Image Classification on CIFAR-100 (test) (20%, 50%, 80%, 90% Noise Accuracy) benchmark leaderboard · SOTA2 Research

Image Classification on CIFAR-100 (test) (20%, 50%, 80%, 90% Noise Accuracy)

80.1Acc (20% Noise)L2B-C2D

Evaluation Results

Method	Links
L2B-C2D2022.02		80.1	78.1	69.6	60.7
AugDesc2022.02		79.5	77.2	66.4	41.2
UniCon2022.02		78.9	77.6	63.9	44.8
L2B-UniCon2022.02		78.8	77.3	67.6	49.6
C2D2022.02		78.7	76.4	67.8	58.7
TCL2022.02		78	73.3	65	54.5
L2B-DivideMix2022.02		77.9	75.9	62.2	35.8
DivideMix2022.02		77.3	74.6	60.2	31.5
Sel-CL+2022.02		76.5	72.4	59.6	48.8
MOIT+2022.02		75.9	70.6	47.6	41.8
M-correction2022.02		73.9	66.1	48.2	24.3
MSLC2022.02		72.5	65.4	24.3	16.7
PENCIL2022.02		69.4	57.5	31.1	15.3
Meta-Learning2022.02		68.5	59.2	42.4	19.5
GCE2022.02		68.1	53.3	22.1	8.9
Mixup2022.02		67.8	57.3	30.8	14.6
MLC2022.02		66.8	52.7	21.8	15
Co-teaching+2022.02		65.6	51.8	27.9	13.7