Progressive Meta-Pooling Learning for Lightweight Image Classification Model
| Autor: | Peijie Dong, Xin Niu, Zhiliang Tian, Lujun Li, Xiaodong Wang, Zimian Wei, Hengyue Pan, Dongsheng Li |
|---|---|
| Rok vydání: | 2023 |
| Předmět: | |
| DOI: | 10.48550/arxiv.2301.10038 |
| Popis: | 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\%. Comment: 5 pages, 2 figures, ICASSP23 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|