PSSCL

Reported on 16 benchmarks across 2 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision8 results

Image ClassificationonCIFAR-10N-Random2
Accuracy (mean)
96.21
Image ClassificationonCIFAR-10N-Random3
Accuracy (mean)
96.49
Image ClassificationonANIMAL
Accuracy
88.74
best: 89 (Jigsaw-ViT)
Image ClassificationonCIFAR-10N-Aggregate
Accuracy (mean)
96.41
best: 97.39 (ProMix)
Image ClassificationonCIFAR-10N-Random1
Accuracy (mean)
96.17
best: 96.97 (ProMix)
Image ClassificationonCIFAR-100N
Accuracy (mean)
72
best: 74.08 (PGDF)
Image ClassificationonFood-101
Accuracy (% )
86.41
best: 86.42 (LongReMix)
Image ClassificationonCIFAR-10N-Worst
Accuracy (mean)
95.12
best: 96.16 (ProMix)