Image Saliency Detection:From Convolutional Neural Network to Capsule Network

Human beings possess the innate ability of identifying the most attractive regions or objects in an image. Salient object  etection aims to imitate this ability by automatically identifying and segmenting the most attractive objects in an image. In this talk, I will share with you two recent works that we published in the top venues. In the first work, we showcase a guidance strategy for multi-level contextual information integration under the CNNs framework, while in the second work, we demonstrate how we carry out the saliency detection task using new Capsule Networks.