Generative Learning Method Research Articles

Predicting Late Gadolinium Enhancement of Acute Myocardial Infarction in Contrast-Free Cardiac Cine MRI Using Deep Generative Learning.

Late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) is a standard technique for diagnosing myocardial infarction (MI), which, however, poses risks due to gadolinium contrast usage. Techniques enabling MI assessment based on contrast-free CMR are desirable to overcome the limitations associated with contrast enhancement. We introduce a novel deep generative learning method, termed cine-generated enhancement (CGE), which transforms standard contrast-free cine CMR into LGE-equivalent images for MI assessment. CGE features with multislice spatiotemporal feature extractor, enhancement contrast modulation, and sophisticated loss function. Data from 430 patients with acute MI from 3 centers were collected. After image quality control, 1525 pairs (289 patients) of center I were used for training, and 293 slices (52 patients) of the same center were reserved for internal testing. The 40 patients (401 slices) of the other 2 centers were used for external testing. The CGE robustness was further tested in 20 normal subjects in a public cine CMR data set. CGE images were compared with LGE for image quality assessment and MI quantification regarding scar size and transmurality. The CGE method produced images of superior quality to LGE in both internal and external data sets. There was a significant (P<0.001) correlation between CGE and LGE measurements of scar size (Pearson correlation, 0.79/0.80; intraclass correlation coefficient, 0.79/0.77) and transmurality (Pearson correlation, 0.76/0.64; intraclass correlation coefficient, 0.76/0.63) in internal/external data set. Considering all data sets, CGE demonstrated high sensitivity (91.27%) and specificity (95.83%) in detecting scars. Realistic enhancement images were obtained for the normal subjects in the public data set without false positive subjects. CGE achieved superior image quality to LGE and accurate scar delineation in patients with acute MI of both internal and external data sets. CGE can significantly simplify the CMR examination, reducing scan times and risks associated with gadolinium-based contrasts, which are crucial for acute patients.

Research on personalised knowledge graph recommendation algorithm based on self-supervised learning

A recommendation algorithm that integrates generative graph self-supervised learning and contrastive graph self-supervised learning is proposed in this paper to address the issues of noisy data and graph incompleteness in knowledge graphs. Firstly, implicit semantics are captured by the self-supervised generative learning method through the masking and reconstruction of the edges of knowledge graph triples. Secondly, a multi-level contrastive learning method is proposed, which includes strategies for edge deletion and feature dropout in the graph structure and embedding layers, respectively.Finally, a contrastive loss function is introduced for contrastive learning to improve the quality of the embedded representations, and the BPR loss is incorporated and combined with the loss from the graph self-supervised learning module to optimize the overall performance of the recommender system. The results demonstrate that on the Last.fm, MovieLens, and Yelp2018 datasets, the model proposed in this paper significantly improves Recall and NDCG evaluation metrics compared to other traditional methods.

Federated variational generative learning for heterogeneous data in distributed environments

Distributedly training models across diverse clients with heterogeneous data samples can significantly impact the convergence of federated learning. Various novel federated learning methods address these challenges but often require significant communication resources and local computational capacity, leading to reduced global inference accuracy in scenarios with imbalanced label data distribution and quantity skew. To tackle these challenges, we propose FedVGL, a Federated Variational Generative Learning method that directly trains a local generative model to learn the distribution of local features and improve global target model inference accuracy during aggregation, particularly under conditions of severe data heterogeneity. FedVGL facilitates distributed learning by sharing generators and latent vectors with the global server, aiding in global target model training from mapping local data distribution to the variational latent space for feature reconstruction. Additionally, FedVGL implements anonymization and encryption techniques to bolster privacy during generative model transmission and aggregation. In comparison to vanilla federated learning, FedVGL minimizes communication overhead, demonstrating superior accuracy even with minimal communication rounds. It effectively mitigates model drift in scenarios with heterogeneous data, delivering improved target model training outcomes. Empirical results establish FedVGL's superiority over baseline federated learning methods under severe label imbalance and data skew condition. In a Label-based Dirichlet Distribution setting with α=0.01 and 10 clients using the MNIST dataset, FedVGL achieved an exceptional accuracy over 97% with the VGG-9 target model.

Unbiasing Enhanced Sampling on a High-Dimensional Free Energy Surface with a Deep Generative Model.

Biased enhanced sampling methods that utilize collective variables (CVs) are powerful tools for sampling conformational ensembles. Due to their large intrinsic dimensions, efficiently generating conformational ensembles for complex systems requires enhanced sampling on high-dimensional free energy surfaces. While temperature-accelerated molecular dynamics (TAMD) can trivially adopt many CVs in a simulation, unbiasing the simulation to generate unbiased conformational ensembles requires accurate modeling of a high-dimensional CV probability distribution, which is challenging for traditional density estimation techniques. Here we propose an unbiasing method based on the score-based diffusion model, a deep generative learning method that excels in density estimation across complex data landscapes. We demonstrate that this unbiasing approach, tested on multiple TAMD simulations, significantly outperforms traditional unbiasing methods and can generate accurate unbiased conformational ensembles. With the proposed approach, TAMD can adopt CVs that focus on improving sampling efficiency and the proposed unbiasing method enables accurate evaluation of ensemble averages of important chemical features.

DanceAnyWay: Synthesizing Beat-Guided 3D Dances with Randomized Temporal Contrastive Learning

We present DanceAnyWay, a generative learning method to synthesize beat-guided dances of 3D human characters synchronized with music. Our method learns to disentangle the dance movements at the beat frames from the dance movements at all the remaining frames by operating at two hierarchical levels. At the coarser "beat" level, it encodes the rhythm, pitch, and melody information of the input music via dedicated feature representations only at the beat frames. It leverages them to synthesize the beat poses of the target dances using a sequence-to-sequence learning framework. At the finer "repletion" level, our method encodes similar rhythm, pitch, and melody information from all the frames of the input music via dedicated feature representations. It generates the full dance sequences by combining the synthesized beat and repletion poses and enforcing plausibility through an adversarial learning framework. Our training paradigm also enforces fine-grained diversity in the synthesized dances through a randomized temporal contrastive loss, which ensures different segments of the dance sequences have different movements and avoids motion freezing or collapsing to repetitive movements. We evaluate the performance of our approach through extensive experiments on the benchmark AIST++ dataset and observe improvements of about 7%-12% in motion quality metrics and 1.5%-4% in motion diversity metrics over the current baselines, respectively. We also conducted a user study to evaluate the visual quality of our synthesized dances. We noted that, on average, the samples generated by our method were about 9-48% more preferred by the participants and had a 4-27% better five-point Likert-scale score over the best available current baseline in terms of motion quality and synchronization. Our source code and project page are available at https://github.com/aneeshbhattacharya/DanceAnyWay.

A knowledge-based learning framework for self-supervised pre-training towards enhanced recognition of biomedical microscopy images

Self-supervised pre-training has become the priory choice to establish reliable neural networks for automated recognition of massive biomedical microscopy images, which are routinely annotation-free, without semantics, and without guarantee of quality. Note that this paradigm is still at its infancy and limited by closely related open issues: (1) how to learn robust representations in an unsupervised manner from unlabeled biomedical microscopy images of low diversity in samples? and (2) how to obtain the most significant representations demanded by a high-quality segmentation? Aiming at these issues, this study proposes a knowledge-based learning framework (TOWER) towards enhanced recognition of biomedical microscopy images, which works in three phases by synergizing contrastive learning and generative learning methods: (1) Sample Space Diversification: Reconstructive proxy tasks have been enabled to embed a priori knowledge with context highlighted to diversify the expanded sample space; (2) Enhanced Representation Learning: Informative noise-contrastive estimation loss regularizes the encoder to enhance representation learning of annotation-free images; (3) Correlated Optimization: Optimization operations in pre-training the encoder and the decoder have been correlated via image restoration from proxy tasks, targeting the need for semantic segmentation. Experiments have been conducted on public datasets of biomedical microscopy images against the state-of-the-art counterparts (e.g., SimCLR and BYOL), and results demonstrate that: TOWER statistically excels in all self-supervised methods, achieving a Dice improvement of 1.38 percentage points over SimCLR. TOWER also has potential in multi-modality medical image analysis and enables label-efficient semi-supervised learning, e.g., reducing the annotation cost by up to 99% in pathological classification.

Effectiveness of generative learning strategies in independent study of english using mobile technologies

The aim of the research is to determine and evaluate the practical impact of the educational concept of generative learning in independent study of the English language with the development of the most appropriate and effective educational system. The following methods were used to achieve the aim of the research: EF SET testing, correlation analysis, statistical and mathematical forecast models. Empirical component of the research and the analytical interpretation of the results indicate a positive effect in the application of generative methods of learning English. It is quantified by an improved dynamics of learning English for students of the experimental group (relative to the indicators of the control group) —2.915 times. Performance for the final test for the group which learned using typical methods was 3.06%. The relevant indicators for the group that received focal knowledge by generative learning methods were 8.92%. The results of the study indicate the practical impact of the concept of generative learning on the effectiveness of learning English, and the significant potential for other applications. It is advisable to conduct repeated empirical studies in other educational institutions and other educational subjects taking into account the established facts. The results of those studies will be the ground for developing a generalized educational standard, which will be proposed by the Ministry of Education and Culture of Ukraine for integration and implementation into approved teaching methods.

Tree Species Classification Based on Self-Supervised Learning with Multisource Remote Sensing Images

In order to solve the problem of manual labeling in semi-supervised tree species classification, this paper proposes a pixel-level self-supervised learning model named M-SSL (multisource self-supervised learning), which takes the advantage of the information of plenty multisource remote sensing images and self-supervised learning methods. Based on hyperspectral images (HSI) and multispectral images (MSI), the features were extracted by combining generative learning methods with contrastive learning methods. Two kinds of multisource encoders named MAAE (multisource AAE encoder) and MVAE (multisource VAE encoder) were proposed, respectively, which set up pretext tasks to extract multisource features as data augmentation. Then the features were discriminated by the depth-wise cross attention module (DCAM) to enhance effective ones. At last, joint self-supervised methods output the tress species classification map to find the trade-off between providing negative samples and reducing the amount of computation. The M-SSL model can learn more representative features in downstream tasks. By employing the feature cross-fusion process, the low-dimensional information of the data is simultaneously learned in a unified network. Through the validation of three tree species datasets, the classification accuracy reached 78%. The proposed method can obtain high-quality features and is more suitable for label-less tree species classification.

An asymmetrical-structure auto-encoder for unsupervised representation learning of skeleton sequences

In this paper, we propose a novel framework for unsupervised representation learning using a structure-asymmetrical auto-encoder in which a 2D-CNN-based encoder learns separable spatiotemporal representations in a low-dimensional feature space under the supervision of salient skeleton motion cues. This study addresses the problem of learning action representations of skeleton sequences. The network captures not only correlations of adjacent joints but also long-term motion dependencies by using the proposed unsupervised training, which leads to the advantage that similar movements are gathered around the same cluster, whereas different movements are gathered around distinct clusters. Our method is unsupervised and does not rely on annotations to associate skeleton sequences with actions. Experimental results clearly showed the effectiveness of the proposed representation learning, and improvements compared with skeleton-based generative learning methods. When the proposed network was fine-tuned with partial labeled data, our results still outperformed some fully supervised methods.

Application of Generative Learning Methods In Arabic Lessons To Improve Students' Reading Skills/ تطبيق طريقة التعليم التفسيري في درس اللغة العربية لترقية مهارة القراءة لدى الطالبات

Abstract This research applies Generative learning methods using quantitative method research and the research model was experimental research. The researcher sets the alternative hypothesis (Ha), that there is a relationship between the application of Generative learning methods (Variable X) with the reading skills of students (Variable Y). And vice versa for the final hypothesis (Ho). With uses data collection methods as follows: Observation, Interview, Questionnaire and Test. The application of Generative learning methods is an appropriate method to be applied and effective. The effectiveness of the application of this method can be seen from the results of research data analysis that the value of T Calculate (t0) 10.72 is greater than T Table (tt) 2.861, this indicates that (Ho) is rejected and (Ha) is accepted. And the conclusion of this study is the existence of strong effectiveness with the application of Generative methods to improve the reading skills of students.

End-to-End Deep One-Class Learning for Anomaly Detection in UAV Video Stream.

In recent years, the use of drones for surveillance tasks has been on the rise worldwide. However, in the context of anomaly detection, only normal events are available for the learning process. Therefore, the implementation of a generative learning method in an unsupervised mode to solve this problem becomes fundamental. In this context, we propose a new end-to-end architecture capable of generating optical flow images from original UAV images and extracting compact spatio-temporal characteristics for anomaly detection purposes. It is designed with a custom loss function as a sum of three terms, the reconstruction loss (), the generation loss () and the compactness loss () to ensure an efficient classification of the “deep-one” class. In addition, we propose to minimize the effect of UAV motion in video processing by applying background subtraction on optical flow images. We tested our method on very complex datasets called the mini-drone video dataset, and obtained results surpassing existing techniques’ performances with an AUC of 85.3.

Scalable quantum tomography with fidelity estimation

We propose a quantum tomography scheme for pure qudit systems which adopts random base measurements and generative learning methods, along with a built-in fidelity estimation approach to assess the reliability of the tomographic states. We prove the validity of the scheme theoretically, and we perform numerically simulated experiments on several target states including three typical quantum information states and randomly initiated states, demonstrating its efficiency and robustness. The number of replicas required by a certain convergence criterion grows in the manner of low-degree polynomial when the system scales, thus the scheme achieves high scalability that is crucial for practical quantum state tomography.

BAHAN AJAR STATISTIKA BERBASIS GENERATIVE LEARNING UNTUK MENINGKATKAN KEMAMPUAN PEMAHAMAN MATEMATIS

This study aims to produce teaching materials and statistical exercises based on generative learning methods; find out the effects of teaching materials on students' mathematical understanding skills in statistical subjects. The subjects of this study were 49 students of the mathematics education program. The study uses design research with stages of development research, namely analysis, design, development, implementation, and evaluation. Data collection techniques with questionnaire validity of material experts, media experts, education experts, interview instruments, student evaluations, and tests. Based on the results of the study, teaching materials and statistical exercises based on generative learning are at a good level. The results of the student evaluation questionnaire regarding the effect of teaching materials are at a good level. The results of the mathematical comprehension ability test on statistical subjects are at a very good level. This can be seen from the value of practicality, namely that the final grade of students in the statistics course is in good and very good grades.

A cross-corpus study of subjectivity identification using unsupervised learning

AbstractIn this study, we investigate using unsupervised generative learning methods for subjectivity detection across different domains. We create an initial training set using simple lexicon information and then evaluate two iterative learning methods with a base naive Bayes classifier to learn from unannotated data. The first method is self-training, which adds instances with high confidence into the training set in each iteration. The second is a calibrated EM (expectation-maximization) method where we calibrate the posterior probabilities from EM such that the class distribution is similar to that in the real data. We evaluate both approaches on three different domains: movie data, news resource, and meeting dialogues, and we found that in some cases the unsupervised learning methods can achieve performance close to the fully supervised setup. We perform a thorough analysis to examine factors, such as self-labeling accuracy of the initial training set in unsupervised learning, the accuracy of the added examples in self-training, and the size of the initial training set in different methods. Our experiments and analysis show inherent differences across domains and impacting factors explaining the model behaviors.

位置依存型識別器を用いた車載カメラ画像からの路面標示検出

In this study, we propose a method for detecting road markings recorded in an image captured by an in-vehicle camera by using a position-dependent classifier. Road markings are symbols painted on the road surface that help in preventing traffic accidents and in ensuring traffic smooth. Therefore, driver support systems for detecting road markings, such as a system that provides warning in the case when traffic signs are overlooked, and supporting the stopping of a vehicle are required. It is difficult to detect road markings because their appearance changes with the actual traffic conditions, e. g. the shape and resolution change. The variation in these appearances depend on the positional relation between the vehicle and the road markings, and on the vehicle posture. Although these variations are quite large in an entire image, they are relatively small in a local area of the image. Therefore, we try to improve the detection performance by taking into account the local variations in these appearances. We propose a method in which a position-dependent classifier is used to detect road markings recorded in images captured by an in-vehicle camera. Further, to train the classifier efficiently, we propose a generative learning method that takes into consideration the positional relation between the vehicle and road markings, and also the vehicle posture. Experimental results showed that the detection performance when the proposed method was used was better than when a method involving a single classifier was used.

MENINGKATKAN KEMAMPUAN BERPIKIR KRITIS DAN KEMANDIRIAN BELAJAR MAHASISWA MELALUI PEMBELAJARAN GENERATIF

The research aims at analyzing the quality of students’ critical thinking and self-learning abilities by applying generative learning method in the subject of Algebra Structure at Mathematics Education Study Program of STKIP PGRI Lubuk Linggau. The variable of the research was the result of generative learning approach to improve critical thinking and self-learning abilities in the subject of Algebra Structure at Mathematics Education Study Program of STKIP PGRI Lubuk Linggau. The research objects were 23 students of the fifth semester class in Mathematic Education Study Program of STKIP PGRI Lubuk Linggau the year of 2009/2010. Research method applied was quasi experiment, with experiment class treated with generative learning method and without control class. The research result showed that in general, the critical thinking and self-learning abilities of Algebra Structure Subject had the mean of 75.90 (with minimum score of 70) meaning, the critical thinking and self-learning abilities of the students were generally in high level. Whereas the analysis result of variants test was t-count =3.954 and t-table (dk =22, á =1%) = 2,508. It showed that the critical thinking and self-learning abilities of the students with generative learning approach in the subject of Algebra Structure at Mathematics Education Study Program of STKIP PGRI Lubuk Linggau was above the score of 70.

Recognition of camera-captured low-quality characters using motion blur information

Camera-based character recognition has gained attention with the growing use of camera-equipped portable devices. One of the most challenging problems in recognizing characters with hand-held cameras is that captured images undergo motion blur due to the vibration of the hand. Since it is difficult to remove the motion blur from small characters via image restoration, we propose a recognition method without de-blurring. The proposed method includes a generative learning method in the training step to simulate blurred images by controlling blur parameters. The method consists of two steps. The first step recognizes the blurred characters based on the subspace method, and the second one reclassifies structurally similar characters using blur parameters estimated from the camera motion. We have experimentally proved that the effective use of motion blur improves the recognition accuracy of camera-captured characters.

Webgene$_{\rm OS}$: A Generative and Web-Based Learning Architecture to Teach Operating Systems in Undergraduate Courses

Operating systems is a fundamental topic underlying many modern disciplines, including computing, telematics, and control engineering. Moreover, operating systems is one of the core courses considered under the most important curricula recommendations. The learning process in this area involves both a theoretical and a practical part that students have to learn and put into practice. To reinforce operating systems fundamentals, simulation tools and instructional operating systems have been proposed. However, few of these tools address a learning approach that permits one to work with real operating systems while supporting an active learning methodology that integrates theory and practice. This paper applies generative learning methods and Web-based applications to operating systems courses. WebgeneOS is presented as an experimental learning system that leads students through a more active participation in the learning process. WebgeneOS combines the universal connectivity of Web technologies with the educational theory provided by the generative learning methods. The system allows students to send their system programs using Web forms, execute them in a native operating system, and receive their results and feedback information through Web browsers. The benefits of WebgeneOS were evaluated by comparing students' grades. The evaluation involved students attending operating systems courses during the 2002-2003, 2003-2004, and 2004-2005 academic years. Students using WebgeneOS improved their grades by about 13%. Moreover, the system offered a well-balanced formation between the theoretical and the practical learning outcomes. Overall, this paper made evident that Web technologies and generative learning methods help students in their learning process