Abstract | ||
---|---|---|
Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the latency constraint of a mobile device? Neural Architecture Search (NAS) for ConvNet design is a challenging problem due to the combinatorially large design space and search time (at least 200 GPU-hours). To alleviate this complexity, we propose Single-Path NAS, a novel differentiable NAS method for designing device-efficient ConvNets in less than 4 hours. 1. Novel NAS formulation: our method introduces a single-path, over-parameterized ConvNet to encode all architectural decisions with shared convolutional kernel parameters. 2. NAS efficiency: Our method decreases the NAS search cost down to 8 epochs (30 TPU-hours), i.e., up to 5,000x faster compared to prior work. 3. On-device image classification: Single-Path NAS achieves 74.96% top-1 accuracy on ImageNet with 79ms inference latency on a Pixel 1 phone, which is state-of-the-art accuracy compared to NAS methods with similar latency (<80ms). |
Year | Venue | DocType |
---|---|---|
2019 | arXiv: Learning | Journal |
Volume | Citations | PageRank |
abs/1905.04159 | 2 | 0.37 |
References | Authors | |
0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
dimitrios stamoulis | 1 | 54 | 7.05 |
Ruizhou Ding | 2 | 2 | 0.37 |
Di Wang | 3 | 1337 | 143.48 |
Dimitrios K. Lymberopoulos | 4 | 1714 | 109.98 |
Bodhi Priyantha | 5 | 232 | 15.52 |
Jie Liu | 6 | 1438 | 94.17 |
Diana Marculescu | 7 | 2725 | 223.87 |