Inicio  /  Applied Sciences  /  Vol: 11 Par: 8 (2021)  /  Artículo
ARTÍCULO
TITULO

Adversarial Optimization-Based Knowledge Transfer of Layer-Wise Dense Flow for Image Classification

Doyeob Yeo    
Min-Suk Kim and Ji-Hoon Bae    

Resumen

A deep-learning technology for knowledge transfer is necessary to advance and optimize efficient knowledge distillation. Here, we aim to develop a new adversarial optimization-based knowledge transfer method involved with a layer-wise dense flow that is distilled from a pre-trained deep neural network (DNN). Knowledge distillation transferred to another target DNN based on adversarial loss functions has multiple flow-based knowledge items that are densely extracted by overlapping them from a pre-trained DNN to enhance the existing knowledge. We propose a semi-supervised learning-based knowledge transfer with multiple items of dense flow-based knowledge extracted from the pre-trained DNN. The proposed loss function would comprise a supervised cross-entropy loss for a typical classification, an adversarial training loss for the target DNN and discriminators, and Euclidean distance-based loss in terms of dense flow. For both pre-trained and target DNNs considered in this study, we adopt a residual network (ResNet) architecture. We propose methods of (1) the adversarial-based knowledge optimization, (2) the extended and flow-based knowledge transfer scheme, and (3) the combined layer-wise dense flow in an adversarial network. The results show that it provides higher accuracy performance in the improved target ResNet compared to the prior knowledge transfer methods.

 Artículos similares

       
 
Jingying Zhang and Tengfei Bao    
Crack detection is an important component of dam safety monitoring. Detection methods based on deep convolutional neural networks (DCNNs) are widely used for their high efficiency and safety. Most existing DCNNs with high accuracy are too complex for use... ver más
Revista: Water

 
Xiaoling Wang, Qi Kang, Mengchu Zhou, Zheng Fan and Aiiad Albeshri    
Multi-task optimization (MTO) is a novel emerging evolutionary computation paradigm. It focuses on solving multiple optimization tasks concurrently while improving optimization performance by utilizing similarities among tasks and historical optimization... ver más
Revista: Applied Sciences

 
Zhigang Song, Daisong Li, Zhongyou Chen and Wenqin Yang    
The unsupervised domain-adaptive vehicle re-identification approach aims to transfer knowledge from a labeled source domain to an unlabeled target domain; however, there are knowledge differences between the target domain and the source domain. To mitiga... ver más
Revista: Applied Sciences

 
Wajeeh Daher, Hussam Diab and Anwar Rayan    
In recent years, artificial intelligence (AI) has emerged as a valuable resource for teaching and learning, and it has also shown promise as a tool to help solve problems. A tool that has gained attention in education is ChatGPT, which supports teaching ... ver más
Revista: Information

 
Xinyi Liu, Baofeng Zhang and Na Liu    
Both transformer and one-stage detectors have shown promising object detection results and have attracted increasing attention. However, the developments in effective domain adaptive techniques in transformer and one-stage detectors still have not been w... ver más
Revista: Applied Sciences