主办单位：计算机科学与技术学院

时    间：2015.03.16 下午14:30

地    点：G202

报告题目： Semantic-oriented Object Segmentation

Abstract

This talk focuses on the problems of object segmentation and semantic segmentation which aim at separating objects from background or assigning a specific semantic label to each pixel in an image. We propose two approaches for the object segmentation and one approach for semantic segmentation.

For object segmentation, the first proposed approach is based on saliency detection. Motivated by our ultimate goal for object segmentation, a novel saliency detection model is proposed. This model is formulated in the low-rank matrix recovery model by taking the information of image structure derived from bottom-up segmentation as an important constraint. The object segmentation is built in an iterative and mutual optimization framework, which simultaneously performs object segmentation based on the saliency map resulting from saliency detection, and saliency quality boosting based on the segmentation. The optimal saliency map and the final segmentation are achieved after several iterations. The second proposed approach for object segmentation is based on exemplar images. The underlying idea is to transfer segmentation labels of globally and locally similar exemplar images to the query image. For the purpose of finding the most matching exemplars, we propose a novel high-level image representation method called object-oriented descriptor, which captures both global and local information of image. Then, a discriminative predictor is learned online by using the retrieved exemplars. This predictor assigns a probabilistic score of foreground to each region of the query image. After that, the predicted scores are integrated into the segmentation scheme of Markov random field (MRF) energy optimization. Iteratively finding minimum energy of MRF leads the final segmentation.

For semantic segmentation, we propose an approach based on region bank and sparse coding. Region bank is a set of regions generated by multi-level segmentations. This is motivated by the observation that some objects might be captured at certain levels in a hierarchical segmentation. For region description, we propose sparse coding method which represents each local feature descriptor with several basic vectors in the learned visual dictionary, and describes all local feature descriptors within a region by a single sparse histogram. With the sparse representation, support vector machine with multiple kernel learning is employed for semantic inference.

The proposed approaches have been extensively evaluated on several challenging and widely used datasets. Experiments demonstrated the proposed approaches outperform the state-of-the-art methods.

主讲人简介:

Wenbin Zou currently is a Postdoc Fellow, working closely with Prof. Nikos Komodakis, at the IMAGINE group of École des Ponts ParisTech, France. He received the PhD, under the guidance of Prof. Joseph Ronsin and Prof. Kidiyo Kpalma, from the National Institute of Applied Sciences, Rennes, France, in March 2014.  From 2007-2010, he was a postgraduate student at Peking University, where he received the ME degree in Software Engineering, with a specialization in Embedded Multimedia Technology. He was a Visiting Research Student at The Hong Kong University of Science and Technology from 2008-2009.

His current research interests include salient object detection, object segmentation, image retrieval and image semantic interpretation.