Multi-Scale Wavelet Transformer for Face Forgery Detection

Jie Liu, Jingjing Wang, Peng Zhang, Chunmao Wang, Di Xie, Shiliang Pu; Proceedings of the Asian Conference on Computer Vision (ACCV), 2022, pp. 1858-1874


Currently, many face forgery detection methods aggregate spatial and frequency features to enhance the generalization ability and gain promising performance under the cross-dataset scenario. However, these methods only leverage one level frequency information which limits their expressive ability. To overcome these limitations, we propose a multi-scale wavelet transformer framework for face forgery detection. Specifically, to take full advantage of the multi-scale and multi-frequency wavelet representation, we gradually aggregate the multi-scale wavelet representation at different stages of the backbone network. To better fuse the frequency feature with the spatial features, frequency-based spatial attention is designed to guide the spatial feature extractor to concentrate more on forgery traces. Meanwhile, cross-modality attention is proposed to fuse the frequency features with the spatial features. These two attention modules are calculated through a unified transformer block for efficiency. A wide variety of experiments demonstrate that the proposed method is efficient and effective for both within and cross datasets.

Related Material

[pdf] [arXiv]
@InProceedings{Liu_2022_ACCV, author = {Liu, Jie and Wang, Jingjing and Zhang, Peng and Wang, Chunmao and Xie, Di and Pu, Shiliang}, title = {Multi-Scale Wavelet Transformer for Face Forgery Detection}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2022}, pages = {1858-1874} }