GAMR introduces geometric-aware manifold regularization via virtual outlier synthesis to enhance intra-class compactness and inter-class separation, improving robustness to noisy labels beyond passive sample filtering.
Towards understanding deep learning from noisy labels with small-loss criterion
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 4roles
method 1polarities
use method 1representative citing papers
Online Label Refinement lets LLMs learn robust reasoning from noisy supervision by correcting labels when majority answers show rising rollout success and stable history, delivering 3-4% gains on math and reasoning benchmarks even at high noise levels.
HRP decouples annotation reliability (alpha) and pseudo-label reliability (beta) via bilevel meta-learning and routes them to distinct objectives in reliability-aware Mixup and contrastive learning for improved noisy-label robustness.
SeeTN builds a semantic embedding space with prototype transformation and affinity regularization to identify and correct noisy labels, yielding better cross-domain gaze estimation without hurting source accuracy.
citing papers explorer
-
GAMR: Geometric-Aware Manifold Regularization with Virtual Outlier Synthesis for Learning with Noisy Labels
GAMR introduces geometric-aware manifold regularization via virtual outlier synthesis to enhance intra-class compactness and inter-class separation, improving robustness to noisy labels beyond passive sample filtering.
-
Can LLMs Learn to Reason Robustly under Noisy Supervision?
Online Label Refinement lets LLMs learn robust reasoning from noisy supervision by correcting labels when majority answers show rising rollout success and stable history, delivering 3-4% gains on math and reasoning benchmarks even at high noise levels.
-
Holistic Reliability Propagation: Decoupling Annotation and Prediction for Robust Noisy-Label
HRP decouples annotation reliability (alpha) and pseudo-label reliability (beta) via bilevel meta-learning and routes them to distinct objectives in reliability-aware Mixup and contrastive learning for improved noisy-label robustness.
-
See Through the Noise: Improving Domain Generalization in Gaze Estimation
SeeTN builds a semantic embedding space with prototype transformation and affinity regularization to identify and correct noisy labels, yielding better cross-domain gaze estimation without hurting source accuracy.