Region Ranking Svm For Image Classification
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(2016)
摘要
The success of an image classification algorithm largely depends on how it incorporates local information in the global decision. Popular approaches such as average-pooling and max-pooling are suboptimal in many situations. In this paper we propose Region Ranking SVM (RRSVM), a novel method for pooling local information from multiple regions. RRSVM exploits the correlation of local regions in an image, and it jointly learns a region evaluation function and a scheme for integrating multiple regions. Experiments on PASCAL VOC 2007, VOC 2012, and ILSVRC2014 datasets show that RRSVM outperforms the methods that use the same feature type and extract features from the same set of local regions. RRSVM achieves similar to or better than the state-of-the-art performance on all datasets.
更多查看译文
关键词
region ranking SVM,image classification,global decision,average-pooling,max-pooling,RRSVM,local information pooling,PASCAL VOC 2007 datasets,VOC 2012 datasets,ILSVRC2014 datasets,feature extraction
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络