Pith. sign in

REVIEW 1 cited by

Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels

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 2006.07831 v2 pith:FO5L4YQY submitted 2020-06-14 cs.LG stat.ML

classification cs.LGstat.ML
keywords noisylabelslearningdataclassclass2similabelnoise
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Learning with noisy labels has attracted a lot of attention in recent years, where the mainstream approaches are in pointwise manners. Meanwhile, pairwise manners have shown great potential in supervised metric learning and unsupervised contrastive learning. Thus, a natural question is raised: does learning in a pairwise manner mitigate label noise? To give an affirmative answer, in this paper, we propose a framework called Class2Simi: it transforms data points with noisy class labels to data pairs with noisy similarity labels, where a similarity label denotes whether a pair shares the class label or not. Through this transformation, the reduction of the noise rate is theoretically guaranteed, and hence it is in principle easier to handle noisy similarity labels. Amazingly, DNNs that predict the clean class labels can be trained from noisy data pairs if they are first pretrained from noisy data points. Class2Simi is computationally efficient because not only this transformation is on-the-fly in mini-batches, but also it just changes loss computation on top of model prediction into a pairwise manner. Its effectiveness is verified by extensive experiments.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Securing Contrastive mmWave-based Human Activity Recognition against Adversarial Label Flipping

    cs.CR 2026-08 conditional novelty 5.0 of 10

    Trajectory-aware label flipping attacks degrade contrastive mmWave human activity recognition, and a selective contrastive learning defense keeps accuracy above 90% even at 40% poisoned labels.

Pith tools