Pooling Revisited: Your Receptive Field is Suboptimal

The size and shape of the receptive field determine how the network aggregates local information and affect the overall performance of a model considerably. Many components in a neural network, such as kernel sizes and strides for convolution and pooling operations, influence the configuration of a...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Dong-Hwan Jang, Chu, Sanghyeok, Kim, Joonhyuk, Han, Bohyung
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 29.06.2022
Subjects
Artificial neural networks
Computing costs
Feature maps
Image classification
Image segmentation
Machine learning
Modules
Neural networks
Shape optimization
Online AccessGet full text

Cover

More Information
Summary:The size and shape of the receptive field determine how the network aggregates local information and affect the overall performance of a model considerably. Many components in a neural network, such as kernel sizes and strides for convolution and pooling operations, influence the configuration of a receptive field. However, they still rely on hyperparameters, and the receptive fields of existing models result in suboptimal shapes and sizes. Hence, we propose a simple yet effective Dynamically Optimized Pooling operation, referred to as DynOPool, which optimizes the scale factors of feature maps end-to-end by learning the desirable size and shape of its receptive field in each layer. Any kind of resizing modules in a deep neural network can be replaced by the operations with DynOPool at a minimal cost. Also, DynOPool controls the complexity of a model by introducing an additional loss term that constrains computational cost. Our experiments show that the models equipped with the proposed learnable resizing module outperform the baseline networks on multiple datasets in image classification and semantic segmentation.
ISSN:2331-8422