Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search

Abstract

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 better speed/accuracy trade-off of searched networks, which is termed "Partial Order Pruning". It prunes the architecture search space with a partial order assumption to automatically search for the architectures with the best speed and accuracy trade-off. Our algorithm explicitly takes profile information about the inference speed on the target platform into consideration. With the proposed algorithm, we present several Dongfeng (DF) networks that provide high accuracy and fast inference speed on various application GPU platforms. By further searching decoder architectures, our DF-Seg real-time segmentation networks yield state-of-the-art speed/accuracy trade-off on both the target embedded device and the high-end GPU.

arXiv commentAccepted to CVPR 2019

References in corpus (8)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
• Large-Scale Evolution of Image Classifiers
• Large Batch Training of Convolutional Networks
• Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
• Progressive Neural Architecture Search

Cited by in corpus (4)

• Bringing AI To Edge: From Deep Learning's Perspective
• Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS
• BETANAS: BalancEd TrAining and selective drop for Neural Architecture Search
• Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural Networks