ScatSimCLR

Reported on 2 benchmarks across 1 task · 1 paper · 1 SOTA

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

Computer Vision2 results

Image ClassificationonCIFAR-20
Accuracy· 2021-08-31
63.76
best: 73.2 (MV-MR)
SOTA
ScatSimCLR: self-supervised contrastive learning with pretext task regularization for small-scale datasets arXiv:2108.13939
Image ClassificationonSTL-10
Accuracy· 2021-08-31
85.11
best: 99.7 (TURTLE (CLIP + DINOv2))
ScatSimCLR: self-supervised contrastive learning with pretext task regularization for small-scale datasets arXiv:2108.13939