Vicente, Sara; Rother, Carsten; Kolmogorov, VladimirIST Austria
Cosegmentation is typically defined as the task of jointly segmenting something similar in a given set of images. Existing methods are too generic and so far have not demonstrated competitive results for any specific task. In this paper we overcome this limitation by adding two new aspects to cosegmentation: (1) the "something" has to be an object, and (2) the "similarity" measure is learned. In this way, we are able to achieve excellent results on the recently introduced iCoseg dataset, which contains small sets of images of either the same object instance or similar objects of the same class. The challenge of this dataset lies in the extreme changes in viewpoint, lighting, and object deformations within each set. We are able to considerably outperform several competitors. To achieve this performance, we borrow recent ideas from object recognition: the use of powerful features extracted from a pool of candidate object-like segmentations. We believe that our work will be beneficial to several application areas, such as image retrieval.
2217 - 2224
CVPR: Computer Vision and Pattern Recognition
Vicente S, Rother C, Kolmogorov V. Object cosegmentation. In: IEEE; 2011:2217-2224. doi:10.1109/CVPR.2011.5995530
Vicente, S., Rother, C., & Kolmogorov, V. (2011). Object cosegmentation (pp. 2217–2224). Presented at the CVPR: Computer Vision and Pattern Recognition, IEEE. https://doi.org/10.1109/CVPR.2011.5995530
Vicente, Sara, Carsten Rother, and Vladimir Kolmogorov. “Object Cosegmentation,” 2217–24. IEEE, 2011. https://doi.org/10.1109/CVPR.2011.5995530.
S. Vicente, C. Rother, and V. Kolmogorov, “Object cosegmentation,” presented at the CVPR: Computer Vision and Pattern Recognition, 2011, pp. 2217–2224.
Vicente S, Rother C, Kolmogorov V. 2011. Object cosegmentation. CVPR: Computer Vision and Pattern Recognition 2217–2224.
Vicente, Sara, et al. Object Cosegmentation. IEEE, 2011, pp. 2217–24, doi:10.1109/CVPR.2011.5995530.