CEKD:Cross ensemble knowledge distillation for augmented fine-grained data
Sign Up to like & getrecommendations! Published in 2022 at "Applied Intelligence"
DOI: 10.1007/s10489-022-03355-0
Abstract: Data augmentation has been proved effective in training deep models. Existing data augmentation methods tackle finegrained problem by blending image pairs and fusing corresponding labels according to the statistics of mixed pixels, which produces additional… read more here.
Keywords: knowledge distillation; distillation; ensemble knowledge; fine grained ... See more keywords