STNet: Selective Tuning of Convolutional Networks for Object Localization

• Main Authors: Biparva, Mahdi, Tsotsos, John
• Format: Journal Article
• Language: English
• Published: 21-08-2017
• Subjects: Computer Science - Computer Vision and Pattern Recognition
• DOI: 10.48550/arxiv.1708.06418

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.