cvpr cvpr2013 cvpr2013-450 cvpr2013-450-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Michael Rubinstein, Armand Joulin, Johannes Kopf, Ce Liu
Abstract: We present a new unsupervised algorithm to discover and segment out common objects from large and diverse image collections. In contrast to previous co-segmentation methods, our algorithm performs well even in the presence of significant amounts of noise images (images not containing a common object), as typical for datasets collected from Internet search. The key insight to our algorithm is that common object patterns should be salient within each image, while being sparse with respect to smooth transformations across images. We propose to use dense correspondences between images to capture the sparsity and visual variability of the common object over the entire database, which enables us to ignore noise objects that may be salient within their own images but do not commonly occur in others. We performed extensive numerical evaluation on es- tablished co-segmentation datasets, as well as several new datasets generated using Internet search. Our approach is able to effectively segment out the common object for diverse object categories, while naturally identifying images where the common object is not present.
[1] S. Bagon, O. Brostovski, M. Galun, and M. Irani. Detecting and sketching the common. In CVPR, pages 33–40, 2010. 2
[2] D. Batra, A. Kowdle, D. Parikh, J. Luo, and T. Chen. icoseg: Interactive co-segmentation with intelligent scribble guidance. In CVPR, 2010. 2, 5
[3] M. Cheng, G. Zhang, N. Mitra, X. Huang, and S. Hu. Global contrast based salient region detection. In CVPR, pages 409–416, 2011. 3
[4] M. Collins, J. Xu, L. Grady, and V. Singh. Random walks based multi-image segmentation: Quasiconvexity results and gpu-based solutions. In CVPR, 2012. 2
[5] A. Faktor and M. Irani. clustering by composition–unsupervised discovery of image categories. In ECCV, pages 474–487. 2012. 2
[6] D. Hochbaum and V. Singh. An efficient algorithm for cosegmentation. In ICCV, 2009. 2
[7] Y. Jing and S. Baluja. VisualRank: Applying pagerank to large-scale image search. TPAMI, 30(1 1): 1877 –1890, 2008. 2
[8] A. Joulin, F. Bach, and J. Ponce. Discriminative clustering for image co-segmentation. In CVPR, 2010. 2, 5, 6, 8
[9] A. Joulin, F. Bach, and J. Ponce. Multi-class cosegmentation. In CVPR, 2012. 2, 5, 6, 8
[10] G. Kim and A. Torralba. Unsupervised detection of regions of interest using iterative link analysis. In NIPS, 2009. 2
[11] G. Kim and E. Xing. On multiple foreground cosegmentation. In CVPR, 2012. 2
[12] G. Kim, E. Xing, L. Fei-Fei, and T. Kanade. Distributed cosegmentation via submodular optimization on anisotropic diffusion. In ICCV, 2011. 2, 5, 6, 8
[13] D. Kuettel, M. Guillaumin, and V. Ferrari. Segmentation propagation in imagenet. In ECCV, pages 459–473. Springer, 2012. 2, 6
[14] C. Liu, J. Yuen, and A. Torralba. Nonparametric scene parsing via label transfer. TPAMI, 33(12):2368–2382, 2011. 3, 4
[15] C. Liu, J. Yuen, and A. Torralba. SIFT flow: Dense correspondence across scenes and its applications. TPAMI, 33(5):978–994, 2011. 3
[16] L. Mukherjee, V. Singh, and C. Dyer. Half-integrality based algorithms for cosegmentation of images. In CVPR, 2009. 2
[17] A. Oliva and A. Torralba. Modeling the shape of the scene: A holistic representation of the spatial envelope. IJCV, 42: 145–175, 2001 . 4
[18] C. Rother, V. Kolmogorov, and A. Blake. Grabcut: Interactive foreground extraction using iterated graph cuts. In ACM SIGGRAPH, volume 23, pages 309–3 14, 2004. 4
[19] C. Rother, T. Minka, A. Blake, and V. Kolmogorov. Cosegmentation of image pairs by histogram matching - incorporating a global constraint into mrfs. In CVPR, 2006. 2, 4
[20] M. Rubinstein, C. Liu, and W. T. Freeman. Annotation propagation in large image databases via dense image correspondence. In ECCV, pages 85–99, 2012. 2, 3
[21] B. Russell, A. Torralba, K. Murphy, and W. Freeman. Labelme: a database and web-based tool for image annotation. IJCV, 77(1): 157–
[22]
[23]
[24]
[25]
[26] 173, 2008. 6 B. C. Russell, A. A. Efros, J. Sivic, W. T. Freeman, and A. Zisserman. Using multiple segmentations to discover objects and their extent in image collections. In CVPR, 2006. 2 J. Shotton, J. Winn, C. Rother, and A. Criminisi. Textonboost: Joint appearance, shape and context modeling for multi-class object recognition and segmentation. ECCV, pages 1–15, 2006. 5 J. Sivic, B. C. Russell, A. A. Efros, A. Zisserman, and W. T. Freeman. Discovering objects and their location in images. In ICCV, 2005. 2 S. Vicente, C. Rother, and V. Kolmogorov. Object cosegmentation. In CVPR, pages 2217–2224, 2011. 2, 5, 6 J. Winn and N. Jojic. Locus: Learning object classes with unsupervised segmentation. In ICCV, volume 1, pages 756–763, 2005. 2 111999444644