CONet: Channel Optimization for Convolutional Neural Networks
This work addresses the challenge of manual and heuristic-based channel selection in CNNs, offering an automated solution for researchers and practitioners in deep learning, though it appears incremental as it builds on existing NAS methods.
The paper tackles the problem of channel size optimization in convolutional neural networks by introducing CONet, an efficient dynamic scaling algorithm that automatically optimizes channel sizes across layers, resulting in architectures that outperform baseline models on CIFAR10/100 and ImageNet datasets.
Neural Architecture Search (NAS) has shifted network design from using human intuition to leveraging search algorithms guided by evaluation metrics. We study channel size optimization in convolutional neural networks (CNN) and identify the role it plays in model accuracy and complexity. Current channel size selection methods are generally limited by discrete sample spaces while suffering from manual iteration and simple heuristics. To solve this, we introduce an efficient dynamic scaling algorithm -- CONet -- that automatically optimizes channel sizes across network layers for a given CNN. Two metrics -- "\textit{Rank}" and "\textit{Rank Average Slope}" -- are introduced to identify the information accumulated in training. The algorithm dynamically scales channel sizes up or down over a fixed searching phase. We conduct experiments on CIFAR10/100 and ImageNet datasets and show that CONet can find efficient and accurate architectures searched in ResNet, DARTS, and DARTS+ spaces that outperform their baseline models. This document supersedes previously published paper in ICCV2021-NeurArch workshop. An additional section is included on manual scaling of channel size in CNNs to numerically validate of the metrics used in searching optimum channel configurations in CNNs.