当前位置: X-MOL 学术arXiv.cs.CV › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Robust Self-Supervised Convolutional Neural Network for Subspace Clustering and Classification
arXiv - CS - Computer Vision and Pattern Recognition Pub Date : 2020-04-03 , DOI: arxiv-2004.03375
Dario Sitnik and Ivica Kopriva

Insufficient capability of existing subspace clustering methods to handle data coming from nonlinear manifolds, data corruptions, and out-of-sample data hinders their applicability to address real-world clustering and classification problems. This paper proposes the robust formulation of the self-supervised convolutional subspace clustering network ($S^2$ConvSCN) that incorporates the fully connected (FC) layer and, thus, it is capable for handling out-of-sample data by classifying them using a softmax classifier. $S^2$ConvSCN clusters data coming from nonlinear manifolds by learning the linear self-representation model in the feature space. Robustness to data corruptions is achieved by using the correntropy induced metric (CIM) of the error. Furthermore, the block-diagonal (BD) structure of the representation matrix is enforced explicitly through BD regularization. In a truly unsupervised training environment, Robust $S^2$ConvSCN outperforms its baseline version by a significant amount for both seen and unseen data on four well-known datasets. Arguably, such an ablation study has not been reported before.

中文翻译:

用于子空间聚类和分类的鲁棒自监督卷积神经网络

现有子空间聚类方法处理来自非线性流形、数据损坏和样本外数据的数据的能力不足,阻碍了它们解决现实世界聚类和分类问题的适用性。本文提出了包含完全连接 (FC) 层的自监督卷积子空间聚类网络 ($S^2$ConvSCN) 的稳健公式,因此,它能够通过对样本外数据进行分类来处理它们使用 softmax 分类器。$S^2$ConvSCN 通过学习特征空间中的线性自表示模型来聚类来自非线性流形的数据。通过使用误差的相关熵诱导度量 (CIM) 来实现对数据损坏的鲁棒性。此外,表示矩阵的块对角 (BD) 结构是通过 BD 正则化明确强制执行的。在真正无监督的训练环境中,Robust $S^2$ConvSCN 在四个众所周知的数据集上的可见和不可见数据方面都明显优于其基线版本。可以说,以前从未报道过这样的消融研究。
更新日期:2020-04-08
down
wechat
bug