Name
Abstract | ||
|---|---|---|
Image partitioning is an important preprocessing step for many of the state-of-the-art algorithms used for performing high-level computer vision tasks. Typically, partitioning is conducted without regard to the task in hand. We propose a task-specific image partitioning framework to produce a region-based image representation that will lead to a higher task performance than that reached using any task-oblivious partitioning framework and existing supervised partitioning framework, albeit few in number. The proposed method partitions the image by means of correlation clustering, maximizing a linear discriminant function defined over a superpixel graph. The parameters of the discriminant function that define task-specific similarity/dissimilarity among superpixels are estimated based on structured support vector machine (S-SVM) using task-specific training data. The S-SVM learning leads to a better generalization ability while the construction of the superpixel graph used to define the discriminant function allows a rich set of features to be incorporated to improve discriminability and robustness. We evaluate the learned task-aware partitioning algorithms on three benchmark datasets. Results show that task-aware partitioning leads to better labeling performance than the partitioning computed by the state-of-the-art general-purpose and supervised partitioning algorithms. We believe that the task-specific image partitioning paradigm is widely applicable to improving performance in high-level image understanding tasks. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/TIP.2012.2218822 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
task-specific similarity-dissimilarity,image representation,linear discriminant function,pattern clustering,task-specific training data,task-specific image partitioning framework,superpixel graph estimation,s-svm learning,high-level computer vision task,learning (artificial intelligence),benchmark dataset,structured support vector machine learning,learned task-aware partitioning algorithm,computer vision,region-based image representation,correlation clustering,image partitioning,support vector machines,correlation methods,linear programming relaxation,structured support vector machine,supervised partitioning framework,learning artificial intelligence | Structured support vector machine,Computer science,Robustness (computer science),Artificial intelligence,Discriminant function analysis,Computer vision,Correlation clustering,Set partitioning in hierarchical trees,Pattern recognition,Support vector machine,Preprocessor,Linear discriminant analysis,Machine learning | Journal |
Volume | Issue | ISSN |
22 | 2 | 1941-0042 |
Citations | PageRank | References |
10 | 0.50 | 33 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sungwoong Kim | 1 | 76 | 5.10 |
| Sebastian Nowozin | 2 | 2104 | 90.05 |
| Pushmeet Kohli | 3 | 7398 | 332.84 |
| Chang D. Yoo | 4 | 375 | 45.88 |