conftrace_

label noise

498 papers

Explore in graph

Co-occurring keywords

noisy label (321) noisy label learning (163) deep neural network (1803) semi-supervised learning (2341) weakly supervised learning (1328) text classification (6793) image classification (1944) data augmentation (3052) representation learning (6206) active learning (1301)

Papers

Improving Label Noise Robustness with Data Augmentation and Semi-Supervised Learning (Student Abstract) AAAI 2021
Interactive Label Cleaning with Example-based Explanations NIPS 2021
Label Noise SGD Provably Prefers Flat Global Minimizers NIPS 2021
RIM: Reliable Influence-based Active Learning on Graphs NIPS 2021
Optimizing Black-box Metrics with Iterative Example Weighting ICML 2021
Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins ICML 2021
Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data ACL 2021
Re-Labeling ImageNet: From Single to Multi-Labels, From Global to Localized Labels CVPR 2021
Do We Really Need Gold Samples for Sample Weighting Under Label Noise? WACV 2021
Efficient Learning with Arbitrary Covariate Shift ALT 2021
Provably End-to-end Label-noise Learning without Anchor Points ICML 2021
Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization ICML 2021
Instance-dependent Label-noise Learning under a Structural Causal Model NIPS 2021
How does a Neural Network's Architecture Impact its Robustness to Noisy Labels? NIPS 2021
Provable Robustness of Adversarial Training for Learning Halfspaces with Noise ICML 2021
Understanding Instance-Level Label Noise: Disparate Impacts and Treatments ICML 2021
Instance-adaptive training with noise-robust losses against noisy labels EMNLP 2021
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels ICML 2021
Learning from Noisy Labels with Complementary Loss Functions AAAI 2021
Learning from Noisy Labels with No Change to the Training Process ICML 2021
Adversarial Multi Class Learning under Weak Supervision with Performance Guarantees ICML 2021
Training Dynamic based data filtering may not work for NLP datasets EMNLP 2021
Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterion IJCAI 2021
Lower-Bounded Proper Losses for Weakly Supervised Classification ICML 2021
A Second-Order Approach to Learning With Instance-Dependent Label Noise CVPR 2021