S2-aware network for visual recognition

作者：

Highlights：

• A width-aware and deep-aware module is build.

• A size-aware and shape-aware network for visual recognition is build.

• Compared with other state-of-the-art methods, the proposed method can achieve better results while consume less parameters and FLOPs.

摘要

•A width-aware and deep-aware module is build.•A size-aware and shape-aware network for visual recognition is build.•Compared with other state-of-the-art methods, the proposed method can achieve better results while consume less parameters and FLOPs.

论文关键词：Convolution neural network,Size aware,Shape aware,Light weight

论文评审过程：Received 12 December 2020, Revised 18 July 2021, Accepted 23 August 2021, Available online 30 August 2021, Version of Record 10 September 2021.

论文官网地址：https://doi.org/10.1016/j.image.2021.116458