Saliency Detection in Images with Complex Background by End-to-End Sparse Maxout CNN
Makhmudov Farrukh, Hongwei Ge · 2019
This paper proposes a saliency detection model for images with complex background based on the end-to-end sparse maxout convolutional neural network. We introduce the saliency detection model based on two key ideas. The first one is considering sparsity of the convolutional neural network. The second one is implementing the end-to-end architecture for the saliency detection. Experiment results on CAT2000, SALICON, MIT300 and iSUN demonstrate that the proposed method achieves state-of-the-art results in saliency detection and prediction tasks. Furthermore, the analysis of different saliency evaluation metrics related to the results of experiment is provided.