Search Results for author: Wenxuan Tu

Found 10 papers, 3 papers with code

Align then Fusion: Generalized Large-scale Multi-view Clustering with Anchor Matching Correspondences

no code implementations30 May 2022 Siwei Wang, Xinwang Liu, Suyuan Liu, Jiaqi Jin, Wenxuan Tu, Xinzhong Zhu, En Zhu

Under multi-view scenarios, generating correct correspondences could be extremely difficult since anchors are not consistent in feature dimensions.

Graph Clustering

Improved Dual Correlation Reduction Network

no code implementations25 Feb 2022 Yue Liu, Sihang Zhou, Xinwang Liu, Wenxuan Tu, Xihong Yang

Deep graph clustering, which aims to reveal the underlying graph structure and divide the nodes into different clusters without human annotations, is a fundamental yet challenging task.

Graph Clustering

Highly-Efficient Incomplete Large-Scale Multi-View Clustering With Consensus Bipartite Graph

1 code implementation CVPR 2022 Siwei Wang, Xinwang Liu, Li Liu, Wenxuan Tu, Xinzhong Zhu, Jiyuan Liu, Sihang Zhou, En Zhu

Multi-view clustering has received increasing attention due to its effectiveness in fusing complementary information without manual annotations.

Incomplete multi-view clustering

Deep Graph Clustering via Dual Correlation Reduction

2 code implementations29 Dec 2021 Yue Liu, Wenxuan Tu, Sihang Zhou, Xinwang Liu, Linxuan Song, Xihong Yang, En Zhu

To address this issue, we propose a novel self-supervised deep graph clustering method termed Dual Correlation Reduction Network (DCRN) by reducing information correlation in a dual manner.

Graph Clustering

Siamese Attribute-missing Graph Auto-encoder

no code implementations9 Dec 2021 Wenxuan Tu, Sihang Zhou, Yue Liu, Xinwang Liu

First, we entangle the attribute embedding and structure embedding by introducing a siamese network structure to share the parameters learned by both processes, which allows the network training to benefit from more abundant and diverse information.

Graph Representation Learning

Foreground Object Structure Transfer for Unsupervised Domain Adaptation

no code implementations14 Sep 2021 Jieren Cheng, Le Liu, Xiangyan Tang, Wenxuan Tu, Boyi Liu, Ke Zhou, Qiaobo Da, Yue Yang

In practice, since the label of the target domain is not available, we use the clustering information of the source domain to assign pseudo labels to the target domain samples, and then according to the source domain data prior knowledge guides those positive features to maximum the inter-class distance between different classes and mimimum the intra-class distance.

Unsupervised Domain Adaptation

Multi-view Clustering with Deep Matrix Factorization and Global Graph Refinement

no code implementations1 May 2021 Chen Zhang, Siwei Wang, Wenxuan Tu, Pei Zhang, Xinwang Liu, Changwang Zhang, Bo Yuan

Multi-view clustering is an important yet challenging task in machine learning and data mining community.

Deep Fusion Clustering Network

1 code implementation15 Dec 2020 Wenxuan Tu, Sihang Zhou, Xinwang Liu, Xifeng Guo, Zhiping Cai, En Zhu, Jieren Cheng

Specifically, in our network, an interdependency learning-based Structure and Attribute Information Fusion (SAIF) module is proposed to explicitly merge the representations learned by an autoencoder and a graph autoencoder for consensus representation learning.

Deep Clustering Graph Clustering +1

Context-Integrated and Feature-Refined Network for Lightweight Object Parsing

no code implementations26 Jul 2019 Bin Jiang, Wenxuan Tu, Chao Yang, Junsong Yuan

The core components of CIFReNet are the Long-skip Refinement Module (LRM) and the Multi-scale Context Integration Module (MCIM).

Scene Parsing Semantic Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.