.png){kind=icon}
.png){kind=icon}
Return
Resolution Based Incremental Scaling Methodology for CNNs
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2023.3286030.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Designing an optimal CNN for each embedded device with a different resource budget would be time-consuming and inefficient. Network scaling provides a viable solution to tackle this challenge, In this work, we propose a novel network scaling strategy called RBIS (resolution-based incremental scaling). Unlike the previous works that consider the width, depth, and input resolution together, we first find the input resolution candidates on a given hardware platform. For each resolution candidate, we incrementally scale the depth and width of each stage up to limit of available resources. Comparison with other scaling methods proves the superiority of the proposed scaling methodology. RBIS finds a more accurate model by up to 0.53 % for EfficientNet-B1 and 0.67 % for the S3NAS B2 scale.
Keywords:
Neural architecture search
network scaling
EfficientNet