Semi-supervised Generative Adversarial Research Articles

An Optimized Semi-Supervised Generative Adversarial Network Rice Extraction Method Based on Time-Series Sentinel Images

In response to the limitations of meteorological conditions in global rice growing areas and the high cost of annotating samples, this paper combines the Vertical-Vertical (VV) polarization and Vertical-Horizontal (VH) polarization backscatter features extracted from Sentinel-1 synthetic aperture radar (SAR) images and the NDVI, NDWI, and NDSI spectral index features extracted from Sentinel-2 multispectral images. By leveraging the advantages of an optimized Semi-Supervised Generative Adversarial Network (optimized SSGAN) in combining supervised learning and semi-supervised learning, rice extraction can be achieved with fewer annotated image samples. Within the optimized SSGAN framework, we introduce a focal-adversarial loss function to enhance the learning process for challenging samples; the generator module employs the Deeplabv3+ architecture, utilizing a Wide-ResNet network as its backbone while incorporating dropout layers and dilated convolutions to improve the receptive field and operational efficiency. Experimental results indicate that the optimized SSGAN, particularly when utilizing a 3/4 labeled sample ratio, significantly improves rice extraction accuracy, leading to a 5.39% increase in Mean Intersection over Union (MIoU) and a 2.05% increase in Overall Accuracy (OA) compared to the highest accuracy achieved before optimization. Moreover, the integration of SAR and multispectral data results in an OA of 93.29% and an MIoU of 82.10%, surpassing the performance of single-source data. These findings provide valuable insights for the extraction of rice information in global rice-growing regions.

Wi-Fi Fingerprint Indoor Localization by Semi-Supervised Generative Adversarial Network.

Wi-Fi fingerprint indoor localization uses Wi-Fi signal strength measurements obtained from a number of access points. This method needs manual data collection across a positioning area and an annotation process to label locations to the measurement sets. To reduce the cost and effort, this paper proposes a Wi-Fi Semi-Supervised Generative Adversarial Network (SSGAN), which produces artificial but realistic trainable fingerprint data. The Wi-Fi SSGAN is based on a deep learning, which is extended from GAN in a semi-supervised learning manner. It is designed to create location-labeled Wi-Fi fingerprint data, which is different to unlabeled data generation by a normal GAN. Also, the proposed Wi-Fi SSGAN network includes a positioning model, so it does not need a external positioning method. When the Wi-Fi SSGAN is applied to a multi-story landmark localization, the experimental results demonstrate a 35% more accurate performance in comparison to a standard supervised deep neural network.

An Accurate Recognition Method for Landslides Based on a Semi-Supervised Generative Adversarial Network: A Case Study in Lanzhou City

With the development of computer technology, landslide recognition based on machine learning methods has been widely applied in geological disaster management and research. However, in landslide identification, the problems of an insufficient number of samples and an imbalance of samples are often ignored; that is, landslide samples are much smaller than non-landslide samples. In order to solve this problem, taking the main urban area of Lanzhou City as an example, this paper proposes to construct a semi-supervised generated countermeasure network (SSGAN) model, which aims to achieve high performance with a limited number of labeled samples for precise landslide identification, and to help prevent and reduce the harm caused by disasters. In order to express the environmental characteristics of landslide development and the optical texture features of landslide occurrence, the study constructs three sets of samples to represent landslide features, including a landslide influencing factor sample set, a Sentinel-2A optical remote sensing sample set, a joint influencing factor and Sentinel-2A sample set. The three kinds of sample sets are transferred to SSGAN for training to form a comparative study. The results show that the joint sample set has excellent feature results in discriminator and generator. Through the experimental comparison, the model proposed in this paper is compared with the model without semi-supervised generated confrontation training. The experimental results show that the proposed method is better than the unsupervised adversarial learning model in terms of accuracy, F1 score, Kappa coefficient, and MIoU. A total of 160 landslides have been identified in the study area, with a total area of 10.328 km2, with an accuracy rate of 83%. Therefore, the generated results are accurate and reliable, and show that SSGAN can better distinguish landslides from non-landslides in an image, under the condition of obtaining a large number of unmarked environmental features; enhance the effect of landslide classification in complex geographical environment; and then put forward effective suggestions for the prevention and control of landslides and geological disasters in the main urban area of Lanzhou.

MITIGATING OVER-SATURATED FLUORESCENCE IMAGES THROUGH A SEMI-SUPERVISED GENERATIVE ADVERSARIAL NETWORK.

Multiplex immunofluorescence (MxIF) imaging is a critical tool in biomedical research, offering detailed insights into cell composition and spatial context. As an example, DAPI staining identifies cell nuclei, while CD20 staining helps segment cell membranes in MxIF. However, a persistent challenge in MxIF is saturation artifacts, which hinder single-cell level analysis in areas with over-saturated pixels. Traditional gamma correction methods for fixing saturation are limited, often incorrectly assuming uniform distribution of saturation, which is rarely the case in practice. This paper introduces a novel approach to correct saturation artifacts from a data-driven perspective. We introduce a two-stage, high-resolution hybrid generative adversarial network (HDmixGAN), which merges unpaired (CycleGAN) and paired (pix2pixHD) network architectures. This approach is designed to capitalize on the available small-scale paired data and the more extensive unpaired data from costly MxIF data. Specifically, we generate pseudo-paired data from large-scale unpaired over-saturated datasets with a CycleGAN, and train a Pix2pixGAN using both small-scale real and large-scale synthetic data derived from multiple DAPI staining rounds in MxIF. This method was validated against various baselines in a downstream nuclei detection task, improving the F1 score by 6% over the baseline. This is, to our knowledge, the first focused effort to address multi-round saturation in MxIF images, offering a specialized solution for enhancing cell analysis accuracy through improved image quality. The source code and implementation of the proposed method are available at https://github.com/MASILab/DAPIArtifactRemoval.git.

Multilingual Hate Speech Detection: A Semi-Supervised Generative Adversarial Approach.

Social media platforms have surpassed cultural and linguistic boundaries, thus enabling online communication worldwide. However, the expanded use of various languages has intensified the challenge of online detection of hate speech content. Despite the release of multiple Natural Language Processing (NLP) solutions implementing cutting-edge machine learning techniques, the scarcity of data, especially labeled data, remains a considerable obstacle, which further requires the use of semisupervised approaches along with Generative Artificial Intelligence (Generative AI) techniques. This paper introduces an innovative approach, a multilingual semisupervised model combining Generative Adversarial Networks (GANs) and Pretrained Language Models (PLMs), more precisely mBERT and XLM-RoBERTa. Our approach proves its effectiveness in the detection of hate speech and offensive language in Indo-European languages (in English, German, and Hindi) when employing only 20% annotated data from the HASOC2019 dataset, thereby presenting significantly high performances in each of multilingual, zero-shot crosslingual, and monolingual training scenarios. Our study provides a robust mBERT-based semisupervised GAN model (SS-GAN-mBERT) that outperformed the XLM-RoBERTa-based model (SS-GAN-XLM) and reached an average F1 score boost of 9.23% and an accuracy increase of 5.75% over the baseline semisupervised mBERT model.

A semi-supervised learning approach for semantic parsing boosted by BERT word embedding

In the modern world, structured and semi-structured knowledge bases hold a considerable amount of data. There-fore, people who are familiar with formal query languages should not be the only ones who can efficiently and clearly query them. Semantic Parsing (SP) is converting natural language utterances into formal meaning representations. The paper suggests a model for SP that uses a novel method of utilizing the Semi-Supervised Generative Adversarial Network (SS-GAN) to enhance the classifier performance. The proposed SS-GAN extends the fine-tuning of word embedding architectures using unlabeled examples in a generative adversarial environment. We provide a regularization strategy for addressing the mode missing problem and unstable training in SS-GAN. The main viewpoint is to use the extracted feature vectors from the discriminator. Hence, the generator produces outputs by aiding the discriminator’s learned features. A reconstruction loss is added to the loss function of the SS-GAN to drive the genera-tor to reconstruct outputs from the discriminator’s features, hence steering the generator toward actual data configurations. The proposed reconstruction loss improves the performance of SS-GAN, produces high-quality outputs, and may be combined with other regularization loss functions to improve the performance of diverse GANs. We employ BERT word embedding for our model, which can be included in a downstream task and fine-tuned as a model, while the pre-trained BERT model can capture various linguistic properties. We examine the suggested model using the WikiSQL and SparC datasets, and the analysis findings reveal our model outperforms its rivals. The findings from our experiments indicate that the need for labeled samples can be minimized, down to as few as 100 instances, while still achieving commendable classification outcomes.

Semi-supervised community detection method based on generative adversarial networks

Community detection in complex networks often suffers from insufficient data and limited utilization of prior knowledge. In this paper we propose “Semi-supervised Generative Adversarial Network” (GANSE), a novel algorithm that integrates Generative Adversarial Networks (GANs) and semi-supervised learning to address these challenges. This method addresses the issues above through a multi-step process. Initially, the network is rewired using vertex similarity metrics, thereby enhancing its structural integrity. Subsequently, a novel generative adversarial network model is designed, and our model facilitates the reconstruction of the network, thereby yielding partitions. Which form the basis for identifying core communities. Additionally, the local clustering coefficient is incorporated as a reward signal and injected into the node selection process. Moreover, isolated nodes are reallocated, ultimately culminating in the derivation of the final community structure. Experimental results on four large real-life datasets demonstrate the clear superiority of the proposed algorithm in terms of F1 and Jaccard metrics when compared to existing algorithms. Notably, our GANSE method outperforms the traditional algorithms in networks with “missing data”. Thus showing its robustness and effectiveness in real-world incomplete datasets. Our findings highlight the potential of GANs and semi-supervised learning for enhancing community detection accuracy in complex networks.

Leveraging Semi-Supervised Generative Adversarial Networks to Address Data Scarcity Using Decision Boundary Analysis

Leveraging Semi-Supervised Generative Adversarial Networks to Address Data Scarcity Using Decision Boundary Analysis

Fetal MRI Artifacts: Semi-Supervised Generative Adversarial Neural Network for Motion Artifacts Reducing in Fetal Magnetic Resonance Images

Fetal MRI Artifacts: Semi-Supervised Generative Adversarial Neural Network for Motion Artifacts Reducing in Fetal Magnetic Resonance Images

Epileptic Seizure Detection Based on Semi-supervised Generative Adversarial Network

Since the manual diagnosis of electroencephalograph (EEG) recordings requires a lot of labor and material costs for clinical seizure detection, the annotation for seizure data is of great challenge for seizure detection. To tackle the issue of small samples of epilepsy-labeled data, we propose a semi-supervised generative adversarial network-based seizure detection method. To begin with, a Butterworth filter is used to preprocess the EEG, and the filtered EEG signal is input into the SGAN model. Finally, the output of the SGAN model is subjected to post-processing operations including averaging filtering and threshold comparison, and the discriminative result of whether the tested EEG is a seizure is output. The method achieved an average sensitivity of 90.36%, an average specificity of 93.72%, and an average accuracy of 93.72% in the CHB-MIT EEG dataset. Experiments demonstrate that the semi-supervised generative adversarial network has more accurate classification performance in epilepsy detection.

Emotion Recognition Based on Electroencephalogram Using Semi-supervised Generative Adversarial Network.

This paper proposes the use of Semi-supervised Generative Adversarial Network (SGAN) to take advantage of the large amount of unlabeled electroencephalogram (EEG) spectrogram data in improving the classifier's accuracy in emotion recognition. The use of SGAN led the discriminator network to not just learn in a supervised fashion from the small amount of labeled data to distinguish among the different target classes, but also make use of the true unlabeled data to distinguish them from the synthetic ones generated by the generator network. This additional ability to distinguish true and fake samples forces the network to focus only on features that are present on a true sample to distinguish the classes, thereby improving generalization and overall accuracy. An ablation study is devised, where the SGAN classifier is compared to a mere discriminator network without the GAN architecture. The 80% : 20% validation method was employed to classify the EEG spectrogram of 50 participants gathered by Kaohsiung Medical University into two emotion labels in the valence dimension: positive and negative. The proposed method achieved an accuracy of 84.83% given only 50% labeled data, which is not just better than the baseline discriminator network which achieved 83.5% accuracy, but is also better than many previous studies at accuracies around 78%. This demonstrates the ability of SGAN in improving discriminator network's accuracy by training it to also distinguish between the unlabeled true sample and synthetic data.Clinical Relevance- The use of EEG in emotion recognition has seen growing interest due to its ease of access. However, the large amount of labeled data required to train an accurate model has been the limiting factor as databases in the area of emotion recognition with EEG is still relatively small. This paper proposes the use of SGAN to allow using large amount of unlabeled EEG data to improve the recognition rate.

Enhancing Cyber Threat Identification in Open-Source Intelligence Feeds Through an Improved Semi-Supervised Generative Adversarial Learning Approach With Contrastive Learning

Enhancing Cyber Threat Identification in Open-Source Intelligence Feeds Through an Improved Semi-Supervised Generative Adversarial Learning Approach With Contrastive Learning

Abnormal Transactions Detection in the Ethereum Network Using Semi-Supervised Generative Adversarial Networks

Abnormal Transactions Detection in the Ethereum Network Using Semi-Supervised Generative Adversarial Networks

Transfer Learning-Based Semi-Supervised Generative Adversarial Network for Malaria Classification

Malaria is a lethal disease responsible for thousands of deaths worldwide every year. Manual methods of malaria diagnosis are time-consuming that require a great deal of human expertise and efforts. Computer-based automated diagnosis of diseases is progressively becoming popular. Although deep learning models show high performance in the medical field, it demands a large volume of data for training which is hard to acquire for medical problems. Similarly, labeling of medical images can be done with the help of medical experts only. Several recent studies have utilized deep learning models to develop efficient malaria diagnostic system, which showed promising results. However, the most common problem with these models is that they need a large amount of data for training. This paper presents a computer-aided malaria diagnosis system that combines a semi-supervised generative adversarial network and transfer learning. The proposed model is trained in a semi-supervised manner and requires less training data than conventional deep learning models. Performance of the proposed model is evaluated on a publicly available dataset of blood smear images (with malaria-infected and normal class) and achieved a classification accuracy of 96.6%.

CMOS-GAN: Semi-supervised Generative Adversarial Model for Cross-Modality Face Image Synthesis.

Cross-modality face image synthesis such as sketch-to-photo, NIR-to-RGB, and RGB-to-depth has wide applications in face recognition, face animation, and digital entertainment. Conventional cross-modality synthesis methods usually require paired training data, i.e., each subject has images of both modalities. However, paired data can be difficult to acquire, while unpaired data commonly exist. In this paper, we propose a novel semi-supervised cross-modality synthesis method (namely CMOS-GAN), which can leverage both paired and unpaired face images to learn a robust cross-modality synthesis model. Specifically, CMOS-GAN uses a generator of encoder-decoder architecture for new modality synthesis. We leverage pixel-wise loss, adversarial loss, classification loss, and face feature loss to exploit the information from both paired multi-modality face images and unpaired face images for model learning. In addition, since we expect the synthetic new modality can also be helpful for improving face recognition accuracy, we further use a modified triplet loss to retain the discriminative features of the subject in the synthetic modality. Experiments on three cross-modality face synthesis tasks (NIR-to-VIS, RGB-to-depth, and sketch-to-photo) show the effectiveness of the proposed approach compared with the state-of-the-art. In addition, we also collect a large-scale RGB-D dataset (VIPL-MumoFace-3K) for the RGB-to-depth synthesis task. We plan to open-source our code and VIPL-MumoFace-3K dataset to the community.

Medical Image Classification Based on Semi-Supervised Generative Adversarial Network and Pseudo-Labelling

Deep learning has substantially improved the state-of-the-art in object detection and image classification. Deep learning usually requires large-scale labelled datasets to train the models; however, due to the restrictions in medical data sharing and accessibility and the expensive labelling cost, the application of deep learning in medical image classification has been dramatically hindered. In this study, we propose a novel method that leverages semi-supervised adversarial learning and pseudo-labelling to incorporate the unlabelled images in model learning. We validate the proposed method on two public databases, including ChestX-ray14 for lung disease classification and BreakHis for breast cancer histopathological image diagnosis. The results show that our method achieved highly effective performance with an accuracy of 93.15% while using only 30% of the labelled samples, which is comparable to the state-of-the-art accuracy for chest X-ray classification; it also outperformed the current methods in multi-class breast cancer histopathological image classification with a high accuracy of 96.87%.

Research on a Defecation Pre-Warning Algorithm for the Disabled Elderly Based on a Semi-Supervised Generative Adversarial Network.

The elderly population in China is continuously increasing, and the disabled account for a large proportion of the elderly population. An effective solution is urgently needed for incontinence among disabled elderly people. Compared with disposable adult diapers, artificial sphincter implantation and medication for incontinence, the defecation pre-warning method is more flexible and convenient. However, due to the complex human physiology and individual differences, its development is limited. Based on the aging trend of the population and clinical needs, this paper proposes a bowel sound acquisition system and a defecation pre-warning method and system based on a semi-supervised generative adversarial network. A network model was established to predict defecation using bowel sounds. The experimental results show that the proposed method can effectively classify bowel sounds with or without defecation tendency, and the accuracy reached 94.4%.

Fast COVID-19 versus H1N1 screening using Optimized Parallel Inception

COVID-19 and swine-origin influenza A (H1N1) are both pandemics that sparked significant concern worldwide. Since these two diseases have common symptoms, a fast COVID-19 versus H1N1 screening helps better manage patients at healthcare facilities. We present a novel deep model, called Optimized Parallel Inception, for fast screening of COVID-19 and H1N1 patients. We also present a Semi-supervised Generative Adversarial Network (SGAN) to address the problem related to the smaller size of the COVID-19 and H1N1 research data. To evaluate the proposed models, we have merged two separate COVID-19 and H1N1 data from different sources to build a new dataset. The created dataset includes 4,383 positive COVID-19 cases, 989 positive H1N1 cases, and 1,059 negative cases. We applied SGAN on this dataset to remove issues related to unequal class densities. The experimental results show that the proposed model’s screening accuracy is 99.2% and 99.6% for COVID-19 and H1N1, respectively. According to our analysis, the most significant symptoms and underlying chronic diseases for COVID-19 versus H1N1 screening are dry cough, breathing problems, diabetes, and gastrointestinal.

Development and Clinical Validation of Semi-Supervised Generative Adversarial Networks for Detection of Retinal Disorders in Optical Coherence Tomography Images Using Small Dataset.

To develop and test semi-supervised generative adversarial networks (GANs) that detect retinal disorders on optical coherence tomography (OCT) images using a small-labeled dataset. From a public database, we randomly chose a small supervised dataset with 400 OCT images (100 choroidal neovascularization, 100 diabetic macular edema, 100 drusen, and 100 normal) and assigned all other OCT images to unsupervised dataset (107,912 images without labeling). We adopted a semi-supervised GAN and a supervised deep learning (DL) model for automatically detecting retinal disorders from OCT images. The performance of the 2 models was compared in 3 testing datasets with different OCT devices. The evaluation metrics included accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curves. The local validation dataset included 1000 images with 250 from each category. The independent clinical dataset included 366 OCT images using Cirrus OCT Shanghai Shibei Hospital and 511 OCT images using RTVue OCT from Xinhua Hospital respectively. The semi-supervised GANs classifier achieved better accuracy than supervised DL model (0.91 vs 0.86 for local cell validation dataset, 0.91 vs 0.86 in the Shanghai Shibei Hospital testing dataset, and 0.93 vs 0.92 in Xinhua Hospital testing dataset). For detecting urgent referrals (choroidal neo-vascularization and diabetic macular edema) from nonurgent referrals (drusen and normal) on OCT images, the semi-supervised GANs classifier also achieved better area under the receiver operating characteristic curves than supervised DL model (0.99 vs 0.97, 0.97 vs 0.96, and 0.99 vs 0.99, respectively). A semi-supervised GAN can achieve better performance than that of a supervised DL model when the labeled dataset is limited. The current study offers utility to various research and clinical studies using DL with relatively small datasets. Semi-supervised GANs can detect retinal disorders from OCT images using relatively small dataset.

Leveraging Google Earth Engine and Semi-Supervised Generative Adversarial Networks to Assess Initial Burn Severity in Forest

Mapping and monitoring initial burn severity is a critical aspect of forest management and landscape restoration. Recently, supervised learning has achieved great success in evaluating the post-fire forest condition, but plenty of labeled samples are needed to carry out training for supervised learning. However, due to the limitation of accessible labeled data, it is often arduous to put supervised learning into practice in the remote sensing field. In this paper, a novel semi-unsupervised image classification framework by using generative adversarial networks under the Google Earth Engine (GEE) platform is proposed to undertake the burn severity assessment with limited samples. The generative model can produce additional adversarial samples that look like the real samples; therefore, the discriminative model gains better classification capabilities in burn severity assessment with the extra training data provided by the generator. The detailed evaluation and comparative experiments are done in the context of post-fire assessment on eleven forest fires in northern California in the United States. The experimental results demonstrate that our approach significantly outperforms the two other most well-known methods.