CB Loss(ResNet-50)

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 ClassificationonCOCO-MLT
Average mAP· 2019-01-16
49.06
best: 66.19 (LMPT(ViT-B/16))
Class-Balanced Loss Based on Effective Number of Samples arXiv:1901.05555
Long-tail LearningonCOCO-MLT
Average mAP· 2019-01-16
49.06
best: 66.19 (LMPT(ViT-B/16))
Class-Balanced Loss Based on Effective Number of Samples arXiv:1901.05555
Generalized Few-Shot LearningonCOCO-MLT
Average mAP· 2019-01-16
49.06
best: 66.19 (LMPT(ViT-B/16))
Class-Balanced Loss Based on Effective Number of Samples arXiv:1901.05555

Computer Vision2 results

Image ClassificationonCOCO-MLT
Average mAP· 2019-01-16
49.06
best: 66.19 (LMPT(ViT-B/16))
Class-Balanced Loss Based on Effective Number of Samples arXiv:1901.05555
Few-Shot Image ClassificationonCOCO-MLT
Average mAP· 2019-01-16
49.06
best: 66.19 (LMPT(ViT-B/16))
Class-Balanced Loss Based on Effective Number of Samples arXiv:1901.05555