Learning visual saliency using topographic independent component analysis

Daria Stefic, Ioannis Patras

Abstract

Understanding the underlying mechanisms that drive human visual attention is a topic of immense interest. Most of the work is focused on extracting manually selected features that might resemble the human visual processing pathway and using a combination of those features to train a classifier that learns to predict where humans look. In contrast, we will learn the features using a generalization of Independent Component Analysis (ICA), namely the topographic Independent Component Analysis (tICA). We will show that those learned features in combination with linear SVM outperform the hand-crafted ones. In addition, we propose a novel optimization scheme, which jointly optimizes for linear SVM and tICA pooling weights and show that it further improves the results.
BibTeX
@inproceedings{stefic2014learning,
  author = {Daria Stefic and Ioannis Patras},
  title = {{Learning visual saliency using topographic independent component analysis}},
  booktitle = {ICIP},
  year = {2014},
  doi = {10.1109/icip.2014.7025225},
}

Loading related content...

Figure