发表机构
Fudan University; Peking University（复旦大学; 北京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对AI生成视频检测中持续学习框架不足的问题，提出SphereVideo框架，以超球面原型锚定与多尺度时序建模提升泛化性，在已见和未见数据上均优于现有方法
AI 中文摘要
AI生成视频（AIGV）检测旨在区分真实视频与AI生成视频。实际应用中，在现有数据上训练的检测器往往无法泛化到新出现的生成模型，使得该任务极具挑战性，因此持续学习（CL）对提升适应性至关重要，但针对该任务的CL框架仍未得到充分探索。为此，我们提出SphereVideo，这是一种用于AIGV检测的新型CL框架，基于两项关键观察构建：其一，真实视频呈现紧凑的特征分布，基于此，我们鼓励真实视频特征在超球面上围绕真实原型聚类，同时排斥AI生成样本，从而建立决策边界，该原型可作为CL的稳定锚点，调控边界演化并缓解灾难性遗忘；其二，现有方法往往仅依赖空间伪影作为捷径，为增强时序建模，我们引入一种在帧和片段层面建模真实数据时序动态的策略，通过强化真实数据建模，该策略进一步助力学习真实原型并形成稳定决策边界。此外，我们构建了一个全面且具有挑战性的基准，大量实验表明，SphereVideo实现了更优的可塑性-稳定性权衡，在已见数据上比现有方法提升3.08%，在未见AI生成数据上提升4.00%。
英文摘要
AI-generated video (AIGV) detection aims to distinguish real videos from AI-generated ones. In practice, detectors trained on existing data often fail to generalize to newly emerging generative models, making this task challenging. Therefore, continual learning (CL) is essential for improving the adaptability. However, CL frameworks for this task remain underexplored. To this end, we propose SphereVideo, a novel CL framework for AIGV detection built on two key observations. First, real videos exhibit a compact feature distribution. Based on this, we encourage real video features to cluster around a real prototype on a hypersphere while repelling AI-generated samples, thereby establishing a decision boundary. This prototype serves as a stable anchor for CL, regulating boundary evolution and mitigating catastrophic forgetting. Second, existing methods tend to rely solely on spatial artifacts as shortcuts. To enhance temporal modeling, we introduce a strategy that models the temporal dynamics of real data at both frame and clip levels. By strengthening real data modeling, this strategy further facilitates learning a real prototype and forming a stable decision boundary. Moreover, we construct a comprehensive and challenging benchmark. Extensive experiments demonstrate that SphereVideo achieves an improved plasticity-stability trade-off, outperforming prior methods by 3.08% on seen data and 4.00% on unseen AI-generated data.
