← Search

Muhammad Ali

2 accepted papers

2021

Distilling Global and Local Logits With Densely Connected Relations

ICCV 2021poster

In prevalent knowledge distillation, logits in most image recognition models are computed by global average pooling, then used to learn to encode the high-level and task-relevant knowledge. In this work, we solve the limitation of this global logit transfer in this distillation context. We point out…

Cited by 40PDFcodeScholar