Using Features Specifically: An Efficient Network for Scene Segmentation Based on Dedicated Attention Mechanisms
Semantic segmentation is a challenging task in computer vision, which requires both context information and rich spatial detail. To this end, most methods introduce low-level features for spatial detail. However, low-level features lack global information. Too much low-level features will disturb th...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9274395/ |
id |
doaj-f3e97379c49d4847b4229556b41341c6 |
---|---|
record_format |
Article |
spelling |
doaj-f3e97379c49d4847b4229556b41341c62021-03-30T03:29:29ZengIEEEIEEE Access2169-35362020-01-01821794721795610.1109/ACCESS.2020.30417489274395Using Features Specifically: An Efficient Network for Scene Segmentation Based on Dedicated Attention MechanismsZhiqiang Xiong0https://orcid.org/0000-0002-7389-1110Zhicheng Wang1Jie Li2Zhaohui Yu3https://orcid.org/0000-0002-8230-1899Xi Gu4CAD Research Center, College of Electronic and Information Engineering, Tongji University, Shanghai, ChinaCAD Research Center, College of Electronic and Information Engineering, Tongji University, Shanghai, ChinaShanghai Aerospace Electronic Technology Institute, Shanghai, ChinaCAD Research Center, College of Electronic and Information Engineering, Tongji University, Shanghai, ChinaCAD Research Center, College of Electronic and Information Engineering, Tongji University, Shanghai, ChinaSemantic segmentation is a challenging task in computer vision, which requires both context information and rich spatial detail. To this end, most methods introduce low-level features for spatial detail. However, low-level features lack global information. Too much low-level features will disturb the segmentation result. In this paper, we extract low-level features guided by abstract semantic features to improve segmentation results. Specifically, we propose a Pixel-wise Attention Module (PAM) to select low-level features adaptively and a Dual Channel-wise Attention Fusion Module (DCAFM) to fuse the context information further. These two modules use the attention mechanism from a more macro perspective, which is not limited to the inter-layer feature adjustments. There are not complicated and redundant processing modules in our architecture. By using features efficiently, the complexity of the network was significantly reduced. We evaluate our approach on Cityscapes, PASCAL VOC 2012, and PASCAL Context datasets, and we achieve 82.3% Mean IoU on PASCAL VOC 2012 test dataset without pre-training on the MS-COCO dataset.https://ieeexplore.ieee.org/document/9274395/Image processingdeep neural networksemantic segmentationattention mechanism |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zhiqiang Xiong Zhicheng Wang Jie Li Zhaohui Yu Xi Gu |
spellingShingle |
Zhiqiang Xiong Zhicheng Wang Jie Li Zhaohui Yu Xi Gu Using Features Specifically: An Efficient Network for Scene Segmentation Based on Dedicated Attention Mechanisms IEEE Access Image processing deep neural network semantic segmentation attention mechanism |
author_facet |
Zhiqiang Xiong Zhicheng Wang Jie Li Zhaohui Yu Xi Gu |
author_sort |
Zhiqiang Xiong |
title |
Using Features Specifically: An Efficient Network for Scene Segmentation Based on Dedicated Attention Mechanisms |
title_short |
Using Features Specifically: An Efficient Network for Scene Segmentation Based on Dedicated Attention Mechanisms |
title_full |
Using Features Specifically: An Efficient Network for Scene Segmentation Based on Dedicated Attention Mechanisms |
title_fullStr |
Using Features Specifically: An Efficient Network for Scene Segmentation Based on Dedicated Attention Mechanisms |
title_full_unstemmed |
Using Features Specifically: An Efficient Network for Scene Segmentation Based on Dedicated Attention Mechanisms |
title_sort |
using features specifically: an efficient network for scene segmentation based on dedicated attention mechanisms |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Semantic segmentation is a challenging task in computer vision, which requires both context information and rich spatial detail. To this end, most methods introduce low-level features for spatial detail. However, low-level features lack global information. Too much low-level features will disturb the segmentation result. In this paper, we extract low-level features guided by abstract semantic features to improve segmentation results. Specifically, we propose a Pixel-wise Attention Module (PAM) to select low-level features adaptively and a Dual Channel-wise Attention Fusion Module (DCAFM) to fuse the context information further. These two modules use the attention mechanism from a more macro perspective, which is not limited to the inter-layer feature adjustments. There are not complicated and redundant processing modules in our architecture. By using features efficiently, the complexity of the network was significantly reduced. We evaluate our approach on Cityscapes, PASCAL VOC 2012, and PASCAL Context datasets, and we achieve 82.3% Mean IoU on PASCAL VOC 2012 test dataset without pre-training on the MS-COCO dataset. |
topic |
Image processing deep neural network semantic segmentation attention mechanism |
url |
https://ieeexplore.ieee.org/document/9274395/ |
work_keys_str_mv |
AT zhiqiangxiong usingfeaturesspecificallyanefficientnetworkforscenesegmentationbasedondedicatedattentionmechanisms AT zhichengwang usingfeaturesspecificallyanefficientnetworkforscenesegmentationbasedondedicatedattentionmechanisms AT jieli usingfeaturesspecificallyanefficientnetworkforscenesegmentationbasedondedicatedattentionmechanisms AT zhaohuiyu usingfeaturesspecificallyanefficientnetworkforscenesegmentationbasedondedicatedattentionmechanisms AT xigu usingfeaturesspecificallyanefficientnetworkforscenesegmentationbasedondedicatedattentionmechanisms |
_version_ |
1724183473692868608 |