Task-Specific Image Partitioning

Sungwoong Kim, Sebastian Nowozin, Pushmeet Kohli, Chang D. Yoo

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.
BibTeX
@article{kim2013task,
  author = {Sungwoong Kim and Sebastian Nowozin and Pushmeet Kohli and Chang D. Yoo},
  title = {{Task-Specific Image Partitioning}},
  journal = {IEEE Trans. Image Process.},
  year = {2013},
  url = {https://openreview.net/forum?id=faTIlD35jFt},
}

Loading related content...

Figure