SOTAVerified

Learning with noisy labels

Learning with noisy labels means When we say "noisy labels," we mean that an adversary has intentionally messed up the labels, which would have come from a "clean" distribution otherwise. This setting can also be used to cast learning from only positive and unlabeled data.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 21–30 of 249 papers

TitleStatusHype
Active Label Refinement for Robust Training of Imbalanced Medical Image Classification Tasks in the Presence of High Label NoiseCode0
Foster Adaptivity and Balance in Learning with Noisy LabelsCode0
AlleNoise: large-scale text classification benchmark dataset with real-world label noiseCode1
Benchmarking Label Noise in Instance Segmentation: Spatial Noise MattersCode0
Relation Modeling and Distillation for Learning with Noisy Labels—0
Jump-teaching: Ultra Efficient and Robust Learning with Noisy Label—0
High-dimensional Learning with Noisy Labels—0
Can We Treat Noisy Labels as Accurate?Code0
Exploring the Robustness of In-Context Learning with Noisy LabelsCode0
Cross-to-merge training with class balance strategy for learning with noisy labelsCode0
Show:102550
← PrevPage 3 of 25Next →

No leaderboard results yet.