Image Classification on CIFAR-10 (test) (Noise Robustness) benchmark leaderboard · SOTA2 Research

Image Classification on CIFAR-10 (test) (Noise Robustness)

96.7Accuracy (20% Noise)L2B-C2D

Evaluation Results

Method	Links
L2B-C2D2022.02		96.7	95.6	94.8	94.4
L2B-UniCon2022.02		96.5	95.8	94.7	92.8
AugDesc2022.02		96.3	95.4	93.8	91.9
C2D2022.02		96.3	95.2	94.4	93.5
DivideMix2022.02		96.1	94.6	93.2	76
L2B-DivideMix2022.02		96.1	95.4	94	91.3
UniCon2022.02		96	95.6	93.9	90.8
Mixup2022.02		95.6	87.1	71.6	52.2
Sel-CL+2022.02		95.5	93.9	89.2	81.9
TCL2022.02		95	93.9	92.5	89.4
MOIT+2022.02		94.1	91.8	81.1	74.7
M-correction2022.02		94	92	86.8	69.1
MSLC2022.02		93.4	89.9	69.8	56.1
Meta-Learning2022.02		92.9	89.3	77.4	58.7
MLC2022.02		92.6	88.1	77.4	67.9
PENCIL2022.02		92.4	89.1	77.5	58.9
GCE2022.02		90	89.3	73.9	36.5
Co-teaching+2022.02		89.5	85.7	67.4	47.9