arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.00171cs.LGcs.CV
收藏

基于自编码器和注意力的多视点子空间自适应学习

Multi-view Subspace Adaptive Learning via Autoencoder and Attention

China University of Petroleum, Beijing Campus (CUP)(中国石油大学(北京))

Jian-wei Liu, Hao-jie Xie, Run-kun Lu, Xiong-lin Luo

摘要:

多视图学习能够更全面地覆盖数据样本的所有特征,因此多视图学习受到了广泛的关注。传统的子空间聚类方法,如稀疏子空间聚类(SSC)和低秩子空间聚类(LRSC),聚类的亲和矩阵的单一视图,从而忽略了视图之间的融合问题。在本文中,我们提出了一种新的基于注意力和自编码器的多视点子空间自适应学习(MSALAA)。该方法结合了深度自编码器和多视图低秩稀疏子空间聚类(MLRSSC)中各视图自表示的对齐方法,既提高了对非线性拟合的能力,又满足了多视图学习的一致性和互补性原则。我们在六个真实数据集上观察到现有基线方法的显着改进。

英文摘要:

Multi-view learning can cover all features of data samples more comprehensively, so multi-view learning has attracted widespread attention. Traditional subspace clustering methods, such as sparse subspace clustering (SSC) and low-ranking subspace clustering (LRSC), cluster the affinity matrix for a single view, thus ignoring the problem of fusion between views. In our article, we propose a new Multiview Subspace Adaptive Learning based on Attention and Autoencoder (MSALAA). This method combines a deep autoencoder and a method for aligning the self-representations of various views in Multi-view Low-Rank Sparse Subspace Clustering (MLRSSC), which can not only increase the capability to non-linearity fitting, but also can meets the principles of consistency and complementarity of multi-view learning. We empirically observe significant improvement over existing baseline methods on six real-life datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑