论文标题
在视频中进行行动识别的课堂学习学习
Class-Incremental Learning for Action Recognition in Videos
论文作者
论文摘要
我们解决了视频识别的班级学习学习中的灾难性遗忘问题，尽管持续学习的流行，但尚未积极探索。我们的框架通过引入时间通道重要性图并利用通过知识蒸馏来学习传入示例的表示的重要性图来解决这一挑战。我们还将正规化方案纳入我们的目标函数中，该方案鼓励从视频中不同时间步骤获得的单个特征是不相关的，并最终通过减轻灾难性的遗忘来提高准确性。我们评估了针对UCF101，HMDB51和其他一些V2数据集构建的类动作识别基准的全新分割的建议方法，并证明了我们算法与最初为图像数据设计的现有持续学习方法相比，我们的算法的有效性。
We tackle catastrophic forgetting problem in the context of class-incremental learning for video recognition, which has not been explored actively despite the popularity of continual learning. Our framework addresses this challenging task by introducing time-channel importance maps and exploiting the importance maps for learning the representations of incoming examples via knowledge distillation. We also incorporate a regularization scheme in our objective function, which encourages individual features obtained from different time steps in a video to be uncorrelated and eventually improves accuracy by alleviating catastrophic forgetting. We evaluate the proposed approach on brand-new splits of class-incremental action recognition benchmarks constructed upon the UCF101, HMDB51, and Something-Something V2 datasets, and demonstrate the effectiveness of our algorithm in comparison to the existing continual learning methods that are originally designed for image data.
