Research Repository

SaliencyGAN: Deep Learning Semisupervised Salient Object Detection in the Fog of IoT

Wang, Chengjia and Dong, Shizhou and Zhao, Xiaofeng and Papanastasiou, Giorgos and Zhang, Heye and Yang, Guang (2020) 'SaliencyGAN: Deep Learning Semisupervised Salient Object Detection in the Fog of IoT.' IEEE Transactions on Industrial Informatics, 16 (4). 2667 - 2676. ISSN 1551-3203

[img]
Preview
Text
ALL_TII-19-2654.pdf - Accepted Version

Download (11MB) | Preview

Abstract

In modern Internet of Things (IoT), visual analysis and predictions are often performed by deep learning models. Salient object detection (SOD) is a fundamental preprocessing for these applications. Executing SOD on the fog devices is a challenging task due to the diversity of data and fog devices. To adopt convolutional neural networks (CNN) on fog-cloud infrastructures for SOD-based applications, we introduce a semisupervised adversarial learning method in this article. The proposed model, named as SaliencyGAN, is empowered by a novel concatenated generative adversarial network (GAN) framework with partially shared parameters. The backbone CNN can be chosen flexibly based on the specific devices and applications. In the meanwhile, our method uses both the labeled and unlabeled data from different problem domains for training. Using multiple popular benchmark datasets, we compared state-of-the-art baseline methods to our SaliencyGAN obtained with 10-100% labeled training data. SaliencyGAN gained performance comparable to the supervised baselines when the percentage of labeled data reached 30%, and outperformed the weakly supervised and unsupervised baselines. Furthermore, our ablation study shows that SaliencyGAN were more robust to the common “mode missing” (or “mode collapse”) issue compared to the selected popular GAN models. The visualized ablation results have proved that SaliencyGAN learned a better estimation of data distributions. To the best of our knowledge, this is the first IoT-oriented semisupervised SOD method.

Item Type: Article
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Elements
Date Deposited: 17 Jul 2020 09:16
Last Modified: 17 Jul 2020 10:15
URI: http://repository.essex.ac.uk/id/eprint/28150

Actions (login required)

View Item View Item