Venus-DefakerOne2 released
The story so far
qwen has released the Venus-DefakerOne2 model, a broader visual forensics foundational model that extends detection to various forms and media types through alternating LoRA and full-parameter fine-tuning, as well as entropy-based test adaptive. It achieves SOTA performance in six benchmark tests, including DeepFake faces (96.7%), AI-generated images (93.3%), and tampered documents (87.6%), significantly outperforming expert models and predecessor DefakerOne.
AI-written from the reports · Updated 16 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- Hugging Face Daily PapersVenus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage
Venus-DefakerOne2 extends detection to multiple spoofing forms and media types through alternating LoRA and full-parameter fine-tuning, as well as entropy-based test adaptive, achieving SOTA performance in six benchmark tests including DeepFake faces (96.7%), AI-generated images (93.3%), and tampered documents (87.6%), significantly outperforming expert models and predecessor DefakerOne.