Data to 7 Oct 2026

Dimensionality-Driven Learning with Noisy Labels

arXiv 1806.02612 ↗First posted 7 Jun 2018cs.CV cs.LG stat.MLcited by 173

Not on the map. Why?

Abstract (arXiv)

Datasets with significant proportions of noisy (incorrect) class labels present challenges for training accurate Deep Neural Networks (DNNs). We propose a new perspective for understanding DNN generalization for such datasets, by investigating the dimensionality of the deep representation subspace of training samples. We show that from a dimensionality perspective, DNNs exhibit quite distinctive learning styles when trained with clean labels versus when trained with a proportion of noisy labels. Based on this finding, we develop a new dimensionality-driven learning strategy, which monitors the dimensionality of subspaces during training and adapts the loss function accordingly. We empirically demonstrate that our approach is highly tolerant to significant proportions of noisy labels, and can effectively learn low-dimensional local subspaces that capture the data distribution.

Key facts. Cited by 173 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 57; 2022: 41; 2023: 29; 2024: 27; 2025: 13; 2026: 6.

173 papers.

Sort:

By area:

2023Similarity of Neural Network Models: A Survey of Functional and Representational Measurescited by 128
2021Understanding and Improving Early Stopping for Learning with Noisy Labelscited by 112
2022Selective-Supervised Contrastive Learning with Noisy Labelscited by 112
2021Learning with Feature-Dependent Label Noise: A Progressive Approachcited by 102
2021Provably End-to-end Label-Noise Learning without Anchor Pointscited by 97
2022Robust Training under Label Noise by Over-parameterizationcited by 93
2021Augmentation Strategies for Learning with Noisy Labelscited by 86
2021Robust Audio-Visual Instance Discriminationcited by 80
2021Sample Selection with Uncertainty of Losses for Learning with Noisy Labelscited by 79
2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
2021NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphscited by 73
2021Intrinsic Dimension, Persistent Homology and Generalization in Neural Networkscited by 70

38 more

2021Learning Fast Sample Re-weighting Without Reward Datacited by 69
2022FedCorr: Multi-Stage Federated Learning for Label Noise Correctioncited by 61
2022The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generationcited by 60
2021NGC: A Unified Framework for Learning with Open-World Noisy Datacited by 58
2022Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learningcited by 49
2022Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimationcited by 49
2021Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detectioncited by 48
2021Sample Selection for Fair and Robust Trainingcited by 48
2022Investigating Why Contrastive Learning Benefits Robustness Against Label Noisecited by 46
2021LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environmentcited by 40
2021Faster Meta Update Strategy for Noise-Robust Deep Learningcited by 38
2021Rethinking Graph Auto-Encoder Models for Attributed Graph Clusteringcited by 37
2021Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterioncited by 36
2021Robust Long-Tailed Learning under Label Noisecited by 35
2021Joint Negative and Positive Learning for Noisy Labelscited by 34
2021Boosting Co-teaching with Compression Regularization for Label Noisecited by 31
2021Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Networkcited by 30
2022Uncertainty-Aware Learning Against Label Noise on Imbalanced Datasetscited by 28
2023Twin Contrastive Learning with Noisy Labelscited by 28
2021Continual Learning on Noisy Data Streams via Self-Purified Replaycited by 27
2023BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistencycited by 27
2022Sparse Double Descent: Where Network Pruning Aggravates Overfittingcited by 26
2022Neighborhood Collective Estimation for Noisy Label Identification and Correctioncited by 22
2022Intrinsic Dimensionality Estimation within Tight Localities: A Theoretical and Experimental Analysiscited by 22
2022When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Methodcited by 21
2023Why Is Prompt Tuning for Vision-Language Models Robust to Noisy Labels?cited by 21
2021Adaptive Sample Selection for Robust Learning under Label Noisecited by 20
2021Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrectioncited by 20
2022Robust Object Detection With Inaccurate Bounding Boxescited by 20
2022NICEST: Noisy Label Correction and Training for Robust Scene Graph Generationcited by 19
2021Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regressioncited by 18
2021Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning with Label Noisecited by 18
2021PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labelscited by 17
2021Delving into Sample Loss Curve to Embrace Noisy and Imbalanced Datacited by 16
2022Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labelscited by 16
2022Scalable Penalized Regression for Noise Detection in Learning with Noisy Labelscited by 15
2021ScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learningcited by 13
2023FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labelscited by 13

50 most cited of 173 All 173 (JSON)