FIN-GAN: Face Illumination Normalization via Retinex-based Self-supervised Learning and Conditional Generative Adversarial Network

2021 ◽  
Author(s):  
Yaocong Hu ◽  
Mingqi Lu ◽  
Chao Xie ◽  
Xiaobo Lu
Keyword(s):  
Supervised Learning ◽  
Illumination Normalization ◽  
Generative Adversarial Network ◽  
Adversarial Network

scholarly journals Generative Adversarial Networks-Based Semi-Supervised Automatic Modulation Recognition for Cognitive Radio Networks

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3913 ◽  
Author(s):  
Mingxuan Li ◽  
Ou Li ◽  
Guangyi Liu ◽  
Ce Zhang
Keyword(s):  
Deep Learning ◽  
Cognitive Radio ◽  
Supervised Learning ◽  
Rapid Development ◽  
Generative Adversarial Networks ◽  
Modulation Recognition ◽  
Learning Methods ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Automatic Modulation Recognition

With the recently explosive growth of deep learning, automatic modulation recognition has undergone rapid development. Most of the newly proposed methods are dependent on large numbers of labeled samples. We are committed to using fewer labeled samples to perform automatic modulation recognition in the cognitive radio domain. Here, a semi-supervised learning method based on adversarial training is proposed which is called signal classifier generative adversarial network. Most of the prior methods based on this technology involve computer vision applications. However, we improve the existing network structure of a generative adversarial network by adding the encoder network and a signal spatial transform module, allowing our framework to address radio signal processing tasks more efficiently. These two technical improvements effectively avoid nonconvergence and mode collapse problems caused by the complexity of the radio signals. The results of simulations show that compared with well-known deep learning methods, our method improves the classification accuracy on a synthetic radio frequency dataset by 0.1% to 12%. In addition, we verify the advantages of our method in a semi-supervised scenario and obtain a significant increase in accuracy compared with traditional semi-supervised learning methods.

scholarly journals A novel semi-supervised framework for UAV based crop/weed classification

PLoS ONE ◽  
2021 ◽  
Vol 16 (5) ◽  
pp. e0251008
Author(s):  
Shahbaz Khan ◽  
Muhammad Tufail ◽  
Muhammad Tahir Khan ◽  
Zubair Ahmad Khan ◽  
Javaid Iqbal ◽  
...  
Keyword(s):  
Supervised Learning ◽  
Precision Agriculture ◽  
Classification Systems ◽  
Training Data ◽  
Generative Adversarial Network ◽  
Training Time ◽  
Adversarial Network ◽  
Average Accuracy ◽  
High Resolution Images ◽  
Cost Efficient

Excessive use of agrochemicals for weed controlling infestation has serious agronomic and environmental repercussions associated. An appropriate amount of pesticide/ chemicals is essential for achieving the desired smart farming and precision agriculture (PA). In this regard, targeted weed control will be a critical component significantly helping in achieving the goal. A prerequisite for such control is a robust classification system that could accurately identify weed crops in a field. In this regard, Unmanned Aerial Vehicles (UAVs) can acquire high-resolution images providing detailed information for the distribution of weeds and offers a cost-efficient solution. Most of the established classification systems deploying UAV imagery are supervised, relying on image labels. However, this is a time-consuming and tedious task. In this study, the development of an optimized semi-supervised learning approach is proposed, offering a semi-supervised generative adversarial network for crops and weeds classification at early growth stage. The proposed algorithm consists of a generator that provides extra training data for the discriminator, which distinguishes weeds and crops using a small number of image labels. The proposed system was evaluated extensively on the Red Green Blue (RGB) images obtained by a quadcopter in two different croplands (pea and strawberry). The method achieved an average accuracy of 90% when 80% of training data was unlabeled. The proposed system was compared with several standards supervised learning classifiers and the results demonstrated that this technique could be applied for challenging tasks of crops and weeds classification, mainly when the labeled samples are small at less training time.

scholarly journals CR-GAN: Learning Complete Representations for Multi-view Generation

2018 ◽  
Author(s):  
Yu Tian ◽  
Xi Peng ◽  
Long Zhao ◽  
Shaoting Zhang ◽  
Dimitris N. Metaxas
Keyword(s):  
Supervised Learning ◽  
State Of The Art ◽  
Unlabeled Data ◽  
Challenging Problem ◽  
Generative Adversarial Network ◽  
Single View ◽  
Adversarial Network ◽  
Complete Representations ◽  
Wide Range ◽  
And Robotics

Generating multi-view images from a single-view input is an important yet challenging problem. It has broad applications in vision, graphics, and robotics. Our study indicates that the widely-used generative adversarial network (GAN) may learn ?incomplete? representations due to the single-pathway framework: an encoder-decoder network followed by a discriminator network.We propose CR-GAN to address this problem. In addition to the single reconstruction path, we introduce a generation sideway to maintain the completeness of the learned embedding space. The two learning paths collaborate and compete in a parameter-sharing manner, yielding largely improved generality to ?unseen? dataset. More importantly, the two-pathway framework makes it possible to combine both labeled and unlabeled data for self-supervised learning, which further enriches the embedding space for realistic generations. We evaluate our approach on a wide range of datasets. The results prove that CR-GAN significantly outperforms state-of-the-art methods, especially when generating from ?unseen? inputs in wild conditions.

Semi-supervised learning approach for malicious URL detection via adversarial learning1

2021 ◽  
pp. 1-10
Author(s):  
Jie Ling ◽  
Su Xiong ◽  
Yu Luo
Keyword(s):  
Supervised Learning ◽  
High Accuracy ◽  
Detection Accuracy ◽  
Resource Location ◽  
Generative Adversarial Network ◽  
Network Attack ◽  
Adversarial Network ◽  
Imbalance Problem ◽  
Large Numbers ◽  
Rapid Generation

Uniform Resource Location (URL) is the network unified resource location system that specifies the location and access method of resources on the Internet. At present, malicious URL has become one of the main means of network attack. How to detect malicious URL timely and accurately has become an engaging research topic. The recent proposed deep learning-based detection models can achieve high accuracy in simulations, but several problems are exposed when they are used in real applications. These models need a balanced labeled dataset for training, while collecting large numbers of the latest labeled URL samples is difficult due to the rapid generation of URL in the real application environment. In addition, in most randomly collected datasets, the number of benign URL samples and malicious URL samples is extremely unbalanced, as malicious URL samples are often rare. This paper proposes a semi-supervised learning malicious URL detection method based on generative adversarial network (GAN) to solve the above two problems. By utilizing the unlabeled URLs for model training in a semi-supervised way, the requirement of large numbers of labeled samples is weakened. And the imbalance problem can be relieved with the synthetic malicious URL generated by adversarial learning. Experimental results show that the proposed method outperforms the classic SVM and LSTM based methods. Specially, the proposed method can obtain high accuracy with insufficient labeled samples and unbalanced dataset. e.g., the proposed method can achieve 87.8% /91.9% detection accuracy when the number of labeled samples is reduced to 20% /40% of that of conventional methods.

Sign in / Sign up

Export Citation Format

Share Document