Sorry, you need to enable JavaScript to visit this website.

LIGHTING IMAGE/VIDEO STYLE TRANSFER METHODS BY ITERATIVE CHANNEL PRUNING

DOI:
10.60864/mbyb-vs04
Citation Author(s):
Kexin Wu, Fan Tang, Ning Liu, Oliver Deussen, Thi-ngoc-hanh Le , Weiming Dong, Tong-yee Lee
Submitted by:
Fan Tang
Last updated:
6 June 2024 - 10:28am
Document Type:
Presentation Slides
Document Year:
2024
Event:
Paper Code:
lVMSP-L9.5
 

Deploying style transfer methods on resource-constrained devices is challenging, which limits their real-world applicability. To tackle this issue, we propose using pruning techniques to accelerate various visual style transfer methods. We argue that typical pruning methods may not be well-suited for style transfer methods and present an iterative correlation-based channel pruning (ICCP) strategy for encoder-transform-decoder-based image/video style transfer models. The correlation-based channel regularization preserves the feature distributions for content and style references, and the iterative pruning strategy prevents layer collapse when pruning on the encoder-decoder structure. Experiments demonstrate that the proposed ICCP can generate visually competitive results compared to SOTA style transfer methods and significantly reduce the number of parameters (at least 70K) and inference time. The model is available at https://github.com/wukx-wukx/ICCP.

up
0 users have voted: