Rehearsal-based video incremental learning often employs knowledge distillation to mitigate catastrophic forgetting of previously learned data. However, this method faces two major challenges for video task: substantial computing resources from loading teacher model and limited replay capability from performance-limited teacher model. To address these problems, we first propose a knowledge distillation-free framework for rehearsal-based video incremental learning called \textit{Teacher Agent}. Instead of loading parameter-heavy teacher networks, we introduce an agent generator that is either parameter-free or uses only a few parameters to obtain accurate and reliable soft labels. This method not only greatly reduces the computing requirement but also circumvents the problem of knowledge misleading caused by inaccurate predictions of the teacher model. Moreover, we put forward a self-correction loss which provides an effective regularization signal for the review of old knowledge, which in turn alleviates the problem of catastrophic forgetting. Further, to ensure that the samples in the memory buffer are memory-efficient and representative, we introduce a unified sampler for rehearsal-based video incremental learning to mine fixed-length key video frames. Interestingly, based on the proposed strategies, the network exhibits a high level of robustness against spatial resolution reduction when compared to the baseline. Extensive experiments demonstrate the advantages of our method, yielding significant performance improvements while utilizing only half the spatial resolution of video clips as network inputs in the incremental phases.

翻译：基于回放的视频增量学习通常采用知识蒸馏来缓解对先前学习数据的灾难性遗忘。然而，该方法在视频任务中面临两大挑战：加载教师模型所需的大量计算资源，以及性能受限的教师模型导致的重放能力有限。为解决这些问题，我们首先提出一种无需知识蒸馏的基于回放的视频增量学习框架，称为“老师代理”（*Teacher Agent*）。我们不加载参数繁重的教师网络，而是引入一个代理生成器，该生成器无需参数或仅需少量参数即可获得准确可靠的软标签。该方法不仅大幅降低了计算需求，还避免了因教师模型预测不准确而导致的知识误导问题。此外，我们提出一种自修正损失函数，为旧知识的回顾提供了有效的正则化信号，从而缓解了灾难性遗忘问题。进一步地，为确保记忆缓冲区的样本既节省内存又具有代表性，我们引入一种用于基于回放的视频增量学习的统一采样器，以挖掘固定长度的关键视频帧。有趣的是，基于所提出的策略，与基线相比，网络在空间分辨率降低时展现出较高的鲁棒性。大量实验证明了我们方法的优势：在增量阶段仅使用视频片段一半空间分辨率作为网络输入的情况下，仍能实现显著的性能提升。