Yong Li
ABSTRACT
The goal of this paper is to simultaneously segment the object regions appearing in a set of images of the same object class, known as object co-segmentation. Different from typical methods, simply assuming that the regions common among images are the object regions, we additionally consider the disturbance from consistent backgrounds, and indicate not only common regions but salient ones among images to be the object regions. To this end, we propose a Discriminative Low Rank matrix Recovery (DLRR) algorithm to divide the over-completely segmented regions (i.e.,superpixels) of a given image set into object and non-object ones. In DLRR, a low-rank matrix recovery term is adopted to detect salient regions in an image, while a discriminative learning term is used to distinguish the object regions from all the super-pixels. An additional regularized term is imported to jointly measure the disagreement between the predicted saliency and the objectiveness probability corresponding to each super-pixel of the image set. For the unified learning problem by connecting the above three terms, we design an efficient optimization procedure based on block-coordinate descent. Extensive experiments are conducted on two public datasets, i.e., MSRC and iCoseg, and the comparisons with some state-of-the-arts demonstrate the effectiveness of our work.
- B. Alexe, T. Deselaers, and V. Ferrari. What is an object -- In CVPR, 2010.Google Scholar
- D. Batra, A. Kowdle, D. Parikh, J. Luo, and T. Chen. Interactively co-segmentating topically related images with intelligent scribble guidance. IJCV, 93(3):273--292, 2011. Google ScholarDigital Library
- D. Comaniciu and P. Meer. Mean shift: a robust approach toward feature space analysis. TPAMI, 24(5):603--619, 2002. Google ScholarDigital Library
- A. Joulin, F. Bach, and J. Ponce. Discriminative clustering for image co-segmentation. In CVPR, 2010.Google ScholarCross Ref
- A. Joulin, F. Bach, and J. Ponce. Multi-class cosegmentation. In CVPR, 2012.Google ScholarCross Ref
- D. Kuettel and V. Ferrari. Figure-ground segmentation by transferring window masks. In CVPR, 2012. Google ScholarDigital Library
- Z. Lin, M. Chen, and Y. Ma. The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices. UIUC Technical Report UILU-ENG-09--2214, October 2010.Google Scholar
- L. Mukherjee, V. Singh, and J. Peng. Scale invariant cosegmentation for image groups. In CVPR, 2011. Google ScholarDigital Library
- C. Rother, V. Kolmogorov, and A. Blake. "grabcut" - interactive foreground extraction using iterated graph cuts. ACM Trans. Graph., 23(3):309--314, Aug 2004. Google ScholarDigital Library
- X. Shen and Y. Wu. A unified approach to salient object detection via low rank matrix recovery. In CVPR, 2012. Google ScholarDigital Library
- J. Wright, Y. Peng, and Y. Ma. Robust principal component analysis: Exact recovery of corrupted low-rank matrices via convex optimization. In NIPS, 2009.Google ScholarDigital Library
Index Terms
- Object co-segmentation via discriminative low rank matrix recovery
Recommendations
Object co-segmentation via salient and common regions discovery
The goal of this paper is to simultaneously segment the object regions in a set of images with the same object class, known as object co-segmentation. Different from typical methods, simply assuming that the common regions among images are the object ...
Learning completed discriminative local features for texture classification
We propose a novel feature representation method, namely Completed Discriminative Local Features (CDLF), for texture classification.The CDLF learn transformation matrices for texture images that maximize the mutual information between the local features ...
Robust Image Restoration via Reweighted Low-Rank Matrix Recovery
MMM 2014: Proceedings of the 20th Anniversary International Conference on MultiMedia Modeling - Volume 8325In this paper, we propose a robust image restoration method via reweighted low-rank matrix recovery. In the literature, Principal Component Pursuit (PCP) solves low-rank matrix recovery problem via a convex program of mixed nuclear norm and ℓ1 norm. ...
Comments