Progressive Meta-Pooling Learning for Lightweight Image Classification Model

01/24/2023
by   Peijie Dong, et al.
0

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%.

READ FULL TEXT
research
05/30/2022

Pooling Revisited: Your Receptive Field is Suboptimal

The size and shape of the receptive field determine how the network aggr...
research
03/17/2021

Meta-learning of Pooling Layers for Character Recognition

In convolutional neural network-based character recognition, pooling lay...
research
11/02/2020

Receptive Field Size Optimization with Continuous Time Pooling

The pooling operation is a cornerstone element of convolutional neural n...
research
11/01/2021

AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling

Pooling layers are essential building blocks of Convolutional Neural Net...
research
06/12/2019

DeepSquare: Boosting the Learning Power of Deep Convolutional Neural Networks with Elementwise Square Operators

Modern neural network modules which can significantly enhance the learni...
research
06/23/2020

Density-embedding layers: a general framework for adaptive receptive fields

The effectiveness and performance of artificial neural networks, particu...
research
02/10/2022

Deep Learning in Random Neural Fields: Numerical Experiments via Neural Tangent Kernel

A biological neural network in the cortex forms a neural field. Neurons ...

Please sign up or login with your details

Forgot password? Click here to reset