← Image Classification
Papers with Code · CC BY-SA 4.0

CIFAR-10 (with noisy labels)

아카이브 평가 4건 · 마지막 적재/변경

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
모델원본 지표·값논문구현
SSR
Accuracy (under 20% Sym. label noise)
96.74%
Accuracy (under 50% Sym. label noise)
96.13%
Accuracy (under 80% Sym. label noise)
95.56%
Accuracy (under 90% Sym. label noise)
95.17%
SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise
2021-11-22
코드 1
C2D (ELR+ with SimCLR, ResNet-34)
Accuracy (under 20% Sym. label noise)
96.74 ± 0.12
Accuracy (under 50% Sym. label noise)
95.55 ± 0.32
Accuracy (under 80% Sym. label noise)
93.11 ± 0.70
Accuracy (under 90% Sym. label noise)
89.30 ± 0.21
Accuracy (under 95% Sym. label noise)
80.21 ± 1.91
Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels
2021-03-25
코드 1
PGDF (ResNet-18)
Accuracy (under 20% Sym. label noise)
96.7%
Accuracy (under 50% Sym. label noise)
96.3%
Accuracy (under 80% Sym. label noise)
94.7%
Accuracy (under 90% Sym. label noise)
84.0%
Sample Prior Guided Robust Model Learning to Suppress Noisy Labels
2021-12-02
코드 1
C2D (DivideMix with SimCLR, ResNet-18)
Accuracy (under 20% Sym. label noise)
96.23 ± 0.09
Accuracy (under 50% Sym. label noise)
95.15 ± 0.16
Accuracy (under 80% Sym. label noise)
94.30 ± 0.12
Accuracy (under 90% Sym. label noise)
93.42 ± 0.09
Accuracy (under 95% Sym. label noise)
87.72 ± 2.21
Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels
2021-03-25
코드 1