.png){kind=icon}
.png){kind=icon}
Return
MLC: Enhanced Deepfake Detection Through Multi-Level Collaborations
.png){kind=icon}
OA
AI
DOI：10.1049/ipr2.70284.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Deepfake detection, as a defence against AI-generated faces, has attracted significant attention. Existing image-level detectors aim to mine forged traces in latent codes after pre-trained backbones. However, merely considering such semantic-level clues is often insufficient when confronted with unseen manipulations and datasets, where more complicated forgeries are encountered. To this end, this paper proposes a Multi-Level Collaborations strategy, termed MLC, to enhance generalisation through simultaneously extracting pixel-level fine-grained, region-level facial layout, and semantic-level deep clues at different stages of encoding. Specifically, in the shallow stage, deformable convolutions with small receptive fields but adaptability, attached with spatial attentions, are used for spatial fine-grained falsifies. In the middle stage, multiple dilated convolutions with different dilations in a pyramidal manner, further dynamically capture local incoordination within deepfakes. Finally, latent codes cooperated with such fine-grained features, facilitate comprehensive discriminability via the long-sequence dependency modelling system xLSTM. Moreover, multi-task learning is employed for more stable multi-level training. Extensive experiments show that MLC achieves superior performance compared to existing methods in both cross-dataset and cross-manipulation tests. The codes are available at: https://github.com/yanwd628/MLC.
Keywords:
computer vision
image forensics
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
2.2
Papers:
118
Citations:
4.7K