Pith. sign in

REVIEW 6 cited by

Learning from Noisy Labels with Deep Neural Networks: A Survey

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2007.08199 v7 pith:UGQOK2BY submitted 2020-07-16 cs.LG cs.CVstat.ML

classification cs.LGcs.CVstat.ML
keywords learninglabelsdeepnoisydataevaluationnetworksneural
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Deep learning has achieved remarkable success in numerous domains with help from large amounts of big data. However, the quality of data labels is a concern because of the lack of high-quality labels in many real-world scenarios. As noisy labels severely degrade the generalization performance of deep neural networks, learning from noisy labels (robust training) is becoming an important task in modern deep learning applications. In this survey, we first describe the problem of learning with label noise from a supervised learning perspective. Next, we provide a comprehensive review of 62 state-of-the-art robust training methods, all of which are categorized into five groups according to their methodological difference, followed by a systematic comparison of six properties used to evaluate their superiority. Subsequently, we perform an in-depth analysis of noise rate estimation and summarize the typically used evaluation methodology, including public noisy datasets and evaluation metrics. Finally, we present several promising research directions that can serve as a guideline for future studies. All the contents will be available at https://github.com/songhwanjun/Awesome-Noisy-Labels.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 91 citations worldwide. Full citation record

  1. Stop Replacing Noise with Noise: Two-Source Reliability Assessment for Label Correction and Sample Reweighting in Label-Noise Learning

    cs.LG 2026-08 conditional novelty 6.0 of 10

    A decoupled two-source reliability score for label correction and sample reweighting improves refurbishment-based noisy-label learners across synthetic and real-world benchmarks.

  2. Leveraging Dissimilarity Invariance as a Robust Anchor for Learning with Noisy Labels

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Under label noise, dissimilarity between unrelated samples is more stable than similarity, and the NegScale framework exploits this to improve noisy-label training.

  3. When X-ray Features Fail to Identify Intrinsic Emitters: Label Noise and Luminosity Overlap in Machine Learning Classification of AGN and Star-forming Galaxies

    astro-ph.GA 2026-07 conditional novelty 6.0 of 10

    A controlled cross-validation decomposition attributes the apparent X-ray-induced accuracy drop in AGN/SFG classification to sample selection and label noise, not to the X-ray feature itself.

  4. Combating Semantic Contamination in Learning with Label Noise

    cs.CV 2024-12 conditional novelty 6.0 of 10

    Collaborative Cross Learning reduces Semantic Contamination in noisy-label training by aligning embeddings across views and models, improving accuracy on CIFAR and real-world noisy datasets.

  5. SyntheticPop: Attacking Speaker Verification Systems With Synthetic VoicePops

    cs.CR 2025-02 conditional novelty 4.0 of 10

    SyntheticPop adds a low-frequency sine tone to spoofed training audio and drops a VoicePop-based voice authentication system from 69% to 14% accuracy.

  6. Simultaneous Automatic Picking and Manual Picking Refinement for First-Break

    cs.CV 2025-02 conditional novelty 4.0 of 10

    A latent-variable label refinement scheme trains a U-Net to pick seismic first breaks while correcting noisy manual labels, improving accuracy over standard baselines.

Pith tools