1. Separable Selfattention for Mobile Vision Transformers;mehta;ArXiv abs/2206 02680,2022
2. Understanding the Effective Receptive Field in Deep Convolutional Neural Networks;luo;ArXiv abs/1701 04128,2016
3. Rethinking Bottleneck Structure for Efficient Mobile Network Design;daquan;ECCV,2020
4. CBAM: Convolutional Block Attention Module
5. MobileViT: Lightweight, General-purpose, and Mobile-friendly Vision Transformer;mehta;ArXiv abs/2110 02178,2022