Papers with Code 아카이브
Learning with noisy labels
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 20
- 보존된 평가 기록
- 194
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
CoLafier: Collaborative Noisy Label Purifier With Local Intrinsic Dimensionality Guidance
Learning with Noisy Labels: Interconnection of Two Expectation-Maximizations
Robust Loss Functions for Training Decision Trees with Noisy Labels
FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels
CSOT: Curriculum and Structure-Aware Optimal Transport for Learning with Noisy Labels
Exploring Parity Challenges in Reinforcement Learning through Curriculum Learning with Noisy Labels
A Unified Framework for Connecting Noise Modeling to Boost Noise Detection
Learning to Complement with Multiple Humans
Learning with Noisy Labels Using Collaborative Sample Selection and Contrastive Semi-Supervised Learning
Fine tuning Pre trained Models for Robustness Under Noisy Labels
Learning with Noisy Labels for Human Fall Events Classification: Joint Cooperative Training with Trinity Networks
ALEX: Towards Effective Graph Transfer Learning with Noisy Labels
Regularly Truncated M-estimators for Learning with Noisy Labels
Late Stopping: Avoiding Confidently Learning from Mislabeled Examples
Channel-Wise Contrastive Learning for Learning with Noisy Labels
Improving Medical Image Classification in Noisy Labels Using Only Self-supervised Pretraining
Partial Label Supervision for Agnostic Generative Noisy Label Learning
LaplaceConfidence: a Graph-based Approach for Learning with Noisy Labels
Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type Perspective
Unleashing the Potential of Regularization Strategies in Learning with Noisy Labels
Co-Learning Meets Stitch-Up for Noisy Multi-label Visual Recognition
MILD: Modeling the Instance Learning Dynamics for Learning with Noisy Labels
FedNoisy: Federated Noisy Label Learning Benchmark
LNL+K: Enhancing Learning with Noisy Labels Through Noise Source Knowledge Integration
A Gradient-based Approach for Online Robust Deep Neural Network Training with Noisy Labels
MIMO Detection under Hardware Impairments: Learning with Noisy Labels
Learning with Noisy Labels by Adaptive Gradient-Based Outlier Removal
Linear Distance Metric Learning with Noisy Labels
Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
Enhanced Meta Label Correction for Coping with Label Corruption
NoisywikiHow: A Benchmark for Learning with Real-world Noisy Labels in Natural Language Processing
Bayesian Optimization Meets Self-Distillation
Improving Image Recognition by Retrieving from Web-Scale Image-Text Data
Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Movies
Learning with Noisy Labels through Learnable Weighting and Centroid Similarity
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.