Unimore logo AImageLab

Multi-Level Net: a Visual Saliency Prediction Model

Abstract: State of the art approaches for saliency prediction are based on Full Convolutional Networks, in which saliency maps are built using the last layer. In contrast, we here present a novel model that predicts saliency maps exploiting a non-linear combination of features coming from different layers of the network. We also present a new loss function to deal with the imbalance issue on saliency masks. Extensive results on three public datasets demonstrate the robustness of our solution. Our model outperforms the state of the art on SALICON, which is the largest and unconstrained dataset available, and obtains competitive results on MIT300 and CAT2000 benchmarks.


Cornia, Marcella; Baraldi, Lorenzo; Serra, Giuseppe; Cucchiara, Rita "Multi-Level Net: a Visual Saliency Prediction Model" Computer Vision – ECCV 2016 Workshops, vol. 9914, Amsterdam, The Netherlands, pp. 302 -315 , October 9th, 2016, 2016 DOI: 10.1007/978-3-319-48881-3_21

 not available

Paper download:

Related research activities:

Related projects: