MV-MR

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision4 results

Image ClassificationonCIFAR-20
Accuracy· 2023-03-21
73.2
SOTA
MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation arXiv:2303.12130
Self-Supervised LearningonSTL-10
Accuracy· 2023-03-21
89.67
best: 91.7 (ResNet50)
SOTA
MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation arXiv:2303.12130
Image ClassificationonImageNet
Top 5 Accuracy· 2023-03-21
92.1
best: 99.02 (Florence-CoSwin-H)
MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation arXiv:2303.12130
Image ClassificationonSTL-10
Accuracy· 2023-03-21
89.67
best: 99.7 (TURTLE (CLIP + DINOv2))
MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation arXiv:2303.12130