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

• Published in: IEEE transactions on industrial informatics Vol. 16; no. 4; pp. 2667 - 2676
• Main Authors: Wang, Chengjia, Dong, Shizhou, Zhao, Xiaofeng, Papanastasiou, Giorgos, Zhang, Heye, Yang, Guang
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01-04-2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Ablation; Artificial neural networks; Collapse; Computational modeling; Convolutional neural networks (CNNs); Data models; Deep learning; Electronic devices; Feature extraction; Gallium nitride; generative adversarial network (GAN); Internet of Things; Internet of Things (IoT); Machine learning; Object recognition; Salience; salient object detection (SOD); Training
• ISSN: 1551-3203; 1941-0050
• DOI: 10.1109/TII.2019.2945362

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.