Disentangled convolution for optimizing receptive field

Takumi Kobayashi

doi:10.1016/j.patrec.2023.03.029

Disentangled convolution for optimizing receptive field

2023-05-01

3

PRE

AI

T

Takumi Kobayashi *

DOI：10.1016/j.patrec.2023.03.029

原文链接

原文求助

摘要

En 中文

Convolutional neural network (CNN) is one of the primary techniques for high-performance image recognition. The convolution operation with small-sized filters is a key ingredient of CNN and the receptive field of the whole CNN is enlarged by stacking lots of convolution layers. The convolution layer, however, is problematic in terms of the receptive field. It provides fixed small receptive field due to the fixed filter size in convolution, which requires us to manually control it in advance. Besides, the larger-sized convolution filters significantly increase computation cost. Thus, in this study, we propose a method to adaptively tune the receptive field of the convolution operation in an end-to-end manner as well as to enlarge the receptive field in a low computation cost. Based on the biological studies and scale-space theory, we can disentangle convolution operation into Gaussian envelope filtering for smoothing and derivative-related filtering, both of which are heterogeneously parameterized. Those two types of filters are jointly optimized in the end-to-end CNN training and the receptive field of the convolution is adequately optimized via learning the Gaussian envelope with a low extra computation cost. The experimental results on image classification tasks demonstrate that the proposed method effectively enlar ges receptive field to improve performance.

Keyword:

Convolution

Receptive field

Gaussian smoothing

CNN

Image classification

Disentangled convolution for optimizing receptive field

摘要

期刊

机构

引用论文