2023/01/24 by Peijie Dong, Dong, Peijie, Xin Niu +13
Computer Science · Engineering · Mathematics · #Algorithm #Artificial intelligence #Artificial neural network #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Convolution (computer science) #Convolutional neural network #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Field (mathematics) #Indoor and Outdoor Localization Technologies #Machine Learning and ELM #Machine learning #Mathematics #Parameterized complexity #Pattern recognition (psychology) #Pooling #Receptive field
paper · pdf · doi:10.48550/arxiv.2301.10038
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2023/01/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04
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%.