Shallow and Deep Convolutional Networks for Saliency Prediction
Top Cited Papers
Open Access
- 1 June 2016
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 598-606
- https://doi.org/10.1109/cvpr.2016.71
Abstract
The prediction of salient 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 neural network (convnet). 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 end-to-end architectures that are both fast and accurate. Two designs are proposed: a shallow convnet trained from scratch, and a another deeper solution whose first three layers are adapted from another network trained for classification. To the authors' knowledge, these are the first end-to-end CNNs trained and tested for the purpose of saliency prediction.Keywords
Other Versions
This publication has 18 references indexed in Scilit:
- SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet ClassificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Mapping human visual representations in space and time by neural networksJournal of Vision, 2015
- Deep networks for saliency detection via local estimation and global searchPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Saliency detection by multi-context deep learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- SALICON: Saliency in ContextPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- CaffePublished by Association for Computing Machinery (ACM) ,2014
- Saliency Detection: A Boolean Map ApproachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Learning to predict where humans lookPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- A model of saliency-based visual attention for rapid scene analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998