Papers with Code · CC BY-SA 4.0

CIFAR-10N-Worst

아카이브 평가 25건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
ProMix	Accuracy (mean) 96.16	ProMix: Combating Label Noise via Maximizing Clean Sample Utility 2022-07-21	코드 1
PSSCL	Accuracy (mean) 95.12	PSSCL: A progressive sample selection framework with contrastive loss designed for noisy labels 2024-12-18	코드 1
PGDF	Accuracy (mean) 93.65	Sample Prior Guided Robust Model Learning to Suppress Noisy Labels 2021-12-02	코드 1
ILL	Accuracy (mean) 93.58	Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations 2023-05-22	코드 1
SOP+	Accuracy (mean) 93.24	Robust Training under Label Noise by Over-parameterization 2022-02-28	코드 1
Divide-Mix	Accuracy (mean) 92.56	DivideMix: Learning with Noisy Labels as Semi-supervised Learning 2020-02-18	코드 1 · 코드 2
CORES*	Accuracy (mean) 91.66	Learning with Instance-Dependent Label Noise: A Sample Sieve Approach 2020-10-05	코드 1
ELR+	Accuracy (mean) 91.09	Early-Learning Regularization Prevents Memorization of Noisy Labels 2020-06-30	코드 1 · 코드 2
GNL	Accuracy (mean) 86.99	Partial Label Supervision for Agnostic Generative Noisy Label Learning 2023-08-02	코드 1
CAL	Accuracy (mean) 85.36	Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels 2021-02-10	코드 1 · 코드 2
Co-Teaching	Accuracy (mean) 83.83	Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels 2018-04-18	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
CORES	Accuracy (mean) 83.60	Learning with Instance-Dependent Label Noise: A Sample Sieve Approach 2020-10-05	코드 1
ELR	Accuracy (mean) 83.58	Early-Learning Regularization Prevents Memorization of Noisy Labels 2020-06-30	코드 1 · 코드 2
JoCoR	Accuracy (mean) 83.37	Combating noisy labels by agreement: A joint training method with co-regularization 2020-03-05	코드 1 · 코드 2
Co-Teaching+	Accuracy (mean) 83.26	How does Disagreement Help Generalization against Label Corruption? 2019-01-14	코드 1 · 코드 2 · 코드 3
Negative-LS	Accuracy (mean) 82.99	Understanding Generalized Label Smoothing when Learning with Noisy Labels 2021-09-29	코드 1
Positive-LS	Accuracy (mean) 82.76	Does label smoothing mitigate label noise? 2020-03-05	연결 없음
F-div	Accuracy (mean) 82.53	When Optimizing $f$-divergence is Robust with Label Noise 2020-11-07	코드 1 · 코드 2
Peer Loss	Accuracy (mean) 82.53	Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates 2019-10-08	코드 1 · 코드 2
GCE	Accuracy (mean) 80.66	Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels 2018-05-20	코드 1 · 코드 2 · 코드 3 · 코드 4
VolMinNet	Accuracy (mean) 80.53	Provably End-to-end Label-Noise Learning without Anchor Points 2021-02-04	코드 1
T-Revision	Accuracy (mean) 80.48	Are Anchor Points Really Indispensable in Label-Noise Learning? 2019-06-01	코드 1
Forward-T	Accuracy (mean) 79.79	Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach 2016-09-13	코드 1 · 코드 2
CE	Accuracy (mean) 77.69	연결 없음 논문 날짜 미기재	연결 없음
Backward-T	Accuracy (mean) 77.61	Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach 2016-09-13	코드 1 · 코드 2