Oleg Zabluda's blog
Thursday, August 09, 2018
 
MnasNet: Platform-Aware Neural Architecture Search for Mobile (2018) Mingxing Tan, Bo Chen, Ruoming Pang, Vijay...
MnasNet: Platform-Aware Neural Architecture Search for Mobile (2018) Mingxing Tan, Bo Chen, Ruoming Pang, Vijay Vasudevan, Quoc V. Le
"""
automated neural architecture search approach for designing resource-constrained mobile CNN models. We propose to explicitly incorporate latency information into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency. Unlike in previous work, where mobile latency is considered via another, often inaccurate proxy (e.g., FLOPS), in our experiments, we directly measure real-world inference latency by executing the model on a particular platform, e.g., Pixel phones. [...] our approach consistently outperforms state-of-the-art mobile CNN models across multiple vision tasks. On the ImageNet classification task, our model achieves 74.0% top-1 accuracy with 76ms latency on a Pixel phone, which is 1.5x faster than MobileNetV2 (Sandler et al. 2018) and 2.4x faster than NASNet (Zoph et al. 2018) with the same top-1 accuracy. On the COCO object detection task, our model family achieves both higher mAP quality and lower latency than MobileNets.
"""
https://arxiv.org/abs/1807.11626
https://arxiv.org/abs/1807.11626

Labels:


| |

Home

Powered by Blogger