31,924 Hits in 4.8 sec

CGNet: A Light-weight Context Guided Network for Semantic Segmentation [article]

Tianyi Wu, Sheng Tang, Rui Zhang, Yongdong Zhang
2019 arXiv   pre-print
the inherent characteristic of semantic segmentation.  ...  To tackle this problem, we propose a novel Context Guided Network (CGNet), which is a light-weight and efficient network for semantic segmentation.  ...  Inception unit [30] is proposed to approximate a sparse structure and process multi-scale visual information for image classification.  ... 
arXiv:1811.08201v2 fatcat:5tmywuuk7fbm7potodwpjplvgy

CloudAttention: Efficient Multi-Scale Attention Scheme For 3D Point Cloud Learning [article]

Mahdi Saleh, Yige Wang, Nassir Navab, Benjamin Busam, Federico Tombari
2022 arXiv   pre-print
Finally, to mitigate the non-heterogeneity of point clouds, we propose an efficient Multi-Scale Tokenization (MST), which extracts scale-invariant tokens for attention operations.  ...  Spatial operations on large-scale point clouds, stored as sparse data, require extra cost. Attracted by the success of transformers, researchers are using multi-head attention for vision tasks.  ...  Semantic Scene Segmentation In this experiment, we evaluate our network performance for semantic scene segmentation.  ... 
arXiv:2208.00524v1 fatcat:26vbun6ynbdgvikbwdsnypeu7u

BCS-Net: Boundary, Context and Semantic for Automatic COVID-19 Lung Infection Segmentation from CT Images [article]

Runmin Cong, Haowei Yang, Qiuping Jiang, Wei Gao, Haisheng Li, Cong Wang, Yao Zhao, Sam Kwong
2022 arXiv   pre-print
Besides, a semantic guidance (SG) unit generates the semantic guidance map to refine the decoder features by aggregating multi-scale high-level features at the intermediate resolution.  ...  To this end, in this paper, we propose a novel network for automatic COVID-19 lung infection segmentation from CT images, named BCS-Net, which considers the boundary, context, and semantic attributes.  ...  Considering the importance of high-level semantic information for suppressing irrelevant background interference, we design a Semantic Guidance (SG) unit to aggregate multi-scale high-level features and  ... 
arXiv:2207.08114v1 fatcat:cir6ov7ekfbl5gwm4jmxusdhdq

Global Context Reasoning for Semantic Segmentation of 3D Point Clouds

Yanni Ma, Yulan Guo, Hao Liu, Yinjie Lei, Gongjian Wen
2020 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)  
Global contextual dependency is important for semantic segmentation of 3D point clouds.  ...  In this paper, we propose a Point Global Context Reasoning (PointGCR) module to capture global contextual information along the channel dimension.  ...  Although the fusion of context features can capture multi-scale information, they still cannot fully explore the global relationship between objects, which is important for semantic segmentation.  ... 
doi:10.1109/wacv45572.2020.9093411 dblp:conf/wacv/MaGLLW20 fatcat:jb5sjimndzegnmqpwkqiuew4ta

Salient Object Detection for Point Clouds [article]

Songlin Fan, Wei Gao, Ge Li
2022 arXiv   pre-print
To eschew this issue, we present a novel view-dependent perspective of salient objects, reasonably reflecting the most eye-catching objects in point cloud scenarios.  ...  ., super-/sub-class, bounding box, and segmentation map, which endows the brilliant generalizability and broad applicability of our dataset verifying various conjectures.  ...  the first four branches reasonably, the global semantics and multi-scale features can be obtained, respectively.  ... 
arXiv:2207.11889v1 fatcat:z3t45pmzy5colbhxpsvvmctkz4

A Multi-level Alignment Training Scheme for Video-and-Language Grounding [article]

Yubo Zhang, Feiyang Niu, Qing Ping, Govind Thattai
2022 arXiv   pre-print
Global and segment levels of video-language alignment pairs were designed, based on the information similarity ranging from high-level context to fine-grained semantics.  ...  For a pair of video and language description, their semantic relation is reflected by their encodings' similarity.  ...  The training objectives, which models global-level and segment-level alignments, are designed for the network to capture different levels of semantic connection between language and vision.  ... 
arXiv:2204.10938v2 fatcat:bp2kuuhecbhfhd3qse6rcgh3gm

Multi-Scale Remote Sensing Semantic Analysis Based on a Global Perspective

Wei Cui, Dongyou Zhang, Xin He, Meng Yao, Ziwei Wang, Yuanjie Hao, Jie Li, Weijie Wu, Wenqi Cui, Jiejun Huang
2019 ISPRS International Journal of Geo-Information  
field and more contextual semantic information for small-scale image caption so as to play the role of global perspective, thereby enabling the accurate identification of small-scale samples with the  ...  To address this problem, we propose a multi-scale semantic long short-term memory network (MS-LSTM). The remote sensing images are paired into image patches with different spatial scales.  ...  We propose the above multi-scale segmentation and matching principles for two main reasons: a) As a geographical unit with a single function and category, the block has classification stability for all  ... 
doi:10.3390/ijgi8090417 fatcat:qcku56qmereynbni2czfhi25na

Dual Attention Feature Fusion and Adaptive Context for Accurate Segmentation of Very High-Resolution Remote Sensing Images

Hao Shi, Jiahe Fan, Yupei Wang, Liang Chen
2021 Remote Sensing  
However, previous methods fail to generate fine segmentation results, especially for the object boundary pixels.  ...  Land cover classification of high-resolution remote sensing images aims to obtain pixel-level land cover understanding, which is often modeled as semantic segmentation of remote sensing images.  ...  Although the existing multi-scale feature fusion mechanism is a reasonable solution, the improvement is limited by the large semantic gap among the multi-level features.  ... 
doi:10.3390/rs13183715 fatcat:k2m2lwgik5e65kmvfphbw3fify

DNS: A multi-scale deconvolution semantic segmentation network for joint detection and segmentation

Ning Feng, Le Dong, Qianni Zhang, Ning Zhang, Xi Wu, Jianwen Chen, W. Anggono
2019 MATEC Web of Conferences  
To this goal, down-scale and up-scale streams are utilized to combine the multi-scale features for the final detection and segmentation task.  ...  In this paper, we introduce a single semantic segmentation network, called DNS, for joint object detection and segmentation task.  ...  Although Multi-scale CNNs and their variants have made striking success for modelling the global scene structure for an image, they are limited in labelling fine-grained local structures like pixels and  ... 
doi:10.1051/matecconf/201927702005 fatcat:y4oyemcmhfb3pj7hoko4yybe5a

Global River Monitoring Using Semantic Fusion Networks

Zhihao Wei, Kebin Jia, Xiaowei Jia, Ankush Khandelwal, Vipin Kumar
2020 Water  
segment the RSIR in global scale.  ...  Aiming at better water area classification using semantic information, this paper presents a segmentation method for global river monitoring based on semantic clustering and semantic fusion.  ...  Most importantly, we proposed a framework for solving the segmentation challenge for various types of RSIR at a global scale.  ... 
doi:10.3390/w12082258 fatcat:6rj7a6ow4rezbmxuaem6o5n26u

3D Recurrent Neural Networks with Context Fusion for Point Cloud Semantic Segmentation [chapter]

Xiaoqing Ye, Jiamao Li, Hexiao Huang, Liang Du, Xiaolin Zhang
2018 Lecture Notes in Computer Science  
In this paper, a novel end-to-end approach for unstructured point cloud semantic segmentation, named 3P-RNN, is proposed to exploit the inherent contextual features.  ...  Semantic segmentation of 3D unstructured point clouds remains an open research problem.  ...  Though simple, it is more efficient than multi-scale input context aggregation in [22, 23] because of the non-parametric pooling units.  ... 
doi:10.1007/978-3-030-01234-2_25 fatcat:ytdqpwgz6zg5zcra5uinl3ybce


Y. Lyu, G. Vosselman, G.-S. Xia, M. Y. Yang
2021 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Semantic segmentation for aerial platforms has been one of the fundamental scene understanding task for the earth observation.  ...  In order to tackle the scale variation issue, in this paper, we propose the novel bidirectional multi-scale attention networks, which fuse features from multiple scales bidirectionally for more adaptive  ...  In order to handle the multi-scale problem for the semantic segmentation, a number of deep neural networks have been designed. Multi-scale feature fusion.  ... 
doi:10.5194/isprs-annals-v-2-2021-75-2021 fatcat:a7o6wkisybc2xmjzfwyglyncfu

Contextual-Relation Consistent Domain Adaptation for Semantic Segmentation [article]

Jiaxing Huang, Shijian Lu, Dayan Guan, Xiaobing Zhang
2020 arXiv   pre-print
Recent advances in unsupervised domain adaptation for semantic segmentation have shown great potentials to relieve the demand of expensive per-pixel annotations.  ...  segmentation performance as compared with state-of-the-art methods.  ...  [19] first applies adversarial learning for UDA based semantic segmentation by aligning feature space at global scale.  ... 
arXiv:2007.02424v2 fatcat:kby6leqi2zdkrniapzwrtnlxny

High-Resolution Remote Sensing Image Segmentation Framework Based on Attention Mechanism and Adaptive Weighting

Yifan Liu, Qigang Zhu, Feng Cao, Junke Chen, Gang Lu
2021 ISPRS International Journal of Geo-Information  
Semantic segmentation has been widely used in the basic task of extracting information from images.  ...  In this paper, an Adaptive Multi-Scale Module (AMSM) and Adaptive Fuse Module (AFM) are proposed to solve these two problems.  ...  In particular, on behalf of all the authors, I would like to thank Zhang Shuaishuai again for vividly providing me with ideas for revising the paper and replying to the reviewers' opinions during the review  ... 
doi:10.3390/ijgi10040241 fatcat:wqkht2oavzesngpnlpgrhjh75y

HRCNet: High-Resolution Context Extraction Network for Semantic Segmentation of Remote Sensing Images

Zhiyong Xu, Weicun Zhang, Tianxiang Zhang, Jiangyun Li
2020 Remote Sensing  
Moreover, the imbalance of category scale and uncertain boundary information meanwhile exists in RSIs, which also brings a challenging problem to the semantic segmentation task.  ...  Conventional convolutional neural network (CNN)-based semantic segmentation methods are likely to lose the spatial information in the feature extraction stage and usually pay little attention to global  ...  Acknowledgments: The authors thank ISPRS for providing the Potsdam and Vaihingen datasets. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/rs13010071 fatcat:z4dhudkqrncmnd35b4tcx7arga
« Previous Showing results 1 — 15 out of 31,924 results