Achieving an optimal group structure in a neural architecture search

Abstract

The method proposed in this letter searches for an effective group structure of group convolutions in a convolutional neural network that can improve the classification accuracy. The model's group structure is obtained using an effective differential neural architecture search. Our code can be accessed at https://github.com/minercode625/grunas.git. © 2022 The Authors. Electronics Letters published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.