Abstract | ||
---|---|---|
In this paper, we propose a saliency prediction algorithm utilizing generative adversarial networks. The proposed system contains two parts: saliency network and adversarial networks. The saliency network is the basis for saliency prediction, which calculates an Euclidean cost function on the grayscale values between the predicted saliency map and the ground truth. In order to improve the accuracy of the algorithm, adversarial networks are subsequently utilized to extract the features of input data by coordinating the learning rates of the two sub-networks contained in the networks. Experimental results validate the high accuracy of the proposed approach compared with the state-of-the-art models on three public datasets, SALICON, MIT1003 and Cerf. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/ICIP.2017.8296700 | 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) |
Keywords | Field | DocType |
Saliency prediction, accuracy, GAN, adversarial networks, saliency network | Salience (neuroscience),Computer science,Artificial intelligence,Euclidean geometry,Grayscale,Computer vision,Pattern recognition,Visualization,Feature extraction,Ground truth,Generative grammar,Machine learning,Adversarial system | Conference |
Volume | ISSN | ISBN |
2017-September | 1522-4880 | 9781509021758 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |