Recurrent Residual Module for Fast Inference in Videos
This work addresses the computational bottleneck for video recognition tasks, offering a practical speed-up for applications like pose estimation and object detection, though it is incremental as it builds on existing CNN frameworks.
The authors tackled the problem of computationally expensive CNN inference on videos by proposing the Recurrent Residual Module (RRM), which accelerates inference by reducing redundant computation using similarity in intermediate feature maps, achieving average 2x acceleration on common CNNs and up to 9x on binary networks while maintaining similar recognition performance.
Deep convolutional neural networks (CNNs) have made impressive progress in many video recognition tasks such as video pose estimation and video object detection. However, CNN inference on video is computationally expensive due to processing dense frames individually. In this work, we propose a framework called Recurrent Residual Module (RRM) to accelerate the CNN inference for video recognition tasks. This framework has a novel design of using the similarity of the intermediate feature maps of two consecutive frames, to largely reduce the redundant computation. One unique property of the proposed method compared to previous work is that feature maps of each frame are precisely computed. The experiments show that, while maintaining the similar recognition performance, our RRM yields averagely 2x acceleration on the commonly used CNNs such as AlexNet, ResNet, deep compression model (thus 8-12x faster than the original dense models using the efficient inference engine), and impressively 9x acceleration on some binary networks such as XNOR-Nets (thus 500x faster than the original model). We further verify the effectiveness of the RRM on speeding up CNNs for video pose estimation and video object detection.