Logit-Adj + IFL

Reported on 5 benchmarks across 5 tasks · 1 paper

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

Methodology3 results

Generalized Few-Shot ClassificationonImageNet-GLT
Accuracy· 2022-07-19
40.52
best: 45.64 (RIDE + IFL)
Invariant Feature Learning for Generalized Long-Tailed Classification arXiv:2207.09504
Long-tail LearningonImageNet-GLT
Accuracy· 2022-07-19
40.52
best: 45.64 (RIDE + IFL)
Invariant Feature Learning for Generalized Long-Tailed Classification arXiv:2207.09504
Generalized Few-Shot LearningonImageNet-GLT
Accuracy· 2022-07-19
40.52
best: 45.64 (RIDE + IFL)
Invariant Feature Learning for Generalized Long-Tailed Classification arXiv:2207.09504

Computer Vision2 results

Image ClassificationonImageNet-GLT
Accuracy· 2022-07-19
40.52
best: 45.64 (RIDE + IFL)
Invariant Feature Learning for Generalized Long-Tailed Classification arXiv:2207.09504
Few-Shot Image ClassificationonImageNet-GLT
Accuracy· 2022-07-19
40.52
best: 45.64 (RIDE + IFL)
Invariant Feature Learning for Generalized Long-Tailed Classification arXiv:2207.09504