Labeling Spain With Stanford

Yingbo Zhou, Ifeoma Nwogu, Venu GovindarajuIEEE TIP 2013 · DOI · OpenReview

Abstract

We present an end-to-end framework for outdoor scene region decomposition, learned on a small set of randomly selected images that generalizes well to multiple data sets containing images from around the world. We discuss the different aspects of the framework especially a generalized variational inference method with better approximations to the true marginals of a graphical model. Experimentally, we explain why the framework is robust and performs competitively on many diverse scene data sets, including several unseen scene types. We have obtained high pixel-level accuracies ( ≈ 80%) in three of the four data sets, which include a benchmark data set known as the Stanford background data set. Our model obtained over 70% accuracy on the fourth data set, which contained a number of indoor and close-up images that are significantly different from our training examples.
BibTeX
@article{zhou2013labeling,
  author = {Yingbo Zhou and Ifeoma Nwogu and Venu Govindaraju},
  title = {{Labeling Spain With Stanford}},
  journal = {IEEE Trans. Image Process.},
  year = {2013},
  doi = {10.1109/tip.2013.2285603},
}

Loading related content...

Figure