1 Hit in 3.1 sec

XMixup: Efficient Transfer Learning with Auxiliary Samples by Cross-domain Mixup [article]

Xingjian Li, Haoyi Xiong, Haozhe An, Chengzhong Xu, Dejing Dou
2020 arXiv   pre-print
In this work, we aim to improve the multitask paradigm for deep transfer learning via Cross-domain Mixup (XMixup).  ...  source to target tasks more efficiently: for every class of the target task, XMixup selects the auxiliary samples from the source dataset and augments training samples via the simple mixup strategy.  ...  We propose a novel deep transfer learning algorithm XMixup, namely Cross-domain Mixup, with superiority in both effectiveness and efficiency.  ... 
arXiv:2007.10252v1 fatcat:otkvny26e5c4riw4wv7iddmwya