Video object detection is a fundamental yet challenging task in computer vision. One practical solution is to take advantage of temporal information from the video and apply feature aggregation to enhance the object features in each frame. Though effective, those existing methods always suffer from low inference speeds because they use a fixed number of frames for feature aggregation regardless of the input frame. Therefore, this paper aims to improve the inference speed of the current feature aggregation-based video object detectors while maintaining their performance. To achieve this goal, we propose a vanilla dynamic aggregation module that adaptively selects the frames for feature enhancement. Then, we extend the vanilla dynamic aggregation module to a more effective and reconfigurable deformable version. Finally, we introduce inplace distillation loss to improve the representations of objects aggregated with fewer frames. Extensive experimental results validate the effectiveness and efficiency of our proposed methods: On the ImageNet VID benchmark, integrated with our proposed methods, FGFA and SELSA can improve the inference speed by 31% and 76% respectively while getting comparable performance on accuracy.
View on arXiv