Hybrid Cross Deep Network for Domain Adaptation and Energy Saving in Visual Internet of Things

Abstract

Recently, Visual Internet of Things (VIoT) has become a fast-growing field based on various applications. In this paper, we focus on two critical challenges for applications in VIoT, i.e., domain adaptation and energy saving. The images captured by various visual sensors in VIoT appear quite different due to changes in visual sensor locations, visual sensor settings, image resolutions, and illuminations. Meanwhile, VIoT generates a number of images, and transmitting original images would take up much bandwidth. In order to effectively classify such images and save energy, we propose a novel deep model named hybrid cross deep network (HCDN), which could learn domain-invariant and discriminative features for images in VIoT. The proposed HCDN is designed to contain the cross regularization loss and the classification loss. Moreover, it is also trained with images from different visual sensors. Specifically, the cross regularization loss selects the triplet samples from the source domain and the target domain, and adopts the calibration parameter to align the difference between two domains. We employ the vector extracted from the proposed HCDN to represent each image, which requires a smaller storage capacity than the original images. Energy consumption will be reduced when we transmit such vectors to the intelligent visual label system for image classification in VIoT. The proposed HCDN is verified on two domain adaptation datasets, and the experimental results prove its effectiveness.