@inproceedings{22ff91a692804c3aa7d41ab184c798b3,
title = "ChamNet: Towards efficient network design through platform-aware model adaptation",
abstract = "This paper proposes an efficient neural network (NN) architecture design methodology called Chameleon that honors given resource constraints. Instead of developing new building blocks or using computationally-intensive reinforcement learning algorithms, our approach leverages existing efficient network building blocks and focuses on exploiting hardware traits and adapting computation resources to fit target latency and/or energy constraints. We formulate platform-aware NN architecture search in an optimization framework and propose a novel algorithm to search for optimal architectures aided by efficient accuracy and resource (latency and/or energy) predictors. At the core of our algorithm lies an accuracy predictor built atop Gaussian Process with Bayesian optimization for iterative sampling. With a one-time building cost for the predictors, our algorithm produces state-of-the-art model architectures on different platforms under given constraints in just minutes. Our results show that adapting computation resources to building blocks is critical to model performance. Without the addition of any special features, our models achieve significant accuracy improvements relative to state-of-the-art handcrafted and automatically designed architectures. We achieve 73.8% and 75.3% top-1 accuracy on ImageNet at 20ms latency on a mobile CPU and DSP. At reduced latency, our models achieve up to 8.2% (4.8%) and 6.7% (9.3%) absolute top-1 accuracy improvements compared to MobileNetV2 and MnasNet, respectively, on a mobile CPU (DSP), and 2.7% (4.6%) and 5.6% (2.6%) accuracy gains over ResNet-101 and ResNet-152, respectively, on an Nvidia GPU (Intel CPU).",
keywords = "Categorization, Deep Learning, Recognition: Detection, Retrieval",
author = "Xiaoliang Dai and Peizhao Zhang and Bichen Wu and Hongxu Yin and Fei Sun and Yanghan Wang and Marat Dukhan and Yunqing Hu and Yiming Wu and Yangqing Jia and Peter Vajda and Matt Uyttendaele and Jha, {Niraj K.}",
note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 ; Conference date: 16-06-2019 Through 20-06-2019",
year = "2019",
month = jun,
doi = "10.1109/CVPR.2019.01166",
language = "English (US)",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "11390--11399",
booktitle = "Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019",
address = "United States",
}