MBNet: A Multi-Resolution Branch Network for Semantic Segmentation Of Ultra-High Resolution Images
Authors:
- 23 May 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2589-2593
Abstract
Semantic segmentation of ultra-high resolution images is more challenging than ordinary images since high-resolution images need to be cropped into patches in training due to GPU memory limitation. To solve this problem, we design a multibranch structure to deal with multi-resolution inputs, called Multi-resolution Branch Network (MBNet). MBNet takes patches of various instead of only one resolution as inputs, so it can make the extracted features pure and different from each other so as to cover the complex scenes with tremendous variation. Moreover, to make full use of the multi-branch structure, we design a zoom module. Zoom module abandons the previous L2-norm before feature concatenation but combines different features according to the learned attention, which fully releases the advantages of multi-resolution. Results on two benchmark datasets show that our method improves significantly over the previous state-of-the-art methods.Keywords
This publication has 16 references indexed in Scilit:
- Dual Attention Network for Scene Segmentation2019
- ICNet for Real-Time Semantic Segmentation on High-Resolution Images2018
- The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesionsScientific Data, 2018
- DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images2018
- Squeeze-and-Excitation Networks2018
- Non-local Neural Networks2018
- Feature Pyramid Networks for Object Detection2017
- Pyramid Scene Parsing Network2017
- RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation2017
- Deep Residual Learning for Image Recognition2016