DPP-Net: Device-Aware Progressive Search for Pareto-Optimal Neural Architectures [chapter]

Jin-Dong Dong, An-Chieh Cheng, Da-Cheng Juan, Wei Wei, Min Sun
2018 Lecture Notes in Computer Science  
Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performances in applications such as image classification and language modeling. However, these techniques typically ignore device-related objectives such as inference time, memory usage, and power consumption. Optimizing neural architecture for devicerelated objectives is immensely crucial for deploying deep networks on portable devices with limited computing resources. We propose DPP-Net: Device-aware
more » ... ressive Search for Pareto-optimal Neural Architectures, optimizing for both device-related (e.g., inference time and memory usage) and device-agnostic (e.g., accuracy and model size) objectives. DPP-Net employs a compact search space inspired by current state-of-the-art mobile CNNs, and further improves search efficiency by adopting progressive search . Experimental results on CIFAR-10 are poised to demonstrate the effectiveness of Pareto-optimal networks found by DPP-Net, for three different devices: (1) a workstation with Titan X GPU, (2) NVIDIA Jetson TX1 embedded system, and (3) mobile phone with ARM Cortex-A53. Compared to CondenseNet and NASNet (Mobile), DPP-Net achieves better performances: higher accuracy & shorter inference time on various devices. Additional experimental results show that models found by DPP-Net also achieve considerablygood performance on ImageNet as well.
doi:10.1007/978-3-030-01252-6_32 fatcat:ff45jydddjbc3puknmo7r4qghy