Deep neural networks based methods have been proved to achieve outstanding
performance on object detection and classification tasks. Despite significant
performance improvement, due to the deep structures, they still require
prohibitive runtime to process images and maintain the highest possible
performance for real-time applications. Observing the phenomenon that human
vision system (HVS) relies heavily on the temporal dependencies among frames
from the visual input to conduct recognition efficiently, we propose a novel
framework dubbed as TKD: temporal knowledge distillation. This framework
distills the temporal knowledge from a heavy neural networks based model over
selected video frames (the perception of the moments) to a light-weight model.
To enable the distillation, we put forward two novel procedures: 1) an
Long-short Term Memory (LSTM) based key frame selection method; and 2) a novel
teacher-bounded loss design. To validate, we conduct comprehensive empirical
evaluations using different object detection methods over multiple datasets
including Youtube-Objects and Hollywood scene dataset. Our results show
consistent improvement in accuracy-speed trad-offs for object detection over
the frames of the dynamic scene, compare to other modern object recognition
methods.

我们提出了一种名为 TKD 的新框架，利用深度神经网络基于的模型所选择的视频帧（瞬间的感知）来蒸馏轻量级模型中的时间知识，通过进行两个新的步骤：1）基于 LSTM 的关键帧选择方法；2）新的教师束缚损失设计。使用不同的目标检测方法，在多个数据集上进行了全面的经验评估，包括 Youtube-Objects 和 Hollywood 场景数据集。我们的结果显示，与其他现代对象识别方法相比，我们在动态场景的帧上的目标检测准确度 - 速度平衡方面有着一致的提高。