Name
Abstract | ||
|---|---|---|
This paper introduces to use semi-supervised learning for large scale image co segmentation. Different from traditional unsupervised cosegmentation that does not use any segmentation ground truth, semi-supervised cosegmentation exploits the similarity from both the very limited training image foregrounds, as well as the common object shared between the large number of unsegmented images. This would be a much practical way to effectively co segment a large number of related images simultaneously, where previous unsupervised co segmentation work poorly due to the large variances in appearance between different images and the lack of segmentation ground truth for guidance in co segmentation. For semi-supervised co segmentation in large scale, we propose an effective method by minimizing an energy function, which consists of the inter-image distance, the intra-image distance and the balance term. We also propose an iterative updating algorithm to efficiently solve this energy function, which decomposes the original energy minimization problem into sub-problems, and updates each image alternatively to reduce the number of variables in each sub-problem for computation efficiency. Experiment results on iCoseg and Pascal VOC datasets show that the proposed co segmentation method can effectively co segment hundreds of images in less than one minute. And our semi-supervised co segmentation is able to outperform both unsupervised co segmentation as well as fully supervised single image segmentation, especially when the training data is limited. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/ICCV.2013.56 | ICCV |
Keywords | Field | DocType |
fully supervised single image segmentation,energy function,image cosegmentation,semisupervised learning,balance term,co segmentation,co segment,large scale image,segmentation ground truth,supervised single image segmentation,training image foregrounds,intraimage distance,semisupervised cosegmentation,semi-supervised co segmentation,image segmentation,semi-supervised learning,large number,iterative updating algorithm,proposed co segmentation method,large scale image cosegmentation,inter-image distance,icoseg datasets,unsupervised co segmentation,pascal voc datasets,previous unsupervised co segmentation,binary quadratic programming problem,minimisation,traditional unsupervised co segmentation,unsupervised learning,energy minimization problem,energy minimization function,unsupervised cosegmentation,iterative methods,training data,semi supervised learning | Computer vision,Scale-space segmentation,Semi-supervised learning,Pattern recognition,Segmentation,Iterative method,Computer science,Segmentation-based object categorization,Image segmentation,Unsupervised learning,Ground truth,Artificial intelligence | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1550-5499 |
Citations | PageRank | References |
11 | 0.50 | 23 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhengxiang Wang | 1 | 107 | 5.06 |
| Rujie Liu | 2 | 147 | 15.49 |