Subspace segmentation with a large number of subspaces using infinity norm minimization

作者：

Highlights：

• We find an observation important to the LSN subspace segmentation.

• We provide the theoretical support of the mentioned observation.

• Our paper is the first to adopt infinite norm in subspace segmentation.

• The computational complexity of our ADM algorithm is lower than O(n3).

• Our method achieve the state-of-the-art results in extensive experiments.

摘要

•We find an observation important to the LSN subspace segmentation.•We provide the theoretical support of the mentioned observation.•Our paper is the first to adopt infinite norm in subspace segmentation.•The computational complexity of our ADM algorithm is lower than O(n3).•Our method achieve the state-of-the-art results in extensive experiments.

论文关键词：Subspace segmentation,Large subspace number,Infinity norm,Spectral-clustering based methods

论文评审过程：Received 14 May 2018, Revised 3 December 2018, Accepted 18 December 2018, Available online 19 December 2018, Version of Record 27 December 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.12.025