LSHFM (T: ResNet101 S: MobileNetV2)

Reported on 2 benchmarks across 1 task · 1 paper

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

Natural Language Processing2 results

Knowledge DistillationonCOCO (Common Objects in Context)
mAP· 2020-11-03
73.73
best: 77.16 (LSHFM (T: ResNet101 S: ResNet50))
Distilling Knowledge by Mimicking Features arXiv:2011.01424
Knowledge DistillationonPASCAL VOC
mAP· 2020-11-03
90.14
best: 93.17 (LSHFM (T: ResNet101 S: ResNet50))
Distilling Knowledge by Mimicking Features arXiv:2011.01424