Clustered Saliency Prediction

We present a new method for image salience prediction, Clustered Saliency Prediction. This method divides individuals into clusters based on their personal features and their known saliency maps, and generates a separate image salience model for each cluster. We test our approach on a public dataset of personalized saliency maps, with varying importance weights for personal feature factors and observe the effects on the clusters. For each cluster, we use an image-to-image translation method, mainly Pix2Pix model, to convert universal saliency maps to saliency maps of that cluster. We try three state-of-the-art universal saliency prediction methods, DeepGaze II, ML-Net and SalGAN, and see their impact on the results. We show that our Clustered Saliency Prediction technique outperforms the state-of-the-art universal saliency prediction models. Also we demonstrate the effectiveness of our clustering method by comparing the results of Clustered Saliency Prediction using clusters obtained by Subject Similarity Clustering algorithm with two baseline methods. We propose an approach to assign new people to the most appropriate cluster, based on their personal features and any known saliency maps. In our experiments we see that this method of assigning new people to a cluster on average chooses the cluster that gives higher saliency scores.