The prediction of saliency areas in images has been traditionally addressed with hand crafted features based on neuroscience principles. This paper however addresses the problem with a completely data-driven approach by training a convolutional network. The learning process is formulated as a minimization of a loss function that measures the Euclidean distance of the predicted saliency map with the provided ground truth. The recent publication of large datasets of saliency prediction has provided enough data to train a not very deep architecture which is both fast and accurate. The convolutional network in this paper, named JuntingNet, won the LSUN 2015 challenge on saliency prediction with a superior performance in all considered metrics.
@article{arxiv.1507.01422,
title = {End-to-end Convolutional Network for Saliency Prediction},
author = {Junting Pan and Xavier Giró-i-Nieto},
journal= {arXiv preprint arXiv:1507.01422},
year = {2015}
}
Comments
Winner of the saliency prediction challenge in the Large-scale Scene Understanding (LSUN) Challenge in the associated workshop of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015