English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Nowadays, forgery faces pose pressing security concerns over fake news,fraud, impersonation, etc. Despite the demonstrated success in intra-domainface forgery detection, existing detection methods lack generalizationcapability and tend to suffer from dramatic performance drops when deployed tounforeseen domains. To mitigate this issue, this paper designs a more generalfake face detection model based on the vision transformer(ViT) architecture. Inthe training phase, the pretrained ViT weights are freezed, and only theLow-Rank Adaptation(LoRA) modules are updated. Additionally, the Single CenterLoss(SCL) is applied to supervise the training process, further improving thegeneralization capability of the model. The proposed method achievesstate-of-the-arts detection performances in both cross-manipulation andcross-dataset evaluations.

Enhancing General Face Forgery Detection via Vision Transformer with Low-Rank Adaptation