Practical networks for edge devices adopt shallow depth and small convolutional kernels to save memory and computational cost, which leads to a restricted receptive field. Conventional efficient learning methods focus on lightweight convolution designs, ignoring the role of the receptive field in neural network design. In this paper, we propose the Meta-Pooling framework to make the receptive field learnable for a lightweight network, which consists of parameterized pooling-based operations. Specifically, we introduce a parameterized spatial enhancer, which is composed of pooling operations to provide versatile receptive fields for each layer of a lightweight model. Then, we present a Progressive Meta-Pooling Learning (PMPL) strategy for the parameterized spatial enhancer to acquire a suitable receptive field size. The results on the ImageNet dataset demonstrate that MobileNetV2 using Meta-Pooling achieves top1 accuracy of 74.6\%, which outperforms MobileNetV2 by 2.3\%.
@article{arxiv.2301.10038,
title = {Progressive Meta-Pooling Learning for Lightweight Image Classification Model},
author = {Peijie Dong and Xin Niu and Zhiliang Tian and Lujun Li and Xiaodong Wang and Zimian Wei and Hengyue Pan and Dongsheng Li},
journal= {arXiv preprint arXiv:2301.10038},
year = {2023}
}