Multi-teacher Knowledge Distillation for Compressed Video Action Recognition on Deep Neural Networks
Meng-Chieh Wu, Ching‐Te Chiu, Kun-Hsuan Wu · 2019
Recently, convolutional neural networks (CNNs) have seen great progress in classifying images. Action recognition is different from still image classification; video data contains temporal information that plays an important role in video understanding. Currently, most CNN-based approaches for action recognition have excessive computational costs, with an explosion of parameters and computation time. The currently most efficient method trains a deep network directly on compressed video containing the motion information. However, this method has a large number of parameters. We propose a multi-teacher knowledge distillation framework for compressed video action recognition to compress this model. With this framework, the model is compressed by transferring the knowledge from multiple teachers to a single small student model. With multi-teacher knowledge distillation, students learn better than with single-teacher knowledge distillation. Experiments show that we can reach a 2.4× compression rate in a number of parameters and a 1.2× computation reduction with 1.79% loss of accuracy on the UCF-101 dataset and 0.35% loss of accuracy on the HMDB51 dataset.