Visual object clustering via mixed-norm regularization
Many vision problems deal with high-dimensional data, such as motion segmentation and face clustering. However, these high-dimensional data usually lie in a low-dimensional structure. Sparse representation is a powerful principle for solving a number of clustering problems with high-dimensional data...
| Main Authors: | , , , , , |
|---|---|
| Format: | Conference Paper |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2015
|
| Online Access: | http://hdl.handle.net/20.500.11937/43834 |
| _version_ | 1848756822330048512 |
|---|---|
| author | Zhang, X. Pham, DucSon Phung, D. Liu, Wan-Quan Saha, B. Venkatesh, S. |
| author_facet | Zhang, X. Pham, DucSon Phung, D. Liu, Wan-Quan Saha, B. Venkatesh, S. |
| author_sort | Zhang, X. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | Many vision problems deal with high-dimensional data, such as motion segmentation and face clustering. However, these high-dimensional data usually lie in a low-dimensional structure. Sparse representation is a powerful principle for solving a number of clustering problems with high-dimensional data. This principle is motivated from an ideal modeling of data points according to linear algebra theory. However, real data in computer vision are unlikely to follow the ideal model perfectly. In this paper, we exploit the mixed norm regularization for sparse subspace clustering. This regularization term is a convex combination of the l1norm, which promotes sparsity at the individual level and the block norm l2/1 which promotes group sparsity. Combining these powerful regularization terms will provide a more accurate modeling, subsequently leading to a better solution for the affinity matrix used in sparse subspace clustering. This could help us achieve better performance on motion segmentation and face clustering problems. This formulation also caters for different types of data corruptions. We derive a provably convergent algorithm based on the alternating direction method of multipliers (ADMM) framework, which is computationally efficient, to solve the formulation. We demonstrate that this formulation outperforms other state-of-arts on both motion segmentation and face clustering. |
| first_indexed | 2025-11-14T09:18:18Z |
| format | Conference Paper |
| id | curtin-20.500.11937-43834 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T09:18:18Z |
| publishDate | 2015 |
| publisher | Institute of Electrical and Electronics Engineers Inc. |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-438342017-09-13T13:42:26Z Visual object clustering via mixed-norm regularization Zhang, X. Pham, DucSon Phung, D. Liu, Wan-Quan Saha, B. Venkatesh, S. Many vision problems deal with high-dimensional data, such as motion segmentation and face clustering. However, these high-dimensional data usually lie in a low-dimensional structure. Sparse representation is a powerful principle for solving a number of clustering problems with high-dimensional data. This principle is motivated from an ideal modeling of data points according to linear algebra theory. However, real data in computer vision are unlikely to follow the ideal model perfectly. In this paper, we exploit the mixed norm regularization for sparse subspace clustering. This regularization term is a convex combination of the l1norm, which promotes sparsity at the individual level and the block norm l2/1 which promotes group sparsity. Combining these powerful regularization terms will provide a more accurate modeling, subsequently leading to a better solution for the affinity matrix used in sparse subspace clustering. This could help us achieve better performance on motion segmentation and face clustering problems. This formulation also caters for different types of data corruptions. We derive a provably convergent algorithm based on the alternating direction method of multipliers (ADMM) framework, which is computationally efficient, to solve the formulation. We demonstrate that this formulation outperforms other state-of-arts on both motion segmentation and face clustering. 2015 Conference Paper http://hdl.handle.net/20.500.11937/43834 10.1109/WACV.2015.142 Institute of Electrical and Electronics Engineers Inc. restricted |
| spellingShingle | Zhang, X. Pham, DucSon Phung, D. Liu, Wan-Quan Saha, B. Venkatesh, S. Visual object clustering via mixed-norm regularization |
| title | Visual object clustering via mixed-norm regularization |
| title_full | Visual object clustering via mixed-norm regularization |
| title_fullStr | Visual object clustering via mixed-norm regularization |
| title_full_unstemmed | Visual object clustering via mixed-norm regularization |
| title_short | Visual object clustering via mixed-norm regularization |
| title_sort | visual object clustering via mixed-norm regularization |
| url | http://hdl.handle.net/20.500.11937/43834 |