期刊
IEEE TRANSACTIONS ON MULTIMEDIA
卷 16, 期 2, 页码 470-479出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMM.2013.2293424
关键词
Structure cues; graphlet; weakly supervised; segmentation; active learning
资金
- Singapore National Research Foundation under its International Research Centre@Singapore Funding Initiative
- Nature Science Foundation of China [61373076]
- Fundamental Research Funds for the Central Universities [2013121026]
- 985 Project of Xiamen University
- Natural Science Foundation of China [61002009]
- Key Science and Technology Program of Zhejiang Province of China [2012C01035-1]
- Zhejiang Provincial Natural Science Foundation of China [LZ13F020004]
Weakly-supervised image segmentation is a challenging problem with multidisciplinary applications in multimedia content analysis and beyond. It aims to segment an image by leveraging its image-level semantics (i.e., tags). This paper presents a weakly-supervised image segmentation algorithm that learns the distribution of spatially structural superpixel sets from image-level labels. More specifically, we first extract graphlets from a given image, which are small-sized graphs consisting of superpixels and encapsulating their spatial structure. Then, an efficient manifold embedding algorithm is proposed to transfer labels from training images into graphlets. It is further observed that there are numerous redundant graphlets that are not discriminative to semantic categories, which are abandoned by a graphlet selection scheme as they make no contribution to the subsequent segmentation. Thereafter, we use a Gaussian mixture model (GMM) to learn the distribution of the selected post-embedding graphlets (i.e., vectors output from the graphlet embedding). Finally, we propose an image segmentation algorithm, termed representative graphlet cut, which leverages the learned GMM prior to measure the structure homogeneity of a test image. Experimental results show that the proposed approach outperforms state-of-the-art weakly-supervised image segmentation methods, on five popular segmentation data sets. Besides, our approach performs competitively to the fully-supervised segmentation models.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据