Filters








16,848 Hits in 4.8 sec

Boundary Guided Context Aggregation for Semantic Segmentation [article]

Haoxiang Ma, Hongyu Yang, Di Huang
<span title="2021-10-27">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Based on which, a Boundary guided Context Aggregation module (BCA) improved from Non-local network is further proposed to capture long-range dependencies between the pixels in the boundary regions and  ...  The recent studies on semantic segmentation are starting to notice the significance of the boundary information, where most approaches see boundaries as the supplement of semantic details.  ...  Inspired by the success of Non-local module in modeling long-range dependency in semantic segmentation, an attention-based module is developed, i.e., Boundary guided Context Aggregation module (BCA), to  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.14587v1">arXiv:2110.14587v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gonwztvw7ffl7k5lrbjymk3en4">fatcat:gonwztvw7ffl7k5lrbjymk3en4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211102144629/https://arxiv.org/pdf/2110.14587v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d4/e0/d4e0b9c6f08155445732f4d4ffb071f55b96690b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.14587v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Dual Attention Network for Scene Segmentation [article]

Jun Fu, Jing Liu, Haijie Tian, Yong Li, Yongjun Bao, Zhiwei Fang, Hanqing Lu
<span title="2019-04-21">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Unlike previous works that capture contexts by multi-scale features fusion, we propose a Dual Attention Networks (DANet) to adaptively integrate local features with their global dependencies.  ...  Specifically, we append two types of attention modules on top of traditional dilated FCN, which model the semantic interdependencies in spatial and channel dimensions respectively.  ...  Acknowledgment This work was supported by Beijing Natural Science Foundation (4192059) and National Natural Science Foundation of China (61872366, 61472422 and 61872364).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.02983v4">arXiv:1809.02983v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6jowndquhbg3tgcuohmtuwazmu">fatcat:6jowndquhbg3tgcuohmtuwazmu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200910074457/https://arxiv.org/pdf/1809.02983v4.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d6/82/d6821b4e67afac4597792734ff3e4edf413f2780.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.02983v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Strengthen the Feature Distinguishability of Geo-object Details in the Semantic Segmentation of High-resolution Remote Sensing Images

Jie Chen, Hao Wang, Ya Guo, Geng Sun, Yi Zhang, Min Deng
<span title="">2021</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/b2n2tpw5ang73osulebz6bm4ju" style="color: black;">IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing</a> </i> &nbsp;
Deep convolutional neural network (DCNN) has become a mainstream technology in semantic segmentation due to its powerful semantic feature representation.  ...  First, the cascaded relation attention module is adopted to determine the relationship among different channels or positions.  ...  of a neural network and enhance the connection among geo objects by capturing the global long-range dependence and improve the distinguishability of features.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/jstars.2021.3053067">doi:10.1109/jstars.2021.3053067</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2rwima2ulbfkbbqxfoy6fteupm">fatcat:2rwima2ulbfkbbqxfoy6fteupm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210717181241/https://ieeexplore.ieee.org/ielx7/4609443/9314330/09329050.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e3/96/e3965d868b8933382f56b9596370b20ee90aaad9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/jstars.2021.3053067"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Hybridizing Cross-Level Contextual and Attentive Representations for Remote Sensing Imagery Semantic Segmentation

Xin Li, Feng Xu, Runliang Xia, Xin Lyu, Hongmin Gao, Yao Tong
<span title="2021-07-29">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/kay2tsbijbawliu45dnhvyvgsq" style="color: black;">Remote Sensing</a> </i> &nbsp;
Therefore, a remote sensing imagery semantic segmentation neural network, named HCANet, is proposed to generate representative and discriminative representations for dense predictions.  ...  Moreover, a hybrid representation enhancement module (HREM) is designed to fuse cross-level contextual and self-attentive representations flexibly.  ...  Non-local block helps the network capture long-range dependencies. This simple yet efficient way is of great significance in semantic segmentation performance.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs13152986">doi:10.3390/rs13152986</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/l4ap4w66nbg3pdyhfkpc5dwdsq">fatcat:l4ap4w66nbg3pdyhfkpc5dwdsq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210804214925/https://res.mdpi.com/d_attachment/remotesensing/remotesensing-13-02986/article_deploy/remotesensing-13-02986-v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9a/95/9a9547705c99d1046e60084811041f2ec5dbd97a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs13152986"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Urban Land Cover Classification of High-Resolution Aerial Imagery Using a Relation-Enhanced Multiscale Convolutional Network

Chun Liu, Doudou Zeng, Hangbin Wu, Yin Wang, Shoujun Jia, Liang Xin
<span title="2020-01-17">2020</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/kay2tsbijbawliu45dnhvyvgsq" style="color: black;">Remote Sensing</a> </i> &nbsp;
The results demonstrate that the proposed method can effectively capture long-range dependencies and improve the accuracy of land cover classification.  ...  The proposed network is used for urban land cover classification against two datasets: the ISPRS 2D semantic labelling contest of Vaihingen and an area of Shanghai of about 143 km2.  ...  We are also grateful to Akram Akbar, Shuhang Zhang, Wen Zhang, and Jin Zhao for their advice and support in experimental design.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs12020311">doi:10.3390/rs12020311</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pa4645kxzzdjzhizzynfsbjwhe">fatcat:pa4645kxzzdjzhizzynfsbjwhe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200212171051/https://res.mdpi.com/d_attachment/remotesensing/remotesensing-12-00311/article_deploy/remotesensing-12-00311-v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/69/4a/694ade15de47358c5d61491a59759294bd4bad78.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs12020311"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Multi-Attention-Network for Semantic Segmentation of Fine Resolution Remote Sensing Images [article]

Rui Li, Shunyi Zheng, Chenxi Duan, Ce Zhang, Jianlin Su, P.M. Atkinson
<span title="2020-11-23">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Third, even though the dot-product attention mechanism has been introduced and utilized in semantic segmentation to model long-range dependencies, the large time and space demands of attention impede the  ...  Second, long-range dependencies of feature maps are insufficiently explored, resulting in sub-optimal feature representations associated with each semantic class.  ...  Using the kernel attention mechanism (KAM) and channel attention mechanism (CAM) which model the long-range dependencies of positions and channels, respectively, we design an attention block to enhance  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.02130v4">arXiv:2009.02130v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/z6wwjzhkcbgiffk7oq42gzf7ku">fatcat:z6wwjzhkcbgiffk7oq42gzf7ku</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201029013846/https://arxiv.org/ftp/arxiv/papers/2009/2009.02130.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f4/ff/f4ff2a49e60cd3a3dc3111321728a7e413f16356.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.02130v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Enhancing feature fusion with spatial aggregation and channel fusion for semantic segmentation

Jie Hu, Huifang Kong, Lei Fan, Jun Zhou
<span title="2021-05-04">2021</span> <i title="Institution of Engineering and Technology (IET)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/j7d2hucrlnfzzecpjzw46furp4" style="color: black;">IET Computer Vision</a> </i> &nbsp;
Semantic segmentation is crucial to the autonomous driving, as an accurate recognition and location of the surrounding scenes can be provided for the street scenes understanding task.  ...  Many existing segmentation networks usually fuse high-level and low-level features to boost segmentation performance.  ...  IMICZ2017004 and the 111 Project BP0719039, and the computational resources used in this study are provided by the Automotive Electronics and Control Research Centre, Hefei University of Technology.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1049/cvi2.12026">doi:10.1049/cvi2.12026</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bryfeojixbhpzny5z4cepabvna">fatcat:bryfeojixbhpzny5z4cepabvna</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210716205800/https://ietresearch.onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cvi2.12026" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c3/54/c354d90444378f19b22b9139be996bdff8aac4b6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1049/cvi2.12026"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Saliency Guided Self-attention Network for Weakly and Semi-supervised Semantic Segmentation

Qi Yao, Xiaojin Gong
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
Moreover, by simply replacing the additional supervisions with partially labeled ground-truth, SGAN works effectively for semi-supervised semantic segmentation as well.  ...  INDEX TERMS Weakly and semi-supervised semantic segmentation, self-attention, saliency. XIAOJIN GONG (Member, IEEE) received the B.A. and M.A.  ...  As validated in [5] , [6] , this mechanism is able to successfully capture long-range contextual dependencies in fully-supervised semantic segmentation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2966647">doi:10.1109/access.2020.2966647</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gp2dhzvl75curawframh3tzliy">fatcat:gp2dhzvl75curawframh3tzliy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108074111/https://ieeexplore.ieee.org/ielx7/6287639/8948470/08959112.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/76/df/76dfe7c04f7df8f3e38e67132d60323adf362a29.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2966647"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Transformer Meets Convolution: A Bilateral Awareness Net-work for Semantic Segmentation of Very Fine Resolution Ur-ban Scene Images [article]

Libo Wang, Rui Li, Dongzhi Wang, Chenxi Duan, Teng Wang, Xiaoliang Meng
<span title="2021-06-23">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this manuscript, we pro-pose a bilateral awareness network (BANet) which contains a dependency path and a texture path to fully capture the long-range relationships and fine-grained details in VFR images  ...  Specif-ically, the dependency path is conducted based on the ResT, a novel Transformer backbone with memory-efficient multi-head self-attention, while the texture path is built on the stacked convo-lution  ...  Special thanks to editors and reviewers for providing valuable insight into this article.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.12413v1">arXiv:2106.12413v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4k2qyetrvvbrji7zhffc4byvcm">fatcat:4k2qyetrvvbrji7zhffc4byvcm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210625195208/https://arxiv.org/ftp/arxiv/papers/2106/2106.12413.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/13/6d/136db8b399bb8d1f74f971ae82f02d87b5395a1b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.12413v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Attention guided global enhancement and local refinement network for semantic segmentation [article]

Jiangyun Li, Sen Zha, Chen Chen, Meng Ding, Tianxiang Zhang, Hong Yu
<span title="2022-04-09">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The encoder-decoder architecture is widely used as a lightweight semantic segmentation network.  ...  Then, the two methods are integrated into a Context Fusion Block, and based on that, a novel Attention guided Global enhancement and Local refinement Network (AGLN) is elaborately designed.  ...  The self-attention mechanism is applied to capture long-range dependency since its first success in video classification [29] , and its potential has been well-explored during recent years [10] , [30  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.04363v1">arXiv:2204.04363v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/epwtjq7h3fe3ph526jmj57isqe">fatcat:epwtjq7h3fe3ph526jmj57isqe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220516083633/https://arxiv.org/pdf/2204.04363v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/5b/40/5b409e06b01da47baa1b5d4e48a9f6bfe5ad1de8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.04363v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Semantic Segmentation of Aerial Imagery via Split-Attention Networks with Disentangled Nonlocal and Edge Supervision

Cheng Zhang, Wanshou Jiang, Qing Zhao
<span title="2021-03-19">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/kay2tsbijbawliu45dnhvyvgsq" style="color: black;">Remote Sensing</a> </i> &nbsp;
In this work, we propose a new deep convolution neural network (DCNN) architecture for semantic segmentation of aerial imagery.  ...  Taking advantage of recent research, we use split-attention networks (ResNeSt) as the backbone for high-quality feature expression.  ...  Acknowledgments: The authors would like to express their gratitude to the editors and the reviewers for their constructive and helpful comments for the substantial improvement of this paper.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs13061176">doi:10.3390/rs13061176</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uvax5riha5e6ncv4xjg3a6kxxa">fatcat:uvax5riha5e6ncv4xjg3a6kxxa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210330092559/https://res.mdpi.com/d_attachment/remotesensing/remotesensing-13-01176/article_deploy/remotesensing-13-01176-v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/91/be/91be57a9ad47337a75b91be59e9c246e373053de.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs13061176"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimation [article]

Hyunyoung Jung, Eunhyeok Park, Sungjoo Yoo
<span title="2021-08-19">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We focus on incorporating implicit semantic knowledge into geometric representation enhancement and suggest two ideas: a metric learning approach that exploits the semantics-guided local geometry to optimize  ...  However, most works suffer from limited supervision of photometric consistency, especially in weak texture regions and at object boundaries.  ...  We would like to especially thank Soohyun Bae at Bobidi for his invaluable comments. This work was supported by the SNU-SK Hynix Solution Research Center (S3RC).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.08829v1">arXiv:2108.08829v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/k5bnxf3aefb4rkde77qoqxtqqm">fatcat:k5bnxf3aefb4rkde77qoqxtqqm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210909093521/https://arxiv.org/pdf/2108.08829v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/72/be/72be512a86523d929ca8b3702484277af82e45ec.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.08829v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Boundary-Aware Feature Propagation for Scene Segmentation [article]

Henghui Ding, Xudong Jiang, Ai Qun Liu, Nadia Magnenat Thalmann, Gang Wang
<span title="2019-08-31">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To this end, we first propose to learn the boundary as an additional semantic class to enable the network to be aware of the boundary layout.  ...  Without bells and whistles, our approach achieves new state-of-the-art segmentation performance on three challenging semantic segmentation datasets, i.e., PASCAL-Context, CamVid, and Cityscapes.  ...  Technological University and University of North Carolina at Chapel Hill.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.00179v1">arXiv:1909.00179v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/urenaqb2jng4bmxnwqckckwr4m">fatcat:urenaqb2jng4bmxnwqckckwr4m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930013623/https://arxiv.org/pdf/1909.00179v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/58/fe/58fee43909afe4c607bf5d77b6273c31f5d0a77f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.00179v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform [article]

Liang-Chieh Chen, Jonathan T. Barron, George Papandreou, Kevin Murphy, Alan L. Yuille
<span title="2016-06-02">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Domain transform filtering is several times faster than dense CRF inference and we show that it yields comparable semantic segmentation results, accurately capturing object boundaries.  ...  Deep convolutional neural networks (CNNs) are the backbone of state-of-art semantic image segmentation systems.  ...  Acknowledgments This work wast partly supported by ARO 62250-CS and NIH Grant 5R01EY022247-03.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1511.03328v2">arXiv:1511.03328v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bcykk4afizhm5dvtk2z3j3cnpq">fatcat:bcykk4afizhm5dvtk2z3j3cnpq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929184353/https://arxiv.org/pdf/1511.03328v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a2/b4/a2b42088b56499a20743d4f8c819168e8759a375.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1511.03328v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Multiscale Semantic Feature Optimization and Fusion Network for Building Extraction Using High-Resolution Aerial Images and LiDAR Data

Qinglie Yuan, Helmi Zulhaidi Mohd Shafri, Aidi Hizami Alias, Shaiful Jahari Hashim
<span title="2021-06-24">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/kay2tsbijbawliu45dnhvyvgsq" style="color: black;">Remote Sensing</a> </i> &nbsp;
A semantic guided spatial attention mechanism is introduced to refine shallow features and alleviate the semantic gap. Finally, hierarchical features are fused via the feature pyramid network.  ...  the proposed network can improve accuracy and achieve better performance for building extraction.  ...  As only using global spatial attention is effective for long-range dependencies, it neglects the influence of the dependence between channels.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs13132473">doi:10.3390/rs13132473</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/thupwpioxvbthn65i2q2bkxkqu">fatcat:thupwpioxvbthn65i2q2bkxkqu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210625083002/https://res.mdpi.com/d_attachment/remotesensing/remotesensing-13-02473/article_deploy/remotesensing-13-02473.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/df/71/df71451e86655c565cad3bb94c8940acef70b6f8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs13132473"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 16,848 results