Papers with Code 아카이브

Learning with noisy labels

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/maclll/selc

공식 코드

SELC: Self-Ensemble Label Correction Improves Learning with Noisy Labels

https://github.com/microsoft/mlc

공식 코드

Meta Label Correction for Noisy Label Learning

https://github.com/mrchenfeng/clipcleaner_acmmm2024

공식 코드

CLIPCleaner: Cleaning Noisy Labels with CLIP

https://github.com/nazmul-karim170/unicon-noisy-label

공식 코드

UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning

https://github.com/pxiangwu/PLC

공식 코드

Learning with Feature-Dependent Label Noise: A Progressive Approach

https://github.com/qunovo/NLPrompt

공식 코드

NLPrompt: Noise-Label Prompt Learning for Vision-Language Models

https://github.com/rstless-research/ncod-learning-with-noisy-labels

공식 코드

Learning with Noisy Labels through Learnable Weighting and Centroid Similarity

https://github.com/sagebei/Exploring-Parity-Challenges-in-Reinforcement-Learning

공식 코드

Exploring Parity Challenges in Reinforcement Learning through Curriculum Learning with Noisy Labels

https://github.com/shengliu66/ELR

공식 코드

Early-Learning Regularization Prevents Memorization of Noisy Labels

https://github.com/shengliu66/sop

공식 코드

Robust Training under Label Noise by Over-parameterization

https://github.com/shikunli/sel-cl

공식 코드

Selective-Supervised Contrastive Learning with Noisy Labels

https://github.com/smilelab-fl/fednoisy

공식 코드

FedNoisy: Federated Noisy Label Learning Benchmark

https://github.com/songheony/TAkS

공식 코드

No Regret Sample Selection with Noisy Labels

https://github.com/sooperset/boss

공식 코드

Bayesian Optimization Meets Self-Distillation

https://github.com/sunarker/lccn

공식 코드

Latent Class-Conditional Noise Model

https://github.com/sunnysiqi/combo

공식 코드

A Unified Framework for Connecting Noise Modeling to Boost Noise Detection

https://github.com/sunnysiqi/lnl_k

공식 코드

LNL+K: Enhancing Learning with Noisy Labels Through Noise Source Knowledge Integration

https://github.com/tangminji/noisywikihow

공식 코드

NoisywikiHow: A Benchmark for Learning with Real-world Noisy Labels in Natural Language Processing

https://github.com/tencentyouturesearch/highlightdetection-clc

공식 코드

Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Movies

https://github.com/thumbe3/label-noise-nlp

공식 코드

Towards Robustness to Label Noise in Text Classification via Noise Modeling

https://github.com/timok93/blind_knowledge_distillation

공식 코드

Blind Knowledge Distillation for Robust Image Classification

https://github.com/tmllab/2023_ICCV_LateStopping

공식 코드

Late Stopping: Avoiding Confidently Learning from Mislabeled Examples

https://github.com/tmllab/2024_ICLR_LabelWave

공식 코드

Early Stopping Against Label Noise Without Validation Data

https://github.com/tmllab/2024_icml_tss

공식 코드

Mitigating Label Noise on Graph via Topological Sample Selection

https://github.com/tmllab/PES

공식 코드

Understanding and Improving Early Stopping for Learning with Noisy Labels

https://github.com/ucsc-real/canlessbemore

공식 코드

Can Less be More? When Increasing-to-Balancing Label Noise Rates Considered Beneficial

https://github.com/ucsc-real/cifar-10-100n

공식 코드

Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations

https://github.com/ucsc-real/negative-label-smoothing

공식 코드

To Smooth or Not? When Label Smoothing Meets Noisy Labels

https://github.com/ucsc-real/selfsup_noisylabel

공식 코드

Mitigating Memorization of Noisy Labels via Regularization between Representations

https://github.com/uds-lsv/bert-lnl

공식 코드

Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text Classification

https://github.com/vamosc/colearning-meet-stitchup

공식 코드

Co-Learning Meets Stitch-Up for Noisy Multi-label Visual Recognition

https://github.com/virusdoll/active-negative-loss

공식 코드

Active Negative Loss: A Robust Framework for Learning with Noisy Labels

https://github.com/wanifarooq/ncod

공식 코드

Learning with Noisy Labels through Learnable Weighting and Centroid Similarity

https://github.com/weijiaheng/Robust-f-divergence-measures

공식 코드

When Optimizing $f$-divergence is Robust with Label Noise

https://github.com/wu-yu-hao/2024_icml_tss

공식 코드

Mitigating Label Noise on Graph via Topological Sample Selection

https://github.com/xiaoboxia/T-Revision

공식 코드

Are Anchor Points Really Indispensable in Label-Noise Learning?

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.