Exploring Deep-to-Shallow Transformable Neural Networks for Intelligent Embedded Systems
This work addresses the problem of deploying accurate and efficient neural networks on resource-constrained embedded systems, representing an incremental advancement in neural architecture search methods.
The paper tackled the trade-off between accuracy and hardware efficiency in neural networks for embedded systems by proposing Double-Win NAS, a deep-to-shallow transformable neural architecture search paradigm, achieving superior performance on benchmarks like ImageNet with improved efficiency on embedded platforms such as NVIDIA Jetson.
Thanks to the evolving network depth, convolutional neural networks (CNNs) have achieved remarkable success across various embedded scenarios, paving the way for ubiquitous embedded intelligence. Despite its promise, the evolving network depth comes at the cost of degraded hardware efficiency. In contrast to deep networks, shallow networks can deliver superior hardware efficiency but often suffer from inferior accuracy. To address this dilemma, we propose Double-Win NAS, a novel deep-to-shallow transformable neural architecture search (NAS) paradigm tailored for resource-constrained intelligent embedded systems. Specifically, Double-Win NAS strives to automatically explore deep networks to first win strong accuracy, which are then equivalently transformed into their shallow counterparts to further win strong hardware efficiency. In addition to search, we also propose two enhanced training techniques, including hybrid transformable training towards better training accuracy and arbitrary-resolution elastic training towards enabling natural network elasticity across arbitrary input resolutions. Extensive experimental results on two popular intelligent embedded systems (i.e., NVIDIA Jetson AGX Xavier and NVIDIA Jetson Nano) and two representative large-scale datasets (i.e., ImageNet and ImageNet-100) clearly demonstrate the superiority of Double-Win NAS over previous state-of-the-art NAS approaches.