Journal
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
Volume 16, Issue 4, Pages 2667-2676Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2019.2945362
Keywords
Convolutional neural networks (CNNs); deep learning; generative adversarial network (GAN); Internet of Things (IoT); salient object detection (SOD)
Categories
Funding
- Innovation funding of Guangdong Province [2018A050506031, 2019B010110001]
- Fundamental Research Funds for the Central Universities
- National Natural Science Foundation of China [U1801265, 61771464]
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available