Papers of the day   All papers

CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features

Comments

May 14 2019 SanghyukChun

Our new paper CutMix is now available in arXiv https://arxiv.org/abs/1905.04899 we achieved 21.60 top-1 error with CutMix augmented ResNet where ResNet-152 baseline is 21.69. Moreover, CutMix trained model enhances the performance of Detectors and Image Captioning! https://t.co/NiQEmgHqa5
0 replies, 3 likes


May 14 2019 arXiv CS-CV

CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features http://arxiv.org/abs/1905.04899
0 replies, 1 likes


Aug 08 2019 arXiv CS-CV

CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features http://arxiv.org/abs/1905.04899
0 replies, 1 likes


May 14 2019 Brundage Bot

CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features. Sangdoo Yun, Dongyoon Han, Seong Joon Oh, Sanghyuk Chun, Junsuk Choe, and Youngjoon Yoo http://arxiv.org/abs/1905.04899
1 replies, 0 likes


Content