Class-Balanced Focal Loss

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 ClassificationonNIH-CXR-LT
Balanced Accuracy· 2022-08-29
0.232
best: 0.294 (Decoupling (cRT))
Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study arXiv:2208.13365
Long-tail LearningonNIH-CXR-LT
Balanced Accuracy· 2022-08-29
0.232
best: 0.294 (Decoupling (cRT))
Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study arXiv:2208.13365
Generalized Few-Shot LearningonNIH-CXR-LT
Balanced Accuracy· 2022-08-29
0.232
best: 0.294 (Decoupling (cRT))
Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study arXiv:2208.13365

Computer Vision2 results

Image ClassificationonNIH-CXR-LT
Balanced Accuracy· 2022-08-29
0.232
best: 0.294 (Decoupling (cRT))
Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study arXiv:2208.13365
Few-Shot Image ClassificationonNIH-CXR-LT
Balanced Accuracy· 2022-08-29
0.232
best: 0.294 (Decoupling (cRT))
Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study arXiv:2208.13365