CLIP baseline 與 Forensics Adapter 在 FF++ / HiDF / Celeb-DF v2 的跨資料集比較,並驗證跨 domain 部署時的分類門檻失效問題
-
Updated
Sep 1, 2026 - Jupyter Notebook
CLIP baseline 與 Forensics Adapter 在 FF++ / HiDF / Celeb-DF v2 的跨資料集比較,並驗證跨 domain 部署時的分類門檻失效問題
Frequency-aware deepfake detection under lossy H.264 compression using XceptionNet, DCT features, learnable frequency masking, and cross-attention fusion.
Deep learning project for improving cross-dataset generalization in underwater beluga whale image classification using supervised contrastive learning.
Official implementation of the CMF-Lite lightweight cross-cue fusion detector for deepfake video detection accepted at MIWAI2026
How Hard is Microservice Anomaly Detection?
Reprodutibilidade: deteccao de fake news em portugues brasileiro (generalizacao, atalhos de aprendizado e robustez). Qualificacao de mestrado e artigo aceito para publicacao no ENIAC 2026.
To associate your repository with the cross-dataset-generalization topic, visit your repo's landing page and select "manage topics."