ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images
Despite significant advancements of deep learning-based forgery detectors for distinguishing manipulated deepfake images, most detection approaches suffer from moderate to significant performance degradation with low-quality compressed deepfake images. Because of the limited information in low-quality images, detecting low-quality deepfake remains an important challenge. In this work, we apply frequency domain learning and optimal transport theory in knowledge distillation (KD) to specifically improve the detection of low-quality compressed deepfake images. We explore transfer learning capability in KD to enable a student network to learn discriminative features from low-quality images effectively. In particular, we propose the Attention-based Deepfake detection Distiller (ADD), which consists of two novel distillations: 1) frequency attention distillation that effectively retrieves the removed high-frequency components in the student network, and 2) multi-view attention distillation that creates multiple attention vectors by slicing the teacher's and student's tensors under different views to transfer the teacher tensor's distribution to the student more efficiently. Our extensive experimental results demonstrate that our approach outperforms state-of-the-art baselines in detecting low-quality compressed deepfake images.
Code (2)
Tasks
DeepFake DetectionFace SwappingKnowledge DistillationTransfer LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Frequency Attention for Knowledge Distillation
Knowledge distillation is an attractive approach for learning compact deep neural networks, which learns a lightweight student model by distilling knowledge from a complex teacher model. Attention-based knowledge distill…
image-classificationImage ClassificationKnowledge Distillationobject-detection+2Triple-View Knowledge Distillation for Semi-Supervised Semantic Segmentation
To alleviate the expensive human labeling, semi-supervised semantic segmentation employs a few labeled images and an abundant of unlabeled images to predict the pixel-level label map with the same size. Previous methods …
DecoderFeature ImportanceKnowledge DistillationSemantic Segmentation+1Powerful Teachers Matter: Text-Guided Multi-view Knowledge Distillation with Visual Prior Enhancement
Knowledge distillation transfers knowledge from large teacher models to smaller students for efficient inference. While existing methods primarily focus on distillation strategies, they often overlook the importance of e…
Knowledge DistillationFD-CanKD: Frequency-Decoupled Cross-Attention Distillation as a Refinement Prior for Compact Object Detectors
Compact object detectors are suitable for resource-constrained visual perception, but their limited representation capacity creates an accuracy gap relative to large models. Conventional detector distillation often relie…
Knowledge DistillationFreeKD: Knowledge Distillation via Semantic Frequency Prompt
Knowledge distillation (KD) has been applied to various tasks successfully, and mainstream methods typically boost the student model via spatial imitation losses. However, the consecutive downsamplings induced in the spa…
Knowledge Distillation