133 citations · 143 across the 4 of their papers we have counts for
4 papers
Learning Fractals by Gradient Descent
Cheng-Hao Tu, Hong-You Chen, David Carlyn +1
Fractals are geometric shapes that can display complex and self-similar patterns found in nature (e.g., clouds and plants). Recent works in visual recognition have leveraged this p…
Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning
Cheng-Hao Tu, Zheda Mai, Wei-Lun Chao
Intermediate features of a pre-trained model have been shown informative for making accurate predictions on downstream tasks, even if the model backbone is kept frozen. The key cha…
On the Importance and Applicability of Pre-Training for Federated Learning
Hong-You Chen, Cheng-Hao Tu, Ziwei Li +2
Pre-training is prevalent in nowadays deep learning to improve the learned model's performance. However, in the literature on federated learning (FL), neural networks are mostly in…
Compacting, Picking and Growing for Unforgetting Continual Learning
Steven C. Y. Hung, Cheng-Hao Tu, Cheng-En Wu +3
Continual lifelong learning is essential to many applications. In this paper, we propose a simple but effective approach to continual deep learning. Our approach leverages the prin…