2017/08/21 by Mahdi Biparva, Biparva, Mahdi, John Tsotsos +1
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Visual Attention and Saliency Detection #cs.CV
paper · pdf · doi:10.48550/arxiv.1708.06418
arxiv created 2017/08/21 · openalex publication_date 2017/08/21 · arxiv updated 2017/08/23 · openalex created_date 2020/10/01 · openalex updated_date 2026/07/28
Visual attention modeling has recently gained momentum in developing visual hierarchies provided by Convolutional Neural Networks. Despite recent successes of feedforward processing on the abstraction of concepts form raw images, the inherent nature of feedback processing has remained computationally controversial. Inspired by the computational models of covert visual attention, we propose the Selective Tuning of Convolutional Networks (STNet). It is composed of both streams of Bottom-Up and Top-Down information processing to selectively tune the visual representation of Convolutional networks. We experimentally evaluate the performance of STNet for the weakly-supervised localization task on the ImageNet benchmark dataset. We demonstrate that STNet not only successfully surpasses the state-of-the-art results but also generates attention-driven class hypothesis maps.