https://github.com/xiaoboxia/rtm_lnl
공식 코드Regularly Truncated M-estimators for Learning with Noisy Labels
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/xingjunm/dimensionality-driven-learning
공식 코드https://github.com/xuefeng-li1/Provably-end-to-end-label-noise-learning-without-anchor-points
공식 코드Provably End-to-end Label-Noise Learning without Anchor Points
https://github.com/xyupeng/lc-booster
공식 코드Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels
https://github.com/yikai-wang/knockoffs-spr
공식 코드Knockoffs-SPR: Clean Sample Selection in Learning with Noisy Labels
https://github.com/yikai-wang/spr-lnl
공식 코드Scalable Penalized Regression for Noise Detection in Learning with Noisy Labels
https://github.com/yikun2019/PENCIL
공식 코드Probabilistic End-to-end Noise Correction for Learning with Noisy Labels
https://github.com/yingyichen-cyy/JigsawViT
공식 코드https://github.com/yingyichen-cyy/Nested-Co-teaching
공식 코드https://github.com/youjiangxu/FaMUS
공식 코드https://github.com/yuanpengtu/SANM
공식 코드Learning with Noisy labels via Self-supervised Adversarial Noisy Masking
https://github.com/yuvalgrin/DetectAndCorrect-Net
공식 코드Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels
https://github.com/yuyinzhou/l2b
공식 코드L2B: Learning to Bootstrap Robust Models for Combating Label Noise
https://github.com/z3n0e/MFRW
공식 코드https://github.com/zdy93/colafier
공식 코드CoLafier: Collaborative Noisy Label Purifier With Local Intrinsic Dimensionality Guidance
https://github.com/zyh-uaiaaaa/MDA-noisy-label-learning
공식 코드https://github.com/zyh-uaiaaaa/erasing-attention-consistency
공식 코드Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition
https://github.com/zzp1012/label-noise-theory
공식 코드https://github.com/AlanChou/Truncated-Loss
Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels
https://github.com/Ashay-20/TF-SAM-Sharpness-Aware-Minimization-Implementation
Sharpness-Aware Minimization for Efficiently Improving Generalization
https://github.com/DaikiTanaka-UT/JointOptimization
https://github.com/EthanCoder24/Protofomer-NLP
https://github.com/GitF82/NLP-Embeddings-Protoformer-Paper
https://github.com/HanxunHuangLemonBear/SCELoss-Reproduce
Symmetric Cross Entropy for Robust Learning with Noisy Labels
https://github.com/JacobPfau/PENCIL
Probabilistic End-to-end Noise Correction for Learning with Noisy Labels
https://github.com/Jannoshh/simple-sam
Sharpness-Aware Minimization for Efficiently Improving Generalization
https://github.com/Janus-Shiau/SAM-tf2
Sharpness-Aware Minimization for Efficiently Improving Generalization
https://github.com/LanXiaoPang613/C2MT
https://github.com/LanXiaoPang613/PSSCL
https://github.com/MindCode-4/code-12/tree/main/Learning-with-Noisy-Labels
Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
https://github.com/MindCode-4/code-13/tree/main/Scalable-Sharpness-Aware-Minimization
Sharpness-Aware Minimization for Efficiently Improving Generalization
https://github.com/MindSpore-scientific-2/code-3/tree/main/Three-Dimensional-Lip-Motion-Network-for-Text-Independent-Speaker-Recognition-master
https://github.com/NiMlr/pynlqn
Sharpness-Aware Minimization for Efficiently Improving Generalization
https://github.com/Sunarker/Safeguarded-Dynamic-Label-Regression-for-Noisy-Supervision
Safeguarded Dynamic Label Regression for Generalized Noisy Supervision
https://github.com/XinshaoAmosWang/DerivativeManipulation
Normalized Loss Functions for Deep Learning with Noisy Labels
https://github.com/XinshaoAmosWang/Emphasis-Regularisation-by-Gradient-Rescaling
Normalized Loss Functions for Deep Learning with Noisy Labels
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.