LF2CS

Reported on 8 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 ClassificationonTiered ImageNet 5-way (5-shot)
Accuracy
66.59
best: 98.8 (CAML [Laion-2b])
Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy
53.14
best: 97.95 (SgVA-CLIP)
Image ClassificationonTiered ImageNet 5-way (1-shot)
Accuracy
53.16
best: 96.8 (CAML [Laion-2b])
Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy
67.36
best: 98.72 (SgVA-CLIP)
Few-Shot Image ClassificationonTiered ImageNet 5-way (5-shot)
Accuracy
66.59
best: 98.8 (CAML [Laion-2b])
Few-Shot Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy
53.14
best: 97.95 (SgVA-CLIP)
Few-Shot Image ClassificationonTiered ImageNet 5-way (1-shot)
Accuracy
53.16
best: 96.8 (CAML [Laion-2b])
Few-Shot Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy
67.36
best: 98.72 (SgVA-CLIP)