Practical Block-Wise Neural Network Architecture Generation

• Published in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 2423 - 2432
• Main Authors: Zhong, Zhao, Yan, Junjie, Wu, Wei, Shao, Jing, Liu, Cheng-Lin
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Computer architecture; Convolutional codes; Convolutional neural networks; Indexes; Network architecture; Task analysis
• ISSN: 1063-6919
• DOI: 10.1109/CVPR.2018.00257

Convolutional neural networks have gained a remarkable success in computer vision. However, most usable network architectures are hand-crafted and usually require expertise and elaborate design. In this paper, we provide a block-wise network generation pipeline called BlockQNN which automatically builds high-performance networks using the Q-Learning paradigm with epsilon-greedy exploration strategy. The optimal network block is constructed by the learning agent which is trained sequentially to choose component layers. We stack the block to construct the whole auto-generated network. To accelerate the generation process, we also propose a distributed asynchronous framework and an early stop strategy. The block-wise generation brings unique advantages: (1) it performs competitive results in comparison to the hand-crafted state-of-the-art networks on image classification, additionally, the best network generated by BlockQNN achieves 3.54% top-1 error rate on CIFAR-10 which beats all existing auto-generate networks. (2) in the meanwhile, it offers tremendous reduction of the search space in designing networks which only spends 3 days with 32 GPUs, and (3) moreover, it has strong generalizability that the network built on CIFAR also performs well on a larger-scale ImageNet dataset.