XMixup: Efficient Transfer Learning with Auxiliary Samples by Cross-domain Mixup
This work addresses the challenge of high computational cost in transfer learning for practitioners, though it is incremental as it builds on existing multitask and mixup methods.
The paper tackles the problem of inefficient multitask learning in deep transfer learning by proposing XMixup, which selects auxiliary samples from the source dataset and uses mixup augmentation for each target class, resulting in an average accuracy improvement of 1.9% across six datasets while reducing training time.
Transferring knowledge from large source datasets is an effective way to fine-tune the deep neural networks of the target task with a small sample size. A great number of algorithms have been proposed to facilitate deep transfer learning, and these techniques could be generally categorized into two groups - Regularized Learning of the target task using models that have been pre-trained from source datasets, and Multitask Learning with both source and target datasets to train a shared backbone neural network. In this work, we aim to improve the multitask paradigm for deep transfer learning via Cross-domain Mixup (XMixup). While the existing multitask learning algorithms need to run backpropagation over both the source and target datasets and usually consume a higher gradient complexity, XMixup transfers the knowledge from 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 evaluate XMixup over six real world transfer learning datasets. Experiment results show that XMixup improves the accuracy by 1.9% on average. Compared with other state-of-the-art transfer learning approaches, XMixup costs much less training time while still obtains higher accuracy.