Skip to Main content Skip to Navigation
Journal articles

Unsupervised Joint Salient Region Detection and Object Segmentation

Wenbin Zou 1, * Zhi Liu 2, 3 Kidiyo Kpalma 4 Joseph Ronsin 4 Yong Zhao 5 Nikos Komodakis 6, 7
* Corresponding author
3 Sirocco - Analysis representation, compression and communication of visual data
7 imagine [Marne-la-Vallée]
ligm - Laboratoire d'Informatique Gaspard-Monge, CSTB - Centre Scientifique et Technique du Bâtiment, ENPC - École des Ponts ParisTech
Abstract : This paper presents a novel unsupervised algorithm to detect salient regions and to segment out foreground objects from background. In contrast to previous unidirectional saliency-based object segmentation methods, in which only the detected saliency map is used to guide the object segmentation, our algorithm mutually exploits detection/segmentation cues from each other. To achieve this goal, an initial saliency map is generated by the proposed segmentation driven low-rank matrix recovery model. Such a saliency map is exploited to initialize object segmentation model, which is formulated as energy minimization of Markov random field. Mutually, the quality of saliency map is further improved by the segmentation result, and serves as a new guidance for the object segmentation. The optimal saliency map and the final segmentation are achieved by jointly optimizing the defined objective functions. Extensive evaluations on MSRA-B and PASCAL-1500 datasets demonstrate that the proposed algorithm achieves the state-of-the-art performance for both the salient region detection and the object segmentation.
Document type :
Journal articles
Complete list of metadatas
Contributor : Kidiyo Kpalma <>
Submitted on : Tuesday, December 15, 2015 - 10:12:47 AM
Last modification on : Thursday, February 27, 2020 - 1:37:41 PM



Wenbin Zou, Zhi Liu, Kidiyo Kpalma, Joseph Ronsin, Yong Zhao, et al.. Unsupervised Joint Salient Region Detection and Object Segmentation. IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2015, 24 (11), ⟨10.1109/TIP.2015.2456497⟩. ⟨hal-01243552⟩



Record views