Semi-supervised Learning Approach Research Articles

Semi-supervised learning approach for localization and pose estimation of texture-less objects in cluttered scenes

3D object recognition and 6D pose estimation are crucial and fundamental endeavours for industrial assembly line automation such as robotic controlled pick-and-place. While the problem on textured objects is extensively studied, it is still an open research topic for texture-less industrial parts, e.g, solid cylinder and hollow tube, which are symmetric and appear similar in shapes from many viewing perspectives, causing pose ambiguity. Also, the industrial assembly line environment is usually cluttered and the captured data is noisy, which makes this task even more challenging. In this paper, we propose a novel object localization and pose estimation technique using RGB images and depth maps of industrial assembly parts. Our segmentation model is fully morphological and unsupervised for localizing the region of interest containing the target object extracted from the depth map. Our segmentation technique is effective in the presence of partial occlusion, multiple objects, and cluttered scenes. We use a model based approach for object recognition based on Stochastic Gradient Descent trained on features of Histogram of Oriented Gradients (HOG) and invariant moments of the region of interest containing the target object. We generate synthetic training images automatically from the CAD models of the industrial parts. We use a contour matching strategy based on Dynamic Time Warping (DTW) algorithm to estimate the optimal 6D pose of the object from a set of candidates. Experimental results show that our proposed approach competes and demonstrates advantages on the challenging T-LESS dataset compared to the state-of-the-art methods. • We introduce a strategy for generating multiple viewpoint synthetic images from a CAD model. • We introduce a non-supervised clustering process for object segmentation based on a depth map that does not require a training stage. • We demonstrate how different HOG feature parameters can be tuned to achieve better prediction and performance. • We present a new real-time strategy for object pose estimation using Dynamic Time Warping (DTW) between the target object contour and best prior candidates. • We show that our method achieves better time performance than other works for pose estimation.

Semi-Supervised Non-Parametric Bayesian Modelling of Spatial Proteomics.

Understanding sub-cellular protein localisation is an essential component in the analysis of context specific protein function. Recent advances in quantitative mass-spectrometry (MS) have led to high resolution mapping of thousands of proteins to sub-cellular locations within the cell. Novel modelling considerations to capture the complex nature of these data are thus necessary. We approach analysis of spatial proteomics data in a non-parametric Bayesian framework, using K-component mixtures of Gaussian process regression models. The Gaussian process regression model accounts for correlation structure within a sub-cellular niche, with each mixture component capturing the distinct correlation structure observed within each niche. The availability of marker proteins (i.e. proteins with a priori known labelled locations) motivates a semi-supervised learning approach to inform the Gaussian process hyperparameters. We moreover provide an efficient Hamiltonian-within-Gibbs sampler for our model. Furthermore, we reduce the computational burden associated with inversion of covariance matrices by exploiting the structure in the covariance matrix. A tensor decomposition of our covariance matrices allows extended Trench and Durbin algorithms to be applied to reduce the computational complexity of inversion and hence accelerate computation. We provide detailed case-studies on Drosophila embryos and mouse pluripotent embryonic stem cells to illustrate the benefit of semi-supervised functional Bayesian modelling of the data.

Clinical biostatistics in the 2020s

Clinical biostatistics in the 2020s

The High Separation Probability Assumption for Semi-Supervised Learning

We propose a novel semi-supervised learning (SSL) assumption—the high separation probability (HSP) assumption—that is complementary to the common low density separation (LDS) assumption, and a highly accurate and efficient SSL algorithm, the transductive minimax probability machine (TMPM). Under the HSP assumption, a preferred classifier should ensure that with high probability the samples are far away from the decision boundary. Similarly, the LDS assumption states that the decision boundary should lie in a low-density region. A remarkable property of HSP is that it provides an elegant theoretical framework for analyzing the generalization performance of SSL, while it remains difficult for the LDS assumption to have a quantitative criterion on how it fits the data. Moreover, it has the same paradigm as the minimax probability machine (MPM) and yields an intractable mixed-integer optimization for solving the transductive label assignment problem. Consequently, we propose TMPM with a label-switching strategy and iterative manner to formalize our approximate solution. Theoretically, we analyze the computational complexity, convergence property, and generalization error bound of TMPM. Empirically, we show that TMPM achieves competitive performance on a wide range of datasets, while being almost one order of magnitude faster than existing SSL approaches.

Semi-supervised adversarial discriminative domain adaptation.

Domain adaptation is a potential method to train a powerful deep neural network across various datasets. More precisely, domain adaptation methods train the model on training data and test that model on a completely separate dataset. The adversarial-based adaptation method became popular among other domain adaptation methods. Relying on the idea of GAN, the adversarial-based domain adaptation tries to minimize the distribution between the training and testing dataset based on the adversarial learning process. We observe that the semi-supervised learning approach can combine with the adversarial-based method to solve the domain adaptation problem. In this paper, we propose an improved adversarial domain adaptation method called Semi-Supervised Adversarial Discriminative Domain Adaptation (SADDA), which can outperform other prior domain adaptation methods. We also show that SADDA has a wide range of applications and illustrate the promise of our method for image classification and sentiment classification problems.

A novel semi-supervised learning approach for State of Health monitoring of maritime lithium-ion batteries

Lithium-ion batteries are a prominent technology for the electrification of the transport sector, which itself is a key measure towards the departure from fossil fuels. The “green shift” is taking place in the marine industry too, where the number of battery-powered vessels is fastly growing. In this case, monitoring the battery State of Health is essential more than ever to optimise battery use, promote safety, and ensure the coverage of ship power and energy demands. Classification societies typically require annual capacity tests for this purpose; however, the tests are disruptive, costly and time-consuming. As a consequence they are seldom, in addition to not being always fully reliable. We propose a novel alternative semi-supervised learning approach to estimate the State of Health of a lithium-ion battery system with no labelled data, starting from a minimal set of weakly labelled data from another similar system. The method is based on operational sensor data gathered from the battery, together with the battery State of Charge. Our results show that the procedure is valid, and the obtained estimates can be used to significantly progress in failure prevention, operational optimisation, and for planning batteries at the design stage.

Intelligent fault identification strategy of photovoltaic array based on ensemble self-training learning

Identifying Photovoltaic (PV) array faults is crucial for improving the service life and consolidating system performance overall. The strategies based on the supervised Machine Learning (ML) approach represent an attractive solution to identify the PV array faults. However, attainable labeled data to train supervised ML algorithms present challenges in practice. Therefore, this work introduces a novel strategy that employs an ensemble learning concept in conjunction with a semi-supervised learning approach based on a self-training philosophy to realize the faults diagnosis of an arc, line-to-line, power tracker unit, open-circuit, and partial shading, under different of aspects which can directly be impacting faults behavior. The developed ensemble learning paradigm comprises multiple merged ML models, which enhances the overall diagnostics performance. Moreover, it works to alleviate the resource-intensive process, which, in turn, contributes to overcoming standard supervised ML algorithms limitations. To ensure high fault diagnostic capabilities through the proposed fault identification strategy, the principal component analysis is introduced to mitigate the correlation between variables. Moreover, the Bayesian optimization method is adopted to control the behaviors of training ML algorithms, providing models with better characterization results. The merits of the proposed strategy are corroborated through simulation and experimental case studies.

Different Traits, Different Evolutionary Pathways: Insights from Salamandrina (Amphibia, Caudata).

Species delimitation is often based on a single or very few genetic or phenetic traits, something which leads to misinterpretations and often does not provide information about evolutionary processes. Here, we investigated the diversity pattern of multiple phenetic traits of the two extant species of Salamandrina, a genus split only after molecular traits had been studied but the two species of which are phenetically very similar. The phenetic traits we studied are size, external body shape and head colour pattern, in a model comparison framework using non-linear mixed models and unsupervised and supervised clustering. Overall, we found high levels of intra-specific variability for body size and shape, depending on population belonging and habitat, while differences between species were generally lower. The habitat the salamanders dwell in also seems important for colour pattern. Basing on our findings, from the methodological point of view, we suggest (i) to take into account the variability at population level when testing for higher level variability, and (ii) a semi-supervised learning approach to high dimensional data. We also showed that different phenotypic traits of the same organism could result from different evolutionary routes. Local adaptation is likely responsible for body size and shape variability, with selective pressures more similar across species than within them. Head colour pattern also depends on habitat, differently from ventral colour pattern (not studied in this paper) which likely evolved under genetic drift.

A Novel Approach for Semi-supervised Learning: Incremental Parallel Training with Cross-Validation (IPT-CV)

A Novel Approach for Semi-supervised Learning: Incremental Parallel Training with Cross-Validation (IPT-CV)

A Semi-Supervised Machine Learning Approach in Predicting High-Risk Pregnancies in the Philippines.

Early risk tagging is crucial in maternal health, especially because it threatens both the mother and the long-term development of the baby. By tagging high-risk pregnancies, mothers would be given extra care before, during, and after pregnancies, thus reducing the risk of complications. In the Philippines, where the fertility rate is high, especially among the youth, awareness of risks can significantly contribute to the overall outcome of the pregnancy and, to an extent, the Maternal mortality rate. Although supervised machine learning models have ubiquity as predictors, there is a gap when data are weak or scarce. Using limited collected data from the municipality of Daraga in Albay, the study first compared multiple supervised machine learning algorithms to analyze and accurately predict high-risk pregnancies. Through hyperparameter tuning, supervised learning algorithms such as Decision Tree, Random Forest, Support Vector Machine, K-Nearest Neighbors, Naïve Bayes, and Multilayer Perceptron were evaluated by using 10-fold cross validation to obtain the best parameters with the best scores. The results show that Decision Tree bested other algorithms and attained a test score of 93.70%. To address the gap, a semi-supervised approach using a Self-Training model was applied to the modified Decision Tree, which was then used as the base estimator with a 30% unlabeled dataset and achieved a 97.01% accuracy rate which outweighs similar studies.

Fine-grained classification of drug trafficking based on Instagram hashtags

Social networks have become important platforms for the marketing and sale of illicit drugs. Hashtags make it easier for users to engage in drug trafficking, further increasing the risk of drug abuse. However, there are significant challenges in the detection and management of drug trafficking activities. In addition, the rapid legalization of some drugs has required a fine-grained classification of drugs to distinguish them from those that are illegal. Motivated by these observations, in this paper, our aim is to develop a methodology using the latest advances in AI technology to classify hashtags from posts advertising illicit drugs for sale on social networks. We present a semi-supervised deep learning approach to classify hashtags from posts advertising illicit drugs. An elegant combination of Bidirectional Encoder Representations from Transformers (BERT) with Graph Convolutional Network (GCN) allows us to analyze the characteristics (e.g., shipping region and platform self-regulation) of illegal drug trafficking. Our BERT+GCN model achieved the best performance with more than 75% accuracy compared to the other three baseline models. Then, fine-grained hashtags identified are applied to explore the characteristics of drug trafficking. Finally, we report our results for further exploration of shipping regions and self-regulation of drug trafficking on the platform in two analysis scenarios. Our developed approach has shown its effectiveness in detecting hashtags for different types of drugs from illegal drug sellers. Based on hashtag classification, we also provide two case studies that indicate that (1) there are differences in self-regulation for different types of drugs on social media, (2) there are regional differences in the demand for different types of drugs.

LMGAN: Linguistically Informed Semi-Supervised GAN with Multiple Generators.

Semi-supervised learning is one of the active research topics these days. There is a trial that solves semi-supervised text classification with a generative adversarial network (GAN). However, its generator has a limitation in producing fake data distributions that are similar to real data distributions. Since the real data distribution is frequently changing, the generator could not create adequate fake data. To overcome this problem, we present a novel approach for semi-supervised learning for text classification based on generative adversarial networks, Linguistically Informed SeMi-Supervised GAN with Multiple Generators, LMGAN. LMGAN uses trained bidirectional encoder representations from transformers (BERT) and the discriminator from GAN-BERT. In addition, LMGAN has multiple generators and utilizes the hidden layers of BERT. To reduce the discrepancy between the distribution of fake data and real data distribution, LMGAN uses fine-tuned BERT and the discriminator from GAN-BERT. However, since injecting fine-tuned BERT could induce incorrect fake data distribution, we utilize linguistically meaningful intermediate hidden layer outputs of BERT to enrich fake data distribution. Our model shows well-distributed fake data compared to the earlier GAN-based approach that failed to generate adequate high-quality fake data. Moreover, we can get better performances with extremely limited amounts of labeled data, up to 20.0%, compared to the baseline GAN-based model.

Semi-Supervised Approach for EGFR Mutation Prediction on CT Images

The use of deep learning methods in medical imaging has been able to deliver promising results; however, the success of such models highly relies on large, properly annotated datasets. The annotation of medical images is a laborious, expensive, and time-consuming process. This difficulty is increased for the mutations status label since these require additional exams (usually biopsies) to be obtained. On the other hand, raw images, without annotations, are extensively collected as part of the clinical routine. This work investigated methods that could mitigate the labelled data scarcity problem by using both labelled and unlabelled data to improve the efficiency of predictive models. A semi-supervised learning (SSL) approach was developed to predict epidermal growth factor receptor (EGFR) mutation status in lung cancer in a less invasive manner using 3D CT scans.The proposed approach consists of combining a variational autoencoder (VAE) and exploiting the power of adversarial training, intending that the features extracted from unlabelled data to discriminate images can help in the classification task. To incorporate labelled and unlabelled images, adversarial training was used, extending a traditional variational autoencoder. With the developed method, a mean AUC of 0.701 was achieved with the best-performing model, with only 14% of the training data being labelled. This SSL approach improved the discrimination ability by nearly 7 percentage points over a fully supervised model developed with the same amount of labelled data, confirming the advantage of using such methods when few annotated examples are available.

A Privacy-Preserving Semisupervised Algorithm Under Maximum Correntropy Criterion.

Existing semisupervised learning approaches generally focus on the single-agent (centralized) setting, and hence, there is the risk of privacy leakage during joint data processing. At the same time, using the mean square error criterion in such approaches does not allow one to efficiently deal with problems involving non-Gaussian distribution. Thus, in this article, we present a novel privacy-preserving semisupervised algorithm under the maximum correntropy criterion (MCC). The proposed algorithm allows us to share data among different entities while effectively mitigating the risk of privacy leaks. In addition, under MCC, our proposed approach works well for data with non-Gaussian distribution noise. Our experiments on three different learning tasks demonstrate that our method distinctively outperforms the related algorithms in common regression learning scenarios.

Semi-Supervised Segmentation of Echocardiography Videos Using Graph Signal Processing

Machine learning and computer vision algorithms can provide a precise and automated interpretation of medical videos. The segmentation of the left ventricle of echocardiography videos plays an essential role in cardiology for carrying out clinical cardiac diagnosis and monitoring the patient’s condition. Most of the developed deep learning algorithms for video segmentation require an enormous amount of labeled data to generate accurate results. Thus, there is a need to develop new semi-supervised segmentation methods due to the scarcity and costly labeled data. In recent research, semi-supervised learning approaches based on graph signal processing emerged in computer vision due to their ability to avail the geometrical structure of data. Video object segmentation can be considered as a node classification problem. In this paper, we propose a new approach called GraphECV based on the use of graph signal processing for semi-supervised learning of video object segmentation applied for the segmentation of the left ventricle in echordiography videos. GraphECV includes instance segmentation, extraction of temporal, texture and statistical features to represent the nodes, construction of a graph using K-nearest neighbors, graph sampling to embed the graph with small amount of labeled nodes or graph signals, and finally a semi-supervised learning approach based on the minimization of the Sobolov norm of graph signals. The new algorithm is evaluated using two publicly available echocardiography videos, EchoNet-Dynamic and CAMUS datasets. The proposed approach outperforms other state-of-the-art methods under challenging background conditions.

Language Model-Guided Classifier Adaptation for Brain-Computer Interfaces for Communication.

Brain-computer interfaces (BCIs), such as the P300 speller, can provide a means of communication for individuals with severe neuromuscular limitations. BCIs interpret electroencephalography (EEG) signals in order to translate embedded information about a user's intent into executable commands to control external devices. However, EEG signals are inherently noisy and nonstationary, posing a challenge to extended BCI use. Conventionally, a BCI classifier is trained via supervised learning in an offline calibration session; once trained, the classifier is deployed for online use and is not updated. As the statistics of a user's EEG data change over time, the performance of a static classifier may decline with extended use. It is therefore desirable to automatically adapt the classifier to current data statistics without requiring offline recalibration. In an existing semi-supervised learning approach, the classifier is trained on labeled EEG data and is then updated using incoming unlabeled EEG data and classifier-predicted labels. To reduce the risk of learning from incorrect predictions, a threshold is imposed to exclude unlabeled data with low-confidence label predictions from the expanded training set when retraining the adaptive classifier. In this work, we propose the use of a language model for spelling error correction and disambiguation to provide information about label correctness during semi-supervised learning. Results from simulations with multi-session P300 speller user EEG data demonstrate that our language-guided semi-supervised approach significantly improves spelling accuracy relative to conventional BCI calibration and threshold-based semi-supervised learning.

Momentum Pseudo-Labeling: Semi-Supervised ASR With Continuously Improving Pseudo-Labels

End-to-end automatic speech recognition (ASR) has become a popular alternative to traditional module-based systems, simplifying the model-building process with a single deep neural network architecture. However, the training of end-to-end ASR systems is generally data-hungry: a large amount of labeled data (speech-text pairs) is necessary to learn direct speech-to-text conversion effectively. To make the training less dependent on labeled data, pseudo-labeling, a semi-supervised learning approach, has been successfully introduced to end-to-end ASR, where a seed model is self-trained with pseudo-labels generated from unlabeled (speech-only) data. Here, we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">momentum pseudo-labeling</i> (MPL), a simple yet effective strategy for semi-supervised ASR. MPL consists of a pair of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">online</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">offline</i> models that interact and learn from each other, inspired by the mean teacher method. The online model is trained to predict pseudo-labels generated on the fly by the offline model. The offline model maintains an exponential moving average of the online model parameters. The interaction between the two models allows better ASR training on unlabeled data by continuously improving the quality of pseudo-labels. We apply MPL to a connectionist temporal classification-based model and evaluate it on various semi-supervised scenarios with varying amounts of data or domain mismatch. The results demonstrate that MPL significantly improves the seed model by stabilizing the training on unlabeled data. Moreover, we present additional techniques, e.g., the use of Conformer and an external language model, to further enhance MPL, which leads to better performance than other semi-supervised methods based on pseudo-labeling.

Voxel-wise adversarial semi-supervised learning for medical image segmentation

Background and Objective:Semi-supervised learning for medical image segmentation is an important area of research for alleviating the huge cost associated with the construction of reliable large-scale annotations in the medical domain. Recent semi-supervised approaches have demonstrated promising results by employing consistency regularization, pseudo-labeling techniques, and adversarial learning. These methods primarily attempt to learn the distribution of labeled and unlabeled data by enforcing consistency in the predictions or embedding context. However, previous approaches have focused only on local discrepancy minimization or context relations across single classes. Methods:In this paper, we introduce a novel adversarial learning-based semi-supervised segmentation method that effectively embeds both local and global features from multiple hidden layers and learns context relations between multiple classes. Our voxel-wise adversarial learning method utilizes a voxel-wise feature discriminator, which considers multilayer voxel-wise features (involving both local and global features) as an input by embedding class-specific voxel-wise feature distribution. Furthermore, our previous representation learning method is improved by overcoming information loss and learning stability problems, which enables rich representations of labeled data. Result:In the experiments, we used the Left Atrial Segmentation Challenge dataset and the Abdominal Multi-Organ dataset to prove the effectiveness of our method in both single class and multiclass segmentation. The experimental results demonstrate that our method outperforms current best-performing state-of-the-art semi-supervised learning approaches. Our proposed adversarial learning-based semi-supervised segmentation method successfully leveraged unlabeled data to improve the network performance by 2% in Dice score coefficient for multi-organ dataset. Conclusion:We compare our approach to a wide range of medical datasets, and showed our method can be adapted to embed class-specific features. Furthermore, visual interpretation of the feature space demonstrates that our proposed method enables a well-distributed and separated feature space from both labeled and unlabeled data, which improves the overall prediction results.

A semi-supervised learning approach for automated 3D cephalometric landmark identification using computed tomography.

Identification of 3D cephalometric landmarks that serve as proxy to the shape of human skull is the fundamental step in cephalometric analysis. Since manual landmarking from 3D computed tomography (CT) images is a cumbersome task even for the trained experts, automatic 3D landmark detection system is in a great need. Recently, automatic landmarking of 2D cephalograms using deep learning (DL) has achieved great success, but 3D landmarking for more than 80 landmarks has not yet reached a satisfactory level, because of the factors hindering machine learning such as the high dimensionality of the input data and limited amount of training data due to the ethical restrictions on the use of medical data. This paper presents a semi-supervised DL method for 3D landmarking that takes advantage of anonymized landmark dataset with paired CT data being removed. The proposed method first detects a small number of easy-to-find reference landmarks, then uses them to provide a rough estimation of the all landmarks by utilizing the low dimensional representation learned by variational autoencoder (VAE). The anonymized landmark dataset is used for training the VAE. Finally, coarse-to-fine detection is applied to the small bounding box provided by rough estimation, using separate strategies suitable for the mandible and the cranium. For mandibular landmarks, patch-based 3D CNN is applied to the segmented image of the mandible (separated from the maxilla), in order to capture 3D morphological features of mandible associated with the landmarks. We detect 6 landmarks around the condyle all at once rather than one by one, because they are closely related to each other. For cranial landmarks, we again use the VAE-based latent representation for more accurate annotation. In our experiment, the proposed method achieved a mean detection error of 2.88 mm for 90 landmarks using only 15 paired training data.

Introducing Urdu Digits Dataset with Demonstration of an Efficient and Robust Noisy Decoder-Based Pseudo Example Generator

In the present work, we propose a novel method utilizing only a decoder for generation of pseudo-examples, which has shown great success in image classification tasks. The proposed method is particularly constructive when the data are in a limited quantity used for semi-supervised learning (SSL) or few-shot learning (FSL). While most of the previous works have used an autoencoder to improve the classification performance for SSL, using a single autoencoder may generate confusing pseudo-examples that could degrade the classifier’s performance. On the other hand, various models that utilize encoder–decoder architecture for sample generation can significantly increase computational overhead. To address the issues mentioned above, we propose an efficient means of generating pseudo-examples by using only the generator (decoder) network separately for each class that has shown to be effective for both SSL and FSL. In our approach, the decoder is trained for each class sample using random noise, and multiple samples are generated using the trained decoder. Our generator-based approach outperforms previous state-of-the-art SSL and FSL approaches. In addition, we released the Urdu digits dataset consisting of 10,000 images, including 8000 training and 2000 test images collected through three different methods for purposes of diversity. Furthermore, we explored the effectiveness of our proposed method on the Urdu digits dataset by using both SSL and FSL, which demonstrated improvement of 3.04% and 1.50% in terms of average accuracy, respectively, illustrating the superiority of the proposed method compared to the current state-of-the-art models.