TY - GEN
T1 - A unified approach to salient object detection via low rank matrix recovery
AU - Shen, Xiaohui
AU - Wu, Ying
PY - 2012
Y1 - 2012
N2 - Salient object detection is not a pure low-level, bottom-up process. Higher-level knowledge is important even for task-independent image saliency. We propose a unified model to incorporate traditional low-level features with higher-level guidance to detect salient objects. In our model, an image is represented as a low-rank matrix plus sparse noises in a certain feature space, where the non-salient regions (or background) can be explained by the low-rank matrix, and the salient regions are indicated by the sparse noises. To ensure the validity of this model, a linear transform for the feature space is introduced and needs to be learned. Given an image, its low-level saliency is then extracted by identifying those sparse noises when recovering the low-rank matrix. Furthermore, higher-level knowledge is fused to compose a prior map, and is treated as a prior term in the objective function to improve the performance. Extensive experiments show that our model can comfortably achieves comparable performance to the existing methods even without the help from high-level knowledge. The integration of top-down priors further improves the performance and achieves the state-of-the-art. Moreover, the proposed model can be considered as a prototype framework not only for general salient object detection, but also for potential task-dependent saliency applications.
AB - Salient object detection is not a pure low-level, bottom-up process. Higher-level knowledge is important even for task-independent image saliency. We propose a unified model to incorporate traditional low-level features with higher-level guidance to detect salient objects. In our model, an image is represented as a low-rank matrix plus sparse noises in a certain feature space, where the non-salient regions (or background) can be explained by the low-rank matrix, and the salient regions are indicated by the sparse noises. To ensure the validity of this model, a linear transform for the feature space is introduced and needs to be learned. Given an image, its low-level saliency is then extracted by identifying those sparse noises when recovering the low-rank matrix. Furthermore, higher-level knowledge is fused to compose a prior map, and is treated as a prior term in the objective function to improve the performance. Extensive experiments show that our model can comfortably achieves comparable performance to the existing methods even without the help from high-level knowledge. The integration of top-down priors further improves the performance and achieves the state-of-the-art. Moreover, the proposed model can be considered as a prototype framework not only for general salient object detection, but also for potential task-dependent saliency applications.
UR - http://www.scopus.com/inward/record.url?scp=84866672748&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84866672748&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2012.6247758
DO - 10.1109/CVPR.2012.6247758
M3 - Conference contribution
AN - SCOPUS:84866672748
SN - 9781467312264
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 853
EP - 860
BT - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
T2 - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
Y2 - 16 June 2012 through 21 June 2012
ER -