8000 GitHub - XinyiYing/SMSR: Learning Sparse Masks for Efficient Image Super-Resolution
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
/ SMSR Public
forked from SYSU-SAIL/SMSR

Learning Sparse Masks for Efficient Image Super-Resolution

Notifications You must be signed in to change notification settings

XinyiYing/SMSR

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

25 Commits
 
 
 
 

Repository files navigation

SMSR

Reposity for "Learning Sparse Masks for Efficient Image Super-Resolution"

[arXiv]

  • Locate and skip redundant computation in SR networks at a fine-grained level for efficient inference.
  • Maintain state-of-the-art performance with significant FLOPs reduction and a speedup on mobile devices.
  • Efficient implementation of sparse convolution based on original Pytorch APIs for easier migration and deployment.

Code will be released soon. Stay tuned.

Network Architecture

Implementation of Sparse Convolution

For easier migration and deployment, we use an efficient implementation of sparse convolution based on original Pytorch APIs rather than the commonly applied CUDA-based implementation. Specifically, sparse features are first extracted from the input, as shown in the following figure. Then, matrix multiplication is executed to produce the output features.

Results

Visualization of Sparse Masks

Citation

@Article{Wang2020Learning,
  author  = {Wang, Longguang and Dong, Xiaoyu and Wang, Yingqian and Ying, Xinyi and Lin, Zaiping and An, Wei and Guo, Yulan},
  title   = {Learning Sparse Masks for Efficient Image Super-Resolution},
  journal = {arXiv},
  year    = {2020},
}

About

Learning Sparse Masks for Efficient Image Super-Resolution

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
0