Towards Evolutional Compression
This addresses the need for efficient CNN deployment on mobile devices, though it appears incremental as it builds on existing compression techniques with a novel evolutionary approach.
The paper tackles the problem of compressing convolutional neural networks (CNNs) for mobile applications by introducing an evolutionary method to automatically eliminate redundant convolution filters, resulting in an extremely compact CNN with improved compression and speed-up ratios, as demonstrated by experiments showing superiority over state-of-the-art methods.
Compressing convolutional neural networks (CNNs) is essential for transferring the success of CNNs to a wide variety of applications to mobile devices. In contrast to directly recognizing subtle weights or filters as redundant in a given CNN, this paper presents an evolutionary method to automatically eliminate redundant convolution filters. We represent each compressed network as a binary individual of specific fitness. Then, the population is upgraded at each evolutionary iteration using genetic operations. As a result, an extremely compact CNN is generated using the fittest individual. In this approach, either large or small convolution filters can be redundant, and filters in the compressed network are more distinct. In addition, since the number of filters in each convolutional layer is reduced, the number of filter channels and the size of feature maps are also decreased, naturally improving both the compression and speed-up ratios. Experiments on benchmark deep CNN models suggest the superiority of the proposed algorithm over the state-of-the-art compression methods.