Filters








10 Hits in 1.2 sec

SPGNet: Semantic Prediction Guidance for Scene Parsing [article]

Bowen Cheng and Liang-Chieh Chen and Yunchao Wei and Yukun Zhu and Zilong Huang and Jinjun Xiong and Thomas Huang and Wen-Mei Hwu and Honghui Shi
2019 arXiv   pre-print
In this work, we propose a Semantic Prediction Guidance (SPG) module which learns to re-weight the local features through the guidance from pixel-wise semantic prediction.  ...  Multi-scale context module and single-stage encoder-decoder structure are commonly employed for semantic segmentation.  ...  Methods Overall Architecture Our SPGNet stacks multiple stages, where earlier decoder output is fed into a semantic prediction guidance (SPG) module (detailed in Sec 3.4) to generate input feature for  ... 
arXiv:1908.09798v1 fatcat:jh645mnoyve7ji3mofwuur2sue

Semantic Flow for Fast and Accurate Scene Parsing [article]

Xiangtai Li, Ansheng You, Zhen Zhu, Houlong Zhao, Maoke Yang, Kuiyuan Yang, Yunhai Tong
2021 arXiv   pre-print
In this paper, we focus on designing effective method for fast and accurate scene parsing.  ...  Inspired by the Optical Flow for motion alignment between adjacent video frames, we propose a Flow Alignment Module (FAM) to learn Semantic Flow between feature maps of adjacent levels, and broadcast high-level  ...  Related Work For scene parsing, there are mainly two paradigms for high-resolution semantic map prediction.  ... 
arXiv:2002.10120v3 fatcat:6qkc3albi5crnnpp6sxtouhywm

GSTO: Gated Scale-Transfer Operation for Multi-Scale Feature Learning in Pixel Labeling [article]

Zhuoying Wang and Yongtao Wang and Zhi Tang and Yangyan Li and Ying Chen and Haibin Ling and Weisi Lin
2020 arXiv   pre-print
and other benchmarks for semantic segmentation including Cityscapes, LIP and Pascal Context, with negligible extra computational cost.  ...  Existing CNN-based methods for pixel labeling heavily depend on multi-scale features to meet the requirements of both semantic comprehension and detail preservation.  ...  In 2017 IEEE Confer- guidance for scene parsing.  ... 
arXiv:2005.13363v2 fatcat:qsvle64qojfmvjjinb4t3rkyme

Image Segmentation Using Deep Learning: A Survey [article]

Shervin Minaee, Yuri Boykov, Fatih Porikli, Antonio Plaza, Nasser Kehtarnavaz, Demetri Terzopoulos
2020 arXiv   pre-print
In this survey, we provide a comprehensive review of the literature at the time of this writing, covering a broad spectrum of pioneering works for semantic and instance-level segmentation, including fully  ...  Various algorithms for image segmentation have been developed in the literature.  ...  ACKNOWLEDGMENTS The authors would like to thank Tsung-Yi Lin from Google Brain, and Jingdong Wang and Yuhui Yuan from Microsoft Research Asia, for reviewing this work, and providing very helpful comments  ... 
arXiv:2001.05566v5 fatcat:wiep26nijncwxjojxbzrqoonti

Global Aggregation then Local Distribution for Scene Parsing [article]

Xiangtai Li, Li Zhang, Guangliang Cheng, Kuiyuan Yang, Yunhai Tong, Xiatian Zhu, Tao Xiang
2021 arXiv   pre-print
Modelling long-range contextual relationships is critical for pixel-wise prediction tasks such as semantic segmentation.  ...  objects), which are very much cared for the semantic segmentation task.  ...  ACKNOWLEDGMENT We gratefully acknowledge the support of Sensetime Research for providing the computing resources in carrying out this research.  ... 
arXiv:2107.13154v1 fatcat:bven5ulbrzctbht5ms5tiyv7hy

Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis [article]

Mang Tik Chiu, Xingqian Xu, Yunchao Wei, Zilong Huang, Alexander Schwing, Robert Brunner, Hrant Khachatrian, Hovnatan Karapetyan, Ivan Dozier, Greg Rose, David Wilson, Adrian Tudor, Naira Hovakimyan (+1 others)
2020 arXiv   pre-print
To encourage research in computer vision for agriculture, we present Agriculture-Vision: a large-scale aerial farmland image dataset for semantic segmentation of agricultural patterns.  ...  As a pilot study of aerial agricultural semantic segmentation, we perform comprehensive experiments using popular semantic segmentation models; we also propose an effective model designed for aerial agricultural  ...  For example, SPGNet [8] proposes a Semantic Prediction Guidance (SPG) module which learns to re-weight the local features through the guidance from pixel-wise semantic prediction, and [26] proposes  ... 
arXiv:2001.01306v2 fatcat:ccjqweniofafxhjclvt4ourlam

Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis

Mang Tik Chiu, Xingqian Xu, Yunchao Wei, Zilong Huang, Alexander G. Schwing, Robert Brunner, Hrant Khachatrian, Hovnatan Karapetyan, Ivan Dozier, Greg Rose, David Wilson, Adrian Tudor (+3 others)
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
For example, semantic segmentation of aerial farmland images requires inference over extremely large-size images with extreme annotation sparsity.  ...  For more information on our database and other related efforts in Agriculture-Vision, please visit our CVPR 2020 workshop and challenge website https://www.agriculture-vision.com.  ...  For example, SPGNet [8] proposes a Semantic Prediction Guidance (SPG) module which learns to re-weight the local features through the guidance from pixel-wise semantic prediction, and [26] proposes  ... 
doi:10.1109/cvpr42600.2020.00290 dblp:conf/cvpr/ChiuXWHSBKKDRWT20 fatcat:2so4vabbrnfvpmfme7qt5qzz6i

AlignSeg: Feature-Aligned Segmentation Networks [article]

Zilong Huang and Yunchao Wei and Xinggang Wang and Wenyu Liu and Thomas S. Huang and Humphrey Shi
2021 arXiv   pre-print
Aggregating features in terms of different convolutional blocks or contextual embeddings has been proven to be an effective way to strengthen feature representations for semantic segmentation.  ...  contextual embeddings in hand, AlignCM enables each pixel to choose private custom contextual information in an adaptive manner, making the contextual embeddings aligned better to provide appropriate guidance  ...  Aligned Context Modeling Contextual information can provide rich semantic guidance for overall scene images, thus rectifying misclassification and inconsistent parsing results.  ... 
arXiv:2003.00872v2 fatcat:y4r56cz7yfbovccfkojlc7mis4

Edge Guided Context Aggregation Network for Semantic Segmentation of Remote Sensing Imagery

Zhiqiang Liu, Jiaojiao Li, Rui Song, Chaoxiong Wu, Wei Liu, Zan Li, Yunsong Li
2022 Remote Sensing  
In this paper, a novel edge guided context aggregation network (EGCAN) is proposed for the semantic segmentation of RSI. The Unet is employed as backbone.  ...  Meanwhile, an edge guided context aggregation branch and minority categories extraction branch are designed for a comprehensive enhancement of semantic modeling.  ...  (DeepLabv3+) [40] , a deep convolutional encoder-decoder architecture for image segmentation (SegNet) [18] , and semantic prediction guidance for scene parsing (SPGNet) [41] , established skip-connection  ... 
doi:10.3390/rs14061353 fatcat:6m3vdsrvkreulohrzs63g34gie

Table of Contents

2019 2019 IEEE/CVF International Conference on Computer Vision (ICCV)  
Prediction Guidance for Scene Parsing 5217 Bowen Cheng (UIUC), Liang-Chieh Chen (Google Inc.), Yunchao Wei (UIUC), Yukun Zhu (Google Inc.), Zilong Huang (Huazhong Univ. of Science and Technology),  ...  University), and Kris Kitani (CMU) SSF-DAN: Separated Semantic Feature Based Domain Adaptation Network for Semantic Segmentation 982 Liang Du (Fudan University), Jingang Scene Understanding End-to-End  ... 
doi:10.1109/iccv.2019.00004 fatcat:5aouo4scprc75c7zetsimylj2y