CARS: Continuous Evolution for Efficient Neural Architecture Search

Zhaohui Yang, Yunhe Wang, Xinghao Chen, Boxin Shi, Chao Xu, Chunjing Xu, Qi Tian, Chang Xu; The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 1829-1838

Abstract


Searching techniques in most of existing neural architecture search (NAS) algorithms are mainly dominated by differentiable methods for the efficiency reason. In contrast, we develop an efficient continuous evolutionary approach for searching neural networks. Architectures in the population that share parameters within one SuperNet in the latest generation will be tuned over the training dataset with a few epochs. The searching in the next evolution generation will directly inherit both the SuperNet and the population, which accelerates the optimal network generation. The non-dominated sorting strategy is further applied to preserve only results on the Pareto front for accurately updating the SuperNet. Several neural networks with different model sizes and performances will be produced after the continuous search with only 0.4 GPU days. As a result, our framework provides a series of networks with the number of parameters ranging from 3.7M to 5.1M under mobile settings. These networks surpass those produced by the state-of-the-art methods on the benchmark ImageNet dataset.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Yang_2020_CVPR,
author = {Yang, Zhaohui and Wang, Yunhe and Chen, Xinghao and Shi, Boxin and Xu, Chao and Xu, Chunjing and Tian, Qi and Xu, Chang},
title = {CARS: Continuous Evolution for Efficient Neural Architecture Search},
booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}