Filters








24,750 Hits in 5.4 sec

End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion [article]

Chao Shang, Yun Tang, Jing Huang, Jinbo Bi, Xiaodong He, Bowen Zhou
2018 arXiv   pre-print
In this work, we propose a novel end-to-end Structure-Aware Convolutional Network (SACN) that takes the benefit of GCN and ConvE together.  ...  Knowledge graph embedding has been an active research topic for knowledge base completion, with progressive improvement from the initial TransE, TransH, DistMult et al to the current state-of-the-art ConvE  ...  Acknowledgements This work was partially supported by NSF grants CCF-1514357 and IIS-1718738, as well as NIH grants R01DA037349 and K02DA043063 to Jinbo Bi.  ... 
arXiv:1811.04441v2 fatcat:7hdkf7jxsferjpeo2d7ddwjtmm

End-to-End Structure-Aware Convolutional Networks for Knowledge Base Completion

Chao Shang, Yun Tang, Jing Huang, Jinbo Bi, Xiaodong He, Bowen Zhou
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Knowledge graph embedding has been an active research topic for knowledge base completion, with progressive improvement from the initial TransE, TransH, DistMult et al to the current state-of-the-art ConvE  ...  In this work, we propose a novel end-to-end StructureAware Convolutional Network (SACN) that takes the benefit of GCN and ConvE together.  ...  Acknowledgements This work was partially supported by NSF grants CCF-1514357 and IIS-1718738, as well as NIH grants R01DA037349 and K02DA043063 to Jinbo Bi.  ... 
doi:10.1609/aaai.v33i01.33013060 fatcat:acgej7ucqrflxebzazwvzpcwju

EdgeStereo: An Effective Multi-Task Learning Network for Stereo Matching and Edge Detection [article]

Xiao Song, Xu Zhao, Liangji Fang, Hanwen Hu
2019 arXiv   pre-print
Recently, leveraging on the development of end-to-end convolutional neural networks (CNNs), deep stereo matching networks have achieved remarkable performance far exceeding traditional approaches.  ...  In addition, we design a compact module called residual pyramid to replace the commonly-used multi-stage cascaded structures or 3-D convolution based regularization modules in current stereo matching networks  ...  Acknowledgements We would like to thank Guorun Yang for helpful discussions and suggestions. This research is supported by the funding from NSFC programs (61673269, 61273285, U1764264).  ... 
arXiv:1903.01700v2 fatcat:st4jqj5gmzdjljh623d2xpmiwq

PPCD-GAN: Progressive Pruning and Class-Aware Distillation for Large-Scale Conditional GANs Compression [article]

Duc Minh Vo, Akihiro Sugimoto, Hideki Nakayama
2022 arXiv   pre-print
To this end, we propose a gradually shrinking GAN (PPCD-GAN) by introducing progressive pruning residual block (PP-Res) and class-aware distillation.  ...  The PP-Res is an extension of the conventional residual block where each convolutional layer is followed by a learnable mask layer to progressively prune network parameters as training proceeds.  ...  Tiny-GAN is a manually designed network based on the Big-GAN [1] architecture and replaces the standard convolutional layer with depthwise separable convolution.  ... 
arXiv:2203.08456v1 fatcat:oe2dyjbzdjd57jsoersxalloqa

AutoShrink: A Topology-Aware NAS for Discovering Efficient Neural Architecture

Tunhou Zhang, Hsin-Pai Cheng, Zhenwen Li, Feng Yan, Chengyu Huang, Hai Li, Yiran Chen
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
To address these problems, we propose AutoShrink, a topology-aware Neural Architecture Search (NAS) for searching efficient building blocks of neural architectures.  ...  Our method is node-based and thus can learn flexible network patterns in cell structures within a topological search space.  ...  We also thank USTC for the support of computing.  ... 
doi:10.1609/aaai.v34i04.6163 fatcat:3ugu37ojina3fnjedeehvgcwwi

Learning Frequency-aware Dynamic Network for Efficient Super-Resolution [article]

Wenbin Xie, Dehua Song, Chang Xu, Chunjing Xu, Hui Zhang, Yunhe Wang
2021 arXiv   pre-print
In addition, we embed predictors into the proposed dynamic network to end-to-end fine-tune the handcrafted frequency-aware masks.  ...  To this end, this paper explores a novel frequency-aware dynamic network for dividing the input into multiple parts according to its coefficients in the discrete cosine transform (DCT) domain.  ...  It motivates us to explore a more efficient SR method according to frequencies of the input instance. To this end, this paper proposes a novel frequency-aware dynamic convolutional network (FADN).  ... 
arXiv:2103.08357v2 fatcat:vnwyt7rdvnbk7gvf4zm7nnleou

AutoShrink: A Topology-aware NAS for Discovering Efficient Neural Architecture [article]

Tunhou Zhang, Hsin-Pai Cheng, Zhenwen Li, Feng Yan, Chengyu Huang, Hai Li, Yiran Chen
2019 arXiv   pre-print
To address these problems, we propose AutoShrink, a topology-aware Neural Architecture Search(NAS) for searching efficient building blocks of neural architectures.  ...  Our method is node-based and thus can learn flexible network patterns in cell structures within a topological search space.  ...  We also thank USTC for the support of computing.  ... 
arXiv:1911.09251v1 fatcat:vs5eqiffvves7mk7inp3ggbmcm

Residual 3D Scene Flow Learning with Context-Aware Feature Extraction [article]

Guangming Wang, Yunzhe Hu, Xinrui Wu, Hesheng Wang
2022 arXiv   pre-print
To solve the first problem, a novel context-aware set convolution layer is proposed in this paper to exploit contextual structure information of Euclidean space and learn soft aggregation weights for local  ...  The context-aware set convolution layer is incorporated in a context-aware point feature pyramid module of 3D point clouds for scene flow estimation.  ...  These methods predict scene flow using only 3D coordinates as inputs in an end-to-end fashion and do not require any prior knowledge of scene structure.  ... 
arXiv:2109.04685v2 fatcat:mjpq6bvrhndftd7hhbca7e7qva

Graph Attention Networks with Local Structure Awareness for Knowledge Graph Completion

Kexi Ji, Bei Hui, Guangchun Luo
2020 IEEE Access  
Therefore, for the comprehensive usage of such structural information in knowledge graph completion, we propose local structure-aware graph attention networks (LSA-GAT).  ...  CONCLUSION AND FUTURE WORK In this paper, we propose a local structure aware model called LSA-GAT for knowledge graph completion.  ... 
doi:10.1109/access.2020.3044343 fatcat:coa2taekdjcf7mggythnxag664

A Bayesian Driver Agent Model for Autonomous Vehicles System Based on Knowledge-Aware and Real-Time Data

Jichang Ma, Hui Xie, Kang Song, Hao Liu
2021 Sensors  
Different from the end-to-end learning method and traditional rule-based methods, our approach breaks the driving system up into a scene recognition module and a decision inference module.  ...  A key research area in autonomous driving is how to model the driver's decision-making behavior, due to the fact it is significant for a self-driving vehicles considering their traffic safety and efficiency  ...  Conflicts of Interest: There are no conflict of interest to declare.  ... 
doi:10.3390/s21020331 pmid:33418987 fatcat:4wcdmmr32fcajfyl56calwb2vm

Foreground-aware Image Inpainting [article]

Wei Xiong, Jiahui Yu, Zhe Lin, Jimei Yang, Xin Lu, Connelly Barnes and Jiebo Luo
2019 arXiv   pre-print
To address the problem, we propose a foreground-aware image inpainting system that explicitly disentangles structure inference and content completion.  ...  These scenarios, however, are very important in practice, especially for applications such as the removal of distracting objects.  ...  These methods typically train a convolutional neural network as a mapping function from a corrupted image to a completed one endto-end.  ... 
arXiv:1901.05945v3 fatcat:tn6kcl2ihbblli3nbaja7bc5ue

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 1090-1100 Integrating Neural Networks Into the Blind Deblurring Framework to Com- pete With the End-to-End Learning-Based Methods.  ...  ., +, TIP 2020 1725-1737 Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression. Li, M., +, TIP 2020 5900-5911 End-to-End Optimized ROI Image Compression.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis [article]

Ben Fei, Weidong Yang, Wenming Chen, Zhijun Li, Yikang Li, Tao Ma, Xing Hu, Lipeng Ma
2022 arXiv   pre-print
Therefore, this work aims to conduct a comprehensive survey on various methods, including point-based, convolution-based, graph-based, and generative model-based approaches, etc.  ...  However, the quality of completed point clouds is still needed to be further enhanced to meet the practical utilization.  ...  [92] proposed an end-to-end generative adversarial network-based dense point cloud completion architecture (DPCG-Net).  ... 
arXiv:2203.03311v2 fatcat:e2kvryolufearetp4ujlw2gwwy

Improving Graph Convolutional Networks Based on Relation-aware Attention for End-to-End Relation Extraction

Yin Hong, Yanxia Liu, Suizhu Yang, Kaiwen Zhang, Aiqing Wen, Jianjun Hu
2020 IEEE Access  
In this paper, we present a novel end-to-end neural model based on graph convolutional networks (GCN) for jointly extracting entities and relations between them.  ...  To consider the complete interaction between entities and relations, we propose a novel relation-aware attention mechanism to obtain the relation representation between two entity spans.  ...  ACKNOWLEDGMENT The authors thank Xiang Ren for dataset details.  ... 
doi:10.1109/access.2020.2980859 fatcat:ueeiv74fmndkpgthcofndyktta

Foreground-Aware Image Inpainting

Wei Xiong, Jiahui Yu, Zhe Lin, Jimei Yang, Xin Lu, Connelly Barnes, Jiebo Luo
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
To address the problem, we propose a foreground-aware image inpainting system that explicitly disentangles structure inference and content completion.  ...  These scenarios, however, are very important in practice, especially for applications such as the removal of distracting objects.  ...  These methods typically train a convolutional neural network as a mapping function from a corrupted image to a completed one endto-end.  ... 
doi:10.1109/cvpr.2019.00599 dblp:conf/cvpr/XiongYLYLBL19 fatcat:rvrnnlrygzeqzldezk7uihdz7e
« Previous Showing results 1 — 15 out of 24,750 results