Weighted Linear Multiple Kernel Learning for Saliency Detection
This paper presents a novel saliency detection method based on weighted linear multiple kernel learning (WLMKL), which is able to adaptively combine different contrast measurements in a supervised manner. Three commonly used bottom-up visual saliency operations are first introduced, including corner-surround contrast (CSC), center-surround contrast (CESC), and global contrast (GC). Then these contrast measures are fed into our WLMKL framework to produce the final saliency map. We show that the assigned weights for each contrast feature maps are always normalized in our WLMKL formulation. In addition, the proposed approach benefits from the advantages of the contribution of each individual contrast operation, and thus produces more robust and accurate saliency maps. The extensive experimental results show the effectiveness of the proposed model, and demonstrate the combination is superior to individual subcomponent.
KeywordsSaliency detection Corner-surround contrast Center-surround contrast Global contrast Multiple kernel learning
This work was partly supported by the National Science Foundation (Grant No. IIS-1302164), the National Natural Science Foundation of China (Grant No. 61881240048, 61571240, 61501247, 61501259, 61671253), China Postdoctoral Science Foundation (Grant No. 2015M581841), Open Fund Project of Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education (Nanjing University of Science and Technology) (Grant No. JYB201709, JYB201710), and Natural Science Foundation of Jiangsu Province, China (BK20160908), NUPTSF (Grant No. NY214139).
- 4.Bruce, N., & Tsotsos, J. (2006). Saliency based on information maximization. In Proceedings of the 18th International Conference on Neural Information Processing System (pp. 155–162). Cambridge, MA: MIT Press.Google Scholar
- 5.Cheng, M., Zhang, G., Mitra, N., Huang, X., & Hu, S. (2011). Global contrast based salient region detection. In Conference on Computer Vision and Pattern Recognition (pp. 409–416).Google Scholar
- 9.Hou, X., & Zhang, L. (2007). Saliency detection: A spectral residual approach. In 2007 IEEE Conference on Computer Vision and Pattern Recognition (pp. 1–8). Piscataway: IEEE.Google Scholar
- 10.Hou, X., & Zhang, L. (2008). Dynamic visual attention: Searching for coding length increments. In Advances in Neural Information Processing Systems (pp. 681–688).Google Scholar
- 11.Hu, Y., Xie, X., Ma, W. Y., Chia, L. T., & Rajan, D. (2005). Salient region detection using weighted feature maps based on the human visual attention model. In Advances in Multimedia Information Processing-PCM (pp. 993–1000).Google Scholar
- 14.Kruthiventi, S. S. S., Gudisa, V., Dholakiya, J. H., & Babu, R. V.: Saliency unified: A deep architecture for simultaneous eye fixation prediction and salient object segmentation. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 5781–5790). Piscataway: IEEE.Google Scholar
- 17.Ma, Q., & Zhang, L. (2008). Image quality assessment with visual attention. In 2008 19th International Conference on Pattern Recognition (pp. 1–4). Piscataway: IEEE.Google Scholar
- 19.Marchesotti, L., Cifarelli, C., G., & Gabriela, C. (2009). A framework for visual saliency detection with applications to image thumbnailing. In 2009 IEEE 12th International Conference on Computer Vision (pp. 2232–2239).Google Scholar
- 29.Zhou, Q., Li, N., Yang, Y., Chen, P., & Liu, W. (2012). Corner-surround contrast for saliency detection. In Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012) (pp. 1423–1426). Piscataway: IEEE.Google Scholar
- 31.Zhou, Q., Cai, S., Zhu, S., & Zheng, B. (2014). Salient object detection using window mask transferring with multi-layer background contrast. In Asian Conference on Computer Vision (pp. 221–235). Cham: Springer.Google Scholar