Shallow and Deep Convolutional Networks for Saliency Prediction
Citations Over TimeTop 1% of 2016 papers
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.
Related Papers
- → Effect of scratch velocity on scratch behavior of injection‐molded polypropylene(2012)18 cited
- → A (Relatively) Unsatisfactory Experience of Use of Scratch in CS1(2017)21 cited
- Investigation on Scratch Tolerance of the Cabin Glass(2004)
- Effect of Scratch on Fatigue Life of Fasten Holes(2007)