Kernelized Subspace Ranking for Saliency Detection
View Researcher's Other CodesDisclaimer: The provided code links for this paper are external links. Science Nest has no responsibility for the accuracy, legality or content of these links. Also, by downloading this code(s), you agree to comply with the terms of use as set out by the author(s) of the code(s).
Authors | Tiantian Wang, Lihe Zhang, Huchuan Lu, Chong Sun, Jinqing Qi |
Journal/Conference Name | EUROPEAN CONFERENCE ON COMPUTER VISION |
Paper Category | ECE |
Paper Abstract | In this paper, we propose a novel saliency method that takes advantage of object-level proposals and region-based convolutional neural network (R-CNN) features. We follow the learning-to-rank methodology, and solve a ranking problem satisfying the constraint that positive samples have higher scores than negative ones. As the dimensionality of the deep features is high and the amount of training data is low, ranking in the primal space is suboptimal. A new kernelized subspace ranking model is proposed by jointly learning a Rank-SVM classifier and a subspace projection. The projection aims to measure the pairwise distances in a low-dimensional space. For an image, the ranking score of each proposal is assigned by the learnt ranker. The final saliency map is generated by a weighted fusion of the top-ranked candidates. Experimental results show that the proposed algorithm performs favorably against the state-of-the-art methods on four benchmark datasets. |
Date of publication | 2016 |
Code Programming Language | MATLAB |
Comment |