Tree-structured Kronecker Convolutional Networks for Semantic Segmentation

12/12/2018
by   Tianyi Wu, et al.
2

Most existing semantic segmentation methods employ atrous convolution to enlarge the receptive field of filters, but neglect partial information. To tackle this issue, we firstly propose a novel Kronecker convolution which adopts Kronecker product to expand the standard convolutional kernel for taking into account the partial feature neglected by atrous convolutions. Therefore, it can capture partial information and enlarge the receptive field of filters simultaneously without introducing extra parameters. Secondly, we propose Tree-structured Feature Aggregation (TFA) module which follows a recursive rule to expand and forms a hierarchical structure. Thus, it can naturally learn representations of multi-scale objects and encode hierarchical contextual information in complex scenes. Finally, we design Tree-structured Kronecker Convolutional Networks (TKCN) which employs Kronecker convolution and TFA module. Extensive experiments on three datasets, PASCAL VOC 2012, PASCAL-Context and Cityscapes, verify the effectiveness of our proposed approach. We make the code and the trained model publicly available at https://github.com/wutianyiRosun/TKCN.

READ FULL TEXT

page 3

page 6

page 7

research
12/12/2018

Tree-structured Kronecker Convolutional Network for Semantic Segmentation

Most existing semantic segmentation methods employ atrous convolution to...
research
11/17/2020

Multi Receptive Field Network for Semantic Segmentation

Semantic segmentation is one of the key tasks in computer vision, which ...
research
06/05/2020

Dilated Convolutions with Lateral Inhibitions for Semantic Image Segmentation

Dilated convolutions are widely used in deep semantic segmentation model...
research
04/05/2020

Anisotropic Convolutional Networks for 3D Semantic Scene Completion

As a voxel-wise labeling task, semantic scene completion (SSC) tries to ...
research
06/15/2015

ParseNet: Looking Wider to See Better

We present a technique for adding global context to deep convolutional n...
research
05/08/2023

Breaking Through the Haze: An Advanced Non-Homogeneous Dehazing Method based on Fast Fourier Convolution and ConvNeXt

Haze usually leads to deteriorated images with low contrast, color shift...
research
10/12/2021

SDWNet: A Straight Dilated Network with Wavelet Transformation for Image Deblurring

Image deblurring is a classical computer vision problem that aims to rec...

Please sign up or login with your details

Forgot password? Click here to reset