COMNET : CORTICAL MODULES ARE POWERFUL
Lists
Only you see this
Abstract
Existing CNN architectures may achieve efficiency in either one or two dimensions: FLOPs, depth, accuracy, representation power, latency but not in all. In this work, we present a pragmatically designed novel CNN architecture “CoMNet” which offers multi-dimensional efficiency at once such as: simple yet accurate, lower latency and FLOPs, high representation power in limited parameters, low memory consumption, negligible branching, smaller depths, and only a few design hyperparameters. The key to achieve the multi-dimensional efficiency is our use of biological underpinnings into CoMNet which is primarily the organization of cortical modules in the visual cortex. To realize CoMNet, a few concepts from well understood CNN designs are directly inherited such as residual learning. Our solid experimental evaluations demonstrate superiority of CoMNet over many state-of-the-art industry and academia dominant architectures such as ResNet, RepVGG etc. For instance, CoMNet supersedes ResNet-50 on ImageNet while being 50% shallower, 22% lesser parameters, 25% lower FLOPs and latency, and in 16% lesser training epochs. Code will be opensourced post the reviews.
BibTeX
@inproceedings{kumar2023comnet,
author = {Ashish Kumar and Laxmidhar Behera},
title = {{COMNET : CORTICAL MODULES ARE POWERFUL}},
booktitle = {International Conference on Learning Representations},
year = {2023},
url = {https://openreview.net/forum?id=Crw1sKsLDvl},
}Loading related content...