European Conference on Computer Vision 2020
This implementation is mainly based on the desciption in the paper on top of XceptionNet. The inplementation has three models:
- FAD: Frequency-aware Decomposition
- LFS: Local Frequency Statistics
- MixBlock: Two-stream Collaborative Framework (@ block 7 and block 12)
Source code is mainly referenced from this repo.
Download pre-trained XceptionNet from here.
Star if you find it useful.