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

Wang, Chengjia; Dong, Shizhou; Zhao, Xiaofeng; Papanastasiou, Giorgos; Zhang, Heye; Yang, Guang

doi:10.1109/tii.2019.2945362

Cited by 100 publications

(51 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The BAM model [8], can perform "multiÑsingle" distillation tasks, but places limitation on network structures. Similar limits can be found in recent classifier amalgamation works 1 . A few recent works [21] [22] [23] has been proposed to unifying heterogeneous teacher classifiers.…”

Section: B Multi-teacher Knowledge Distillationsupporting

confidence: 78%

“…A few recent works [21] [22] [23] has been proposed to unifying heterogeneous teacher classifiers. Without a predefined dustbin class, [23] requires overlapped classes of objects recognized by teacher models, otherwise the model failed to find an optimal feature 1 A detailed comparison at https://github.com/zju-vipa/KamalEngine alignments. Both [22] and [23] learns to extract common feature representation using additional knowledge amalgamation networks.…”

Section: B Multi-teacher Knowledge Distillationmentioning

confidence: 99%

“…Deep learning has achieved tremendous successes in a wide range of visual applications [1]. Effective training of deep neural networks (DNN) often requires powerful computing hardware, availability of massive training data, and optimal hyper-parametric setups.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Industrial Cyber-Physical Systems-Based Cloud IoT Edge for Federated Heterogeneous Distillation

Wang

Yang

Papanastasiou

et al. 2021

IEEE Trans. Ind. Inf.

Self Cite

View full text Add to dashboard Cite

Deep convoloutional networks have been widely deployed in modern cyber-physical systems performing different visual classification tasks. As the fog and edge devices have different computing capacity and perform different sub-tasks, models trained for one device may not be deployable on another. Knowledge distillation technique can effectively compress well trained convolutional neural networks (CNN) into lightweight models suitable to different devices. However, due to privacy issue and transmission cost, manually annotated data for training the deep learning models are usually gradually collected and archived in different sites. Simply training a model on powerful cloud servers and compressing them for particular edge devices failed to use the distributed data stored at different sites. This offline training approach is also inefficient to deal with new data collected from the edge devices. To overcome these obstacles, we propose the heterogeneous brain storming (HBS) method for object recognition tasks in real-world IoT scenarios. Our method enables flexible bidirectional federated learning of heterogeneous models trained on distributed datasets with a new "brain storming" mechanism and optimizable temperature parameters. In our comparison experiments, this heterogeneous brain storming method outperformed multiple state-of-the-art single-model compression methods, as well as the newest multinetwork knowledge distillation methods with both homogeneous and heterogeneous classifiers. The ablation experiment results proved that the trainable temperature parameter into the conventional knowledge distillation loss can effectively ease the learning process of student networks in different methods. To the best of

show abstract

Section: B Multi-teacher Knowledge Distillationsupporting

confidence: 78%

Section: B Multi-teacher Knowledge Distillationmentioning

confidence: 99%

See 1 more Smart Citation

Industrial Cyber-Physical Systems-Based Cloud IoT Edge for Federated Heterogeneous Distillation

Wang

Yang

Papanastasiou

et al. 2021

IEEE Trans. Ind. Inf.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Each of the layer contains some neurons with activation functions that can be utilized to produce non-linear outputs. This methodology is said to be inspired by the neuron structure of the human brain [45,46].…”

Section: Deep Learningmentioning

confidence: 99%

Deep learning and big data technologies for IoT security

Amanullah

Habeeb

Nasaruddin

et al. 2020

Computer Communications

273

119

View full text Add to dashboard Cite

Technology has become inevitable in human life, especially the growth of Internet of Things (IoT), which enables communication and interaction with various devices. However, IoT has been proven to be vulnerable to security breaches. Therefore, it is necessary to develop fool proof solutions by creating new technologies or combining existing technologies to address the security issues. Deep learning, a branch of machine learning has shown promising results in previous studies for detection of security breaches. Additionally, IoT devices generate large volumes, variety, and veracity of data. Thus, when big data technologies are incorporated, higher performance and better data handling can be achieved. Hence, we have conducted a comprehensive survey on state-of-the-art deep learning, IoT security, and big data technologies. Further, a comparative analysis and the relationship among deep learning, IoT security, and big data technologies have also been discussed. Further, we have derived a thematic taxonomy from the comparative analysis of technical studies of the three aforementioned domains. Finally, we have identified and discussed the challenges in incorporating deep learning for IoT security using big data technologies and have provided directions to future researchers on the IoT security aspects. Contents * Corresponding author.

show abstract

“…Deepfill [17] employed a coarseto-refine training process and designed a contextual attention layer to improve its spatial consistency of perception. Saliencygan [18] was proposed for semi-supervised salient object detection. TPSDicyc [19] could generate synthesized images with unpaired and unaligned data.…”

Section: Introductionmentioning

confidence: 99%

Consecutive Context Perceive Generative Adversarial Networks for Serial Sections Inpainting

et al. 2020

View full text Add to dashboard Cite

Image inpainting is a hot topic in computer vision research and has been successfully applied to both traditional and digital mediums, such as oil paintings or old photos mending, image or video denoising and super-resolution. With the introduction of artificial intelligence (AI), a series of algorithms, represented by semantic inpainting, have been developed and better results were achieved. Medical image inpainting, as one of the most demanding applications, needs to meet both the visual effects and strict content correctness. 3D reconstruction of microstructures, based on serial sections, could provide more spatial information and help us understand the physiology or pathophysiology mechanism in histology study, in which extremely high-quality continuous images without any defects are required. In this paper, we proposed a novel Consecutive Context Perceive Generative Adversarial Networks (CCPGAN) for serial sections inpainting. Our method can learn semantic information from its neighboring image, and restore the damaged parts of serial sectioning images to maximum extent. Validated with 2 sets of serial sectioning images of mouse kidney, qualitative and quantitative results suggested that our method could robustly restore breakage of any size and location while achieving near realtime performance.

show abstract

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

Cited by 100 publications

References 23 publications

Industrial Cyber-Physical Systems-Based Cloud IoT Edge for Federated Heterogeneous Distillation

Industrial Cyber-Physical Systems-Based Cloud IoT Edge for Federated Heterogeneous Distillation

Deep learning and big data technologies for IoT security

Consecutive Context Perceive Generative Adversarial Networks for Serial Sections Inpainting

Contact Info

Product

Resources

About