Papers of the day   All papers

CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features

Comments

Mawson: Throwback to last week's AI paper reading group - thanks to @sean3mcmahon. Our next one will be on Thurs 2nd April, led by @lexandstuff covering CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features. https://arxiv.org/abs/1905.04899 https://t.co/1fOIVc2QBc

0 replies, 11 likes


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


へいほぅ: CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features https://arxiv.org/abs/1905.04899 #linedevday

1 replies, 2 likes


arXiv CS-CV: CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features http://arxiv.org/abs/1905.04899

0 replies, 1 likes


arXiv CS-CV: CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features http://arxiv.org/abs/1905.04899

0 replies, 1 likes


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

Found on Mar 05 2020 at https://arxiv.org/pdf/1905.04899.pdf

PDF content of a computer science paper: CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features