SAM: Pushing the Limits of Saliency Prediction Models

Marcella Cornia, Lorenzo Baraldi, Giuseppe Serra, Rita Cucchiara

CVPRW 2018 pp. 1890-1892

doi:10.1109/CVPRW.2018.00250 /cvprw/2018/cornia2018cvprw-sam/

Abstract

The prediction of human eye fixations has been recently gaining a lot of attention thanks to the improvements shown by deep architectures. In our work, we go beyond classical feed-forward networks to predict saliency maps and propose a Saliency Attentive Model which incorporates neural attention mechanisms to iteratively refine predictions. Experiments demonstrate that the proposed strategy overcomes by a considerable margin the state of the art on the largest dataset available for saliency prediction. Here, we provide experimental results on other popular saliency datasets to confirm the effectiveness and the generalization capabilities of our model, which enable us to reach the state of the art on all considered datasets.

CVPRW Semantic Scholar

Cite

Text

Cornia et al. "SAM: Pushing the Limits of Saliency Prediction Models." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018. doi:10.1109/CVPRW.2018.00250

Markdown

[Cornia et al. "SAM: Pushing the Limits of Saliency Prediction Models." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.](https://mlanthology.org/cvprw/2018/cornia2018cvprw-sam/) doi:10.1109/CVPRW.2018.00250

BibTeX

@inproceedings{cornia2018cvprw-sam,
  title     = {{SAM: Pushing the Limits of Saliency Prediction Models}},
  author    = {Cornia, Marcella and Baraldi, Lorenzo and Serra, Giuseppe and Cucchiara, Rita},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2018},
  pages     = {1890-1892},
  doi       = {10.1109/CVPRW.2018.00250},
  url       = {https://mlanthology.org/cvprw/2018/cornia2018cvprw-sam/}
}