Concurrent Segmentation of Categorized Objects from an Image Collection
Le Wang, Jianru Xue, Nanning Zheng, Gang Hua · 2015
We propose a method for automatic segmentation of categorized objects from a collection of images in the same category, which employs a single auto-context model learned from all images without the need of us-ing pixel level labels. Instead of extracting the salient objects from each image one by one, we extract the ob-jects from all images simultaneously. The segmentation of the salient objects is iteratively performed, where the auto-context model is incrementally learned based on new segmentations of all images at each iteration. Upon convergence, we obtain not only the clean segmenta-tions of the salient objects, but also an auto-context classifier learned on all images which can readily be ex-ploited to segment categorized object from a new image. Our experiments validated the efficacy of our proposed approach. 1.