Adaptive Gated Deepfake Detection for Low-Resolution and Resource-Constrained Environments
AdaGate-DF routes deepfake detection by image quality through dual multi-exit gates, hitting 0.9370 AUC on Celeb-DF with low inference latency.
AdaGate-DF is an adaptive gated deepfake detection framework that uses image-quality cues to send high-quality images through earlier exits, saving compute in resource-constrained settings. On Celeb-DF it achieves an AUC of 0.9370, outperforming MaD-CoRN and DefakeHop++, and reaches 0.9708 at 384x384 resolution. On FaceForensics++ it remains effective under class imbalance while balancing uncertainty-aware prediction and computational efficiency.
- Quality-aware gating enables early exits for high-quality images
- AUC 0.9370 on Celeb-DF, 0.9708 at 384x384 resolution
- Compared against MaD-CoRN, DefakeHop++, and ShuffleNetV2
- Targets low-resolution and resource-constrained deployments
- Tags
- adaptive-inferenceceleb-dfdeepfake-detectionfaceforensicsmulti-exit-networksmultimedia-forensics
- Products
- AdaGate-DF
From the original article
1 min read at arxiv.orgDeepfake detection models often rely on high-quality inputs, fixed inference paths, and computationally expensive architectures, limiting their use in low-resolution and resource-constrained settings. This paper proposes AdaGate-DF, an adaptive gated deepfake detection framework that uses image-quality cues to route samples through a dual multi-exit system so high-quality images can exit earlier and save compute.
By Vaishnavi Sen · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.