Neural Architecture Search for Lightweight Non-Local Networks
Johns Hopkins University
arXiv:2004.01961 [cs.CV], (4 Apr 2020)
@misc{li2020neural,
title={Neural Architecture Search for Lightweight Non-Local Networks},
author={Yingwei Li and Xiaojie Jin and Jieru Mei and Xiaochen Lian and Linjie Yang and Cihang Xie and Qihang Yu and Yuyin Zhou and Song Bai and Alan Yuille},
year={2020},
eprint={2004.01961},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
Non-Local (NL) blocks have been widely studied in various vision tasks. However, it has been rarely explored to embed the NL blocks in mobile neural networks, mainly due to the following challenges: 1) NL blocks generally have heavy computation cost which makes it difficult to be applied in applications where computational resources are limited, and 2) it is an open problem to discover an optimal configuration to embed NL blocks into mobile neural networks. We propose AutoNL to overcome the above two obstacles. Firstly, we propose a Lightweight Non-Local (LightNL) block by squeezing the transformation operations and incorporating compact features. With the novel design choices, the proposed LightNL block is 400x computationally cheaper} than its conventional counterpart without sacrificing the performance. Secondly, by relaxing the structure of the LightNL block to be differentiable during training, we propose an efficient neural architecture search algorithm to learn an optimal configuration of LightNL blocks in an end-to-end manner. Notably, using only 32 GPU hours, the searched AutoNL model achieves 77.7% top-1 accuracy on ImageNet under a typical mobile setting (350M FLOPs), significantly outperforming previous mobile models including MobileNetV2 (+5.7%), FBNet (+2.8%) and MnasNet (+2.1%). Code and models are available.
April 12, 2020 by hgpu
