Partial Order Pruning: For Best Speed/Accuracy Trade-Off in Neural Architecture Search

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 9137 - 9145
• Main Authors: Li, Xin, Zhou, Yiming, Pan, Zheng, Feng, Jiashi
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2019
• Subjects: Deep Learning; Grouping and Shape; Segmentation
• ISSN: 1063-6919
• DOI: 10.1109/CVPR.2019.00936

Achieving good speed and accuracy trade-off on a target platform is very important in deploying deep neural networks in real world scenarios. However, most existing automatic architecture search approaches only concentrate on high performance. In this work, we propose an algorithm that can offer bet...