发表机构
Huazhong Agricultural University; Peking University; National University of Singapore; Nantong University; Wuhan University（华中农业大学; 北京大学; 新加坡国立大学; 南通大学; 武汉大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对人脸伪造技术发展带来的检测挑战及传统方法的问题，提出密度感知区域决定性重放策略InfoDense，通过定位决定性补丁、排序候选片段、自适应合并样本等步骤，有效减轻灾难性遗忘，提升跨域泛化能力。
AI 中文摘要
人脸伪造技术的快速发展带来了越来越多的操纵手段。增量式人脸伪造检测（IFFD）作为一种应对不断演变的伪造威胁的有前途的方法应运而生，它通过增量添加新的伪造数据来微调先前训练的模型。然而，传统的基于重放的IFFD方法存在灾难性遗忘问题。在有限内存下存储完整历史图像往往无法保留细微的伪造线索或引入域偏差，降低了模型学习内在和可转移操纵特征的能力。本文提出了一种密度感知区域决定性重放策略InfoDense来应对这些挑战。InfoDense优先考虑伪影密集和伪造关键区域，在保持高保真伪造证据的同时显著降低存储需求。首先引入InfoDense Cut使用基于CLIP的嵌入定位决定性补丁，然后InfoDense Select通过结合潜在空间代表性和决定性补丁数量对候选片段进行排序，确保重放缓冲区的多样性和信息密度，最后InfoDense Fuse通过将存储的片段与当前任务样本自适应合并来重建无偏训练输入，增强知识保留和泛化能力。在具有挑战性的增量深度伪造基准上的大量实验表明，InfoDense有效地减轻了灾难性遗忘，同时提高了跨域泛化能力。
英文摘要
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.
