Sorry, you need to enable JavaScript to visit this website.

In this paper, we propose an accurate generative adversarial networks based saliency prediction model. Saliency network is an intact model to produce saliency maps. With the help of adversarial networks, feature extraction is more smooth and thorough. Moreover, the fully convolutional networks in saliency network facilitate the continuity and accuracy of pixel values in a saliency map. Compared with the six stateof-the-art methods, the proposed model has achieved highest accuracy. Besides, the performance of our model indicates that adversarial networks could be applied to more than classification. For future work, we will extend the algorithm to semi-supervised saliency prediction since DCGAN is a strong candidate for unsupervised learning.

Categories:
6 Views