RS-FSL

Reported on 6 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 Vision6 results

Image ClassificationonOxford 102 Flower
ACCURACY· uses extra data· 2021-04-26
75.33
SOTA
Rich Semantics Improve Few-shot Learning arXiv:2104.12709
Few-Shot Image ClassificationonOxford 102 Flower
ACCURACY· uses extra data· 2021-04-26
75.33
SOTA
Rich Semantics Improve Few-shot Learning arXiv:2104.12709
Image ClassificationonCUB 200 5-way 1-shot
Accuracy· uses extra data· 2021-04-26
65.66
best: 95.8 (PT+MAP+SF+SOT (transductive))
Rich Semantics Improve Few-shot Learning arXiv:2104.12709
Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· uses extra data· 2021-04-26
65.33
best: 97.95 (SgVA-CLIP)
Rich Semantics Improve Few-shot Learning arXiv:2104.12709
Few-Shot Image ClassificationonCUB 200 5-way 1-shot
Accuracy· uses extra data· 2021-04-26
65.66
best: 95.8 (PT+MAP+SF+SOT (transductive))
Rich Semantics Improve Few-shot Learning arXiv:2104.12709
Few-Shot Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· uses extra data· 2021-04-26
65.33
best: 97.95 (SgVA-CLIP)
Rich Semantics Improve Few-shot Learning arXiv:2104.12709