SIPA: A Simple Framework for Efficient Networks
This work addresses the need for lightweight models in resource-constrained IoT environments, representing an incremental improvement through a structured framework for model optimization.
The paper tackles the problem of developing efficient deep learning models for low-power IoT devices by proposing the SIPA framework, which achieved 334x parameter compression and 357x operation reduction compared to WideResNet-28-10, placing 4th in the CIFAR-100 track of the MicroNet Challenge.
With the success of deep learning in various fields and the advent of numerous Internet of Things (IoT) devices, it is essential to lighten models suitable for low-power devices. In keeping with this trend, MicroNet Challenge, which is the challenge to build efficient models from the view of both storage and computation, was hosted at NeurIPS 2019. To develop efficient models through this challenge, we propose a framework, coined as SIPA, consisting of four stages: Searching, Improving, Pruning, and Accelerating. With the proposed framework, our team, OSI AI, compressed 334x the parameter storage and 357x the math operation compared to WideResNet-28-10 and took 4th place in the CIFAR-100 track at MicroNet Challenge 2019 with the top 10% highly efficient computation. Our source code is available from https://github.com/Lee-Gihun/MicroNet_OSI-AI.