InfoDense: Density-Aware Regional Decisive Replay for Memory-Efficient Incremental Face Forgery Detection
Computer Vision and Pattern Recognition
Summary
The authors address the problem of detecting face forgeries as new types keep appearing. They propose a method called InfoDense that smartly saves only important parts of forged images to help a detection model remember past forgeries without needing to store whole images. This approach reduces memory use and helps the model learn better by mixing saved pieces with new examples during training. Their experiments show this method helps avoid forgetting old forgery traits and improves detection across different types of forgeries.
Authors
Jikang Cheng, Hao Shen, Xueyi Zhang, Guangcheng Wang, Zhongyuan Wang, Renye Yan, Baojin Huang
Abstract
The rapid evolution of face forgery techniques has introduced an increasing variety of manipulations. Incremental Face Forgery Detection (IFFD), which incrementally adds new forgery data to fine-tune previously trained models, has emerged as a promising approach to handle evolving forgery threats. However, conventional replay-based IFFD methods suffer from catastrophic forgetting. Storing full historical images under limited memory often either fails to preserve subtle forgery cues or introduces domain bias, reducing the model's ability to learn intrinsic and transferable manipulation characteristics. In this paper, we propose a Density-Aware Regional Decisive replay strategy, termed InfoDense, to address these challenges. InfoDense prioritizes artifact-dense and forgery-critical regions, significantly reducing storage requirements while maintaining high-fidelity forgery evidence. We first introduce InfoDense Cut to localize decisive patches using CLIP-based embeddings. Then, InfoDense Select ranks candidate segments by combining latent-space representativeness and decisive patch counts, ensuring both diversity and information density in the replay buffer. Finally, InfoDense Fuse reconstructs unbiased training inputs by adaptively merging stored segments with current-task samples, enhancing knowledge retention and generalization. Extensive experiments on challenging incremental deepfake benchmarks demonstrate that InfoDense effectively mitigates catastrophic forgetting while improving cross-domain generalization.