arrow
返回

Event-Based Semantic Segmentation With Posterior Attention

delete2023-01-01
delete12
PRE
AI
Z
Zexi Jia
K
Kaichao You
W
Weihua He *
Y
Yang Tian
Y
Yongxiang Feng
Y
Yaoyuan Wang
X
Xu Jia
Y
Yihang Lou
J
Jingyi Zhang
G
Guoqi Li
Z
Ziyang Zhang *
DOI:10.1109/TIP.2023.3249579delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
In the past years, attention-based Transformers have swept across the field of computer vision, starting a new stage of backbones in semantic segmentation. Nevertheless, semantic segmentation under poor light conditions remains an open problem. Moreover, most papers about semantic segmentation work on images produced by commodity frame-based cameras with a limited framerate, hindering their deployment to auto-driving systems that require instant perception and response at milliseconds. An event camera is a new sensor that generates event data at microseconds and can work in poor light conditions with a high dynamic range. It looks promising to leverage event cameras to enable perception where commodity cameras are incompetent, but algorithms for event data are far from mature. Pioneering researchers stack event data as frames so that event-based segmentation is converted to frame-based segmentation, but characteristics of event data are not explored. Noticing that event data naturally highlight moving objects, we propose a posterior attention module that adjusts the standard attention by the prior knowledge provided by event data. The posterior attention module can be readily plugged into many segmentation backbones. Plugging the posterior attention module into a recently proposed SegFormer network, we get EvSegFormer (the event-based version of SegFormer) with state-of-the-art performance in two datasets (MVSEC and DDD-17) collected for event-based segmentation. Code is available at https://github.com/zexiJia/EvSegFormer to facilitate research on event-based vision.
Keyword:
Cameras
Semantic segmentation
Transformers
Task analysis
Semantics
Computer architecture
Standards
Image segmentation
event camera
attention mechanism

期刊

IEEE Transactions on Image Processing 封面图
IEEE Transactions on Image Processing
IF:
13.7
论文数:
1.0W
被引数:
8.4W

机构

H
huawei technologies
学者数:
3.3K
论文数: 2.9K
被引数: 1
T
tsinghua university
学者数:
11.9W
论文数: 10.0W
被引数: 137
P
peking university
学者数:
11.9W
论文数: 8.7W
被引数: 146
D
Dalian University of Technology
学者数:
6.0W
论文数: 4.4W
被引数: 5.5W
C
chinese academy of sciences
学者数:
56.7W
论文数: 45.0W
被引数: 704
学者 查看更多机构
引用论文

引用论文

The Infrared Spectra of First Transition Series Metal(II) Complexes of Picolinic AcidN-Oxide
err2006-12-05
err0
PREAI
errThomas P. E. Auf der Heyde; Craig S. Green; Alan T. Hutton; David A. Thornton
err分享
err收藏
err分享
err收藏
Transformers in Vision: A Survey视觉中的变形金刚: 一项调查
err2022-09-13
err1.1K
errOAAI
errKhan, Salman; Naseer, Muzammal; Hayat, Munawar; Zamir, Syed Waqas; Khan, Fahad Shahbaz; Shah, Mubarak
err分享
err收藏
Front and Back Illuminated Dynamic and Active Pixel Vision Sensors Comparison
err2018-05-01
err93
errOAAI
errTaverni, Gemma; Moeys, Diederik Paul; Li, Chenghan; Cavaco, Celso; Motsnyi, Vasyl; Bello, David San Segundo; Delbruck, Tobi
err分享
err收藏
学者 查看更多内容