The Multi-Feature Information Bottleneck with Application to Unsupervised Image Categorization

Lou, Zhengzheng; Ye, Yangdong; Yan, Xiaoqiang

The Multi-Feature Information Bottleneck with Application to Unsupervised Image Categorization

Zhengzheng Lou, Yangdong Ye, Xiaoqiang Yan

Download BibTeX Cite

Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence. Pages 1508-1514.

Abstract

We present a novel unsupervised data analysis method, Multi-feature Information Bottleneck (MfIB), which is an extension of the Information Bottleneck (IB). In comparison with the original IB, the proposed MfIB method can analyze the data simultaneously from multiple feature variables, which characterize the data from multiple cues. To verify the effectiveness of MfIB, we apply the corresponding MfIB algorithm to unsupervised image categorization. In our experiments, by taking into account multiple types of features, such as local shape, color and texture, the MfIB algorithm is found to be consistently superior to the original IB algorithm which takes only one source of features into consideration. Besides, the performance of MfIB algorithm is also superior to the state-of-the-art unsupervised image categorization methods.

Zhengzheng Lou, Yangdong Ye, and Xiaoqiang Yan. 2013. The Multi-Feature Information Bottleneck with Application to Unsupervised Image Categorization. In Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence, IJCAI-13. IJCAI, 1508–1514. https://ijcai.org/proceedings/2013/225

@inproceedings{ijcai2013p225,
  title     = {The Multi-Feature Information Bottleneck with Application to Unsupervised Image Categorization},
  author    = {Lou, Zhengzheng and Ye, Yangdong and Yan, Xiaoqiang},
  booktitle = {Proceedings of the Twenty-Third International Joint Conference on
               Artificial Intelligence, {IJCAI-13}},
  publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
  editor    = {Francesca Rossi},
  pages     = {1508--1514},
  year      = {2013},
  month     = {8},
  url       = {https://ijcai.org/proceedings/2013/225},
}

TY  - CPAPER
TI  - The Multi-Feature Information Bottleneck with Application to Unsupervised Image Categorization
AU  - Lou, Zhengzheng
AU  - Ye, Yangdong
AU  - Yan, Xiaoqiang
T2  - Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence, IJCAI-13
PB  - AAAI Press / International Joint Conferences on Artificial Intelligence
PY  - 2013
SP  - 1508
EP  - 1514
UR  - https://ijcai.org/proceedings/2013/225
ER  -