingcited by 4
  7. 2024Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learningcited by 4
  8. 2021Compensation Learningcited by 2
  9. 2022Learning from Noisy Labels with Coarse-to-Fine Sample Credibility Modelingcited by 2
  10. 2022Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systemscited by 2
  11. 2023URL: Combating Label Noise for Lung Nodule Malignancy Gradingcited by 2
  12. 2022An Action Is Worth Multiple Words: Handling Ambiguity in Action Recognitioncited by 1
  13. 2024Learning with Instance-Dependent Noisy Labels by Anchor Hallucination and Hard Sample Label Correctioncited by 1
  14. 2024DAC: 2D-3D Retrieval with Noisy Labels via Divide-and-Conquer Alignment and Correctioncited by 1
  15. 2025Correcting Noisy Multilabel Predictions: Modeling Label Noise through Latent Space Shiftscited by 1
  16. 2022Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systemscited by 0
  17. 2024Pairwise Similarity Distribution Clustering for Noisy Label Learningcited by 0
  18. 2025Revisiting Meta-Learning with Noisy Labels: Reweighting Dynamics and Theoretical Guaranteescited by 0
  19. 2026Efficient Content-based Recommendation Model Training via Noise-aware Coreset Selectioncited by 0
  20. 2026Efficient Bilevel Optimization for Meta Label Correction in Noisy Label Learningcited by 0
  21. 2026LiNC: Lightweight Noise Correction via Per-Sample Trust and Gaussian Mixture Modelingcited by 0