Data to 14 Oct 2026

Deep Self-Learning From Noisy Labels

arXiv 1908.02160 ↗First posted 6 Aug 2019cs.CV cs.LGcited by 122

Not on the map. Why?

Abstract (arXiv)

ConvNets achieve good results when training from clean data, but learning from noisy labels significantly degrades performances and remains challenging. Unlike previous works constrained by many conditions, making them infeasible to real noisy cases, this work presents a novel deep self-learning framework to train a robust network on the real noisy datasets without extra supervision. The proposed approach has several appealing benefits. (1) Different from most existing work, it does not rely on any assumption on the distribution of the noisy labels, making it robust to real noises. (2) It does not need extra clean supervision or accessorial network to help training. (3) A self-learning framework is proposed to train the network in an iterative end-to-end manner, which is effective and efficient. Extensive experiments in challenging benchmarks such as Clothing1M and Food101-N show that our approach outperforms its counterparts in all empirical settings.

Key facts. Cited by 122 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 30; 2022: 31; 2023: 21; 2024: 19; 2025: 12; 2026: 9.

122 papers.

Sort:

By area:

2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
2022Selective-Supervised Contrastive Learning with Noisy Labelscited by 112
2021Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognitioncited by 89
2021Breaking the Dilemma of Medical Image-to-image Translationcited by 82
2021Jo-SRC: A Contrastive Approach for Combating Noisy Labelscited by 80
2021Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labelscited by 69
2022Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognitioncited by 67
2021Clusterability as an Alternative to Anchor Points When Learning with Noisy Labelscited by 65
2021NGC: A Unified Framework for Learning with Open-World Noisy Datacited by 58
2022DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotationscited by 54
2021Co-learning: Learning from Noisy Labels with Self-supervisioncited by 51
2022Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimationcited by 49

38 more

2021Hard Sample Aware Noise Robust Learning for Histopathology Image Classificationcited by 48
2022ProMix: Combating Label Noise via Maximizing Clean Sample Utilitycited by 48
2022Is one annotation enough? A data-centric image classification benchmark for noisy and ambiguous label estimationcited by 43
2021LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environmentcited by 40
2022BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptationcited by 39
2023Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discoverycited by 39
2024SelEx: Self-Expertise in Fine-Grained Generalized Category Discoverycited by 34
2022Uncertainty-Aware Learning Against Label Noise on Imbalanced Datasetscited by 28
2021Continual Learning on Noisy Data Streams via Self-Purified Replaycited by 27
2023Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Modelscited by 26
2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 25
2021Unified Robust Training for Graph NeuralNetworks against Label Noisecited by 21
2022Jigsaw-ViT: Learning Jigsaw Puzzles in Vision Transformercited by 21
2023Learning from Noisy Labels with Decoupled Meta Label Purifiercited by 21
2021Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrectioncited by 20
2023Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labelscited by 20
2022How does unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysiscited by 19
2023SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labelscited by 19
2024Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyondcited by 18
2021PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labelscited by 17
2022On the Effects of Different Types of Label Noise in Multi-Label Remote Sensing Image Classificationcited by 17
2022Instance-Dependent Noisy Label Learning via Graphical Modellingcited by 17
2021Delving into Sample Loss Curve to Embrace Noisy and Imbalanced Datacited by 16
2023Fine-Grained Classification with Noisy Labelscited by 15
2021ScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learningcited by 13
2021Learning to Rectify for Robust Learning with Noisy Labelscited by 12
2022L2B: Learning to Bootstrap Robust Models for Combating Label Noisecited by 10
2023Learning with Noisy labels via Self-supervised Adversarial Noisy Maskingcited by 10
2023Outlier Robust Adversarial Trainingcited by 10
2024Learning Discriminative Dynamics with Label Corruption for Noisy Label Detectioncited by 9
2024AffectNet+: A Database for Enhancing Facial Expression Recognition with Soft-Labelscited by 9
2021Sample Prior Guided Robust Model Learning to Suppress Noisy Labelscited by 8
2023Unlocking the Power of Open Set : A New Perspective for Open-Set Noisy Label Learningcited by 8
2024SURE: SUrvey REcipes for building reliable and robust deep networkscited by 8
2024Tackling Noisy Labels with Network Parameter Additive Decompositioncited by 8
2024Noisy Label Processing for Classification: A Surveycited by 8
2024Stable Neighbor Denoising for Source-free Domain Adaptive Segmentationcited by 8
2022PARS: Pseudo-Label Aware Robust Sample Selection for Learning with Noisy Labelscited by 7

50 most cited of 122 All 122 (JSON)