TDM

Reported on 4 benchmarks across 2 tasks · 1 paper

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

Computer Vision4 results

Image ClassificationonCUB 200 5-way 5-shot
Accuracy· uses extra data· 2022-07-04
93.37
best: 98.7 (CAML [Laion-2b])
Task Discrepancy Maximization for Fine-grained Few-Shot Classification arXiv:2207.01376
Image ClassificationonCUB 200 5-way 1-shot
Accuracy· 2022-07-04
84.36
best: 95.8 (PT+MAP+SF+SOT (transductive))
Task Discrepancy Maximization for Fine-grained Few-Shot Classification arXiv:2207.01376
Few-Shot Image ClassificationonCUB 200 5-way 5-shot
Accuracy· uses extra data· 2022-07-04
93.37
best: 98.7 (CAML [Laion-2b])
Task Discrepancy Maximization for Fine-grained Few-Shot Classification arXiv:2207.01376
Few-Shot Image ClassificationonCUB 200 5-way 1-shot
Accuracy· 2022-07-04
84.36
best: 95.8 (PT+MAP+SF+SOT (transductive))
Task Discrepancy Maximization for Fine-grained Few-Shot Classification arXiv:2207.01376