Semi-supervised Classification Approach Research Articles

Semi-Supervised Subcategory Centroid Alignment-Based Scene Classification for High-Resolution Remote Sensing Images

It is usually hard to obtain adequate annotated data for delivering satisfactory scene classification results. Semi-supervised scene classification approaches can transfer the knowledge learned from previously annotated data to remote sensing images with scarce samples for satisfactory classification results. However, due to the differences between sensors, environments, seasons, and geographical locations, cross-domain remote sensing images exhibit feature distribution deviations. Therefore, semi-supervised scene classification methods may not achieve satisfactory classification accuracy. To address this problem, a novel semi-supervised subcategory centroid alignment (SSCA)-based scene classification approach is proposed. The SSCA framework is made up of two components, namely the rotation-robust convolutional feature extractor (RCFE) and the neighbor-based subcategory centroid alignment (NSCA). The RCFE aims to suppress the impact of rotation changes on remote sensing image representation, while the NSCA aims to decrease the impact of intra-category variety across domains on cross-domain scene classification. The SSCA algorithm and several competitive approaches are validated on two datasets to demonstrate its effectiveness. The results prove that the proposed SSCA approach performs better than most competitive approaches by no less than 2% overall accuracy.

Impact of an eddy dipole of the Mozambique channel on mesopelagic organisms, highlighted by multifrequency backscatter classification.

The impact of a cyclonic (C), an anticyclonic (AC) eddy and transition zone (TZ), which is the area between the two eddies, on acoustic groups representing various mesopelagic organisms, was investigated using a semi-supervised multifrequency classification approach (hereafter, Escore algorithm). The Escore algorithm involved selecting regions of interest (ROIs) within multifrequency (18, 38, 70, and 120 kHz) echograms and classifying into four clusters or echo-classes using Sv differences (Sv18-38, Sv70-38, and Sv120-38). Acoustic densities and diel vertical migration strength varied between the AC, C, and TZ according to the frequency. The vertical stratification of temperature, salinity and fluorescence within the oceanographic structures had varied influences on the vertical structure of each echo-class which represent zooplankton-like organisms, small and large fish with swimbladders, and small and large siphonophores with pneumatophores. The echo-classes within the C were influenced by surface fluorescence, whereas in the AC and TZ, the echo-classes were influenced by deeper fluorescence and strong EKE. Our study provides new insights into the environmental variables within mesoscale and sub-mesoscale features impacting different groups of mesopelagic communities in the Indian Ocean.

WOOD-LEAF UNSUPERVISED CLASSIFICATION OF SILVER BIRCH TREES FOR BIOMASS ASSESSMENT USING OBLIQUE POINT CLOUDS

Abstract. Forests play a fundamental role in carbon stocking since about a third of the carbon dioxide produced by activities of human origin is absorbed by forests. Forest biomass is an essential indicator of carbon dioxide absorption, enabling an understanding the interaction between forest dynamics and climate change effects. However, biomass and wood material changes are challenging to quantify in forest stands. Nowadays, recent 3D remote sensing technologies, such as laser scanning systems, have allowed accurate measures of single trees. This study evaluates three approaches to classify wood and non-wood materials and quantify biomass based on LiDAR data, aiming at biomass change detection. Specifically, we propose an automated methodology for estimating the single tree-level biomass of a portion of forest monitored through a LiDAR oblique acquisition. The classification of wood and foliage points was performed with machine learning algorithms, while the tree modelling was conducted rigorously through a Quantitative Structure Model (QSM). The purpose of this study is to evaluate (1) two different unsupervised and one semi-supervised classification approaches for wood and foliage separation and (2) the accuracy of the biomass assessment performed on a QSM-based approach on innovative LiDAR acquisitions. The results are promising; the wood-leaf classification performs effectively in all 20 silver birches considered; as regards the biomass, when the noise is limited, it is estimated in a manner consistent with the reference values calculated using an appropriate allometric equation. Higher values are found mainly in dense undergrowth, which negatively affects the modelling of the tree. The research is ongoing, and further tests will be performed to generalize the methodology on different tree species, deepen the multitemporal variability, and improve the accuracy of the assessment.

NSCKL: Normalized Spectral Clustering With Kernel-Based Learning for Semisupervised Hyperspectral Image Classification.

Spatial-spectral classification (SSC) has become a trend for hyperspectral image (HSI) classification. However, most SSC methods mainly consider local information, so that some correlations may not be effectively discovered when they appear in regions that are not contiguous. Although many SSC methods can acquire spatial-contextual characteristics via spatial filtering, they lack the ability to consider correlations in non-Euclidean spaces. To address the aforementioned issues, we develop a new semisupervised HSI classification approach based on normalized spectral clustering with kernel-based learning (NSCKL), which can aggregate local-to-global correlations to achieve a distinguishable embedding to improve HSI classification performance. In this work, we propose a normalized spectral clustering (NSC) scheme that can learn new features under a manifold assumption. Specifically, we first design a kernel-based iterative filter (KIF) to establish vertices of the undirected graph, aiming to assign initial connections to the nodes associated with pixels. The NSC first gathers local correlations in the Euclidean space and then captures global correlations in the manifold. Even though homogeneous pixels are distributed in noncontiguous regions, our NSC can still aggregate correlations to generate new (clustered) features. Finally, the clustered features and a kernel-based extreme learning machine (KELM) are employed to achieve the semisupervised classification. The effectiveness of our NSCKL is evaluated by using several HSIs. When compared with other state-of-the-art (SOTA) classification approaches, our newly proposed NSCKL demonstrates very competitive performance. The codes will be available at https://github.com/yuanchaosu/TCYB-nsckl.

Seismic Risk Regularization for Urban Changes Due to Earthquakes: A Case of Study of the 2023 Turkey Earthquake Sequence

Damage identification soon after a large-magnitude earthquake is a major problem for early disaster response activities. The faster the damaged areas are identified, the higher the survival chances of inhabitants. Current methods for damage identification are based on the application of artificial intelligence techniques using remote sensing data. Such methods require a large amount of high-quality labeled data for calibration and/or fine-tuning processes, which are expensive in the aftermath of large-scale disasters. In this paper, we propose a novel semi-supervised classification approach for identifying urban changes induced by an earthquake between images recorded at different times. We integrate information from a small set of labeled data with information from ground motion and fragility functions computed on large unlabeled data. A relevant consideration is that ground motion and fragility functions can be computed in real time. The urban changes induced by the 2023 Turkey earthquake sequence are reported as an evaluation of the proposed method. The method was applied to the interferometric coherence computed from C-band synthetic aperture radar images from Sentinel-1. We use only 39 samples labeled as changed and 9000 unlabeled samples. The results show that our method is able to identify changes between images associated with the effects of an earthquake with an accuracy of about 81%. We conclude that the proposed method can rapidly identify affected areas in the aftermath of a large-magnitude earthquake.

An embedding-based text classification approach for understanding micro-geographic housing dynamics

In this article, we introduce an approach for studying micro-geographic housing dynamics using an embedding-based, semi-supervised text classification approach on longitudinal, point-level property listing data. Based on the text used to describe properties for sale and a set of predefined classes and keywords, listings are classified according to their lifecycle of investment or disinvestment. The mixture of property types within 1 × 1 mile grid cells are then calculated and used as input in a clustering algorithm to develop a place-based classification that enables us to examine patterns of change over time. In a case study on Mecklenburg County, North Carolina using 158,253 real estate listings between 2001 and 2020, we demonstrate how this approach has the potential to further our understanding of housing and neighborhood dynamics by grounding our analysis in theoretical concepts around the housing lifecycle and its relationship to neighborhood change.

A novel semi-supervised classification approach for evolving data streams

Classification plays a crucial role in mining the evolving data streams. The concept drift and concept evolution are the major issues of data streams classification, which greatly affect the classification performance. Most existing works of concept drift and evolution are supervised in nature, where labeling the data is time and resource consuming. In this paper, for the evolving data streams, a semi-supervised classification approach using partially labeled data is proposed. Firstly, an ensemble model dynamically maintains a series of micro-clusters to capture the concept drift. The ensemble model processes the instances in an online fashion rather than chunk-based. Secondly, the concept evolution detection module is constructed to detect the outliers by the local density. The module examines the current buffer to capture the class emergence in data streams with complex class distribution. For improving the execution efficiency of emerging class detection without compromising performance, several constructive strategies are adopted, including removing part of the buffer and selectively executing sample generation. The extensive experiments are constructed about the popular data streams sets and the processed industry data streams, whose results indicate the practicality and effectiveness of the proposed approach for the classification of evolving data streams.

Deep Residual Learning-Based Convolutional Variational Autoencoder For Driver Fatigue Classification

Driving under the influence of fatigue often results in uncontrollable vehicle dynamics, which causes severe and fatal accidents. Therefore, early warning on the fatigue onset is crucial to avoid occurrences of such kind of a disaster. In this paper, the authors have investigated a novel semi-supervised convolutional variational autoencoder-based classification approach to classify the state of the driver. A convolutional variational autoencoder is a generative network. The authors have proposed a discriminative model using convolutional variational autoencoders and residual learning. This approach calculates an intermediate loss base on deep features of the network in addition to the label information in training. The loss obtained by this method helps the training to be more effective on the model and leads to better accuracy in driver fatigue classification. The trained model has managed to classify driver fatigue with higher accuracy (97%) than the other successful models taken into comparison, proving that the proposed method is more practical for computing classification loss for driver fatigue to currently available methods.

Semi-supervised learning based on intra-view heterogeneity and inter-view compatibility for image classification

To achieve high value of classification results by using a limited number of training samples, designing a multi-view semi-supervised classification model is extremely urgent. Moreover, considering that graph learning can fully capture the complex data structure information, we propose a graph-based multi-view semi-supervised classification approach named as Semi-supervised Classification based on Intra-view Heterogeneity and Inter-view Compatibility (SSC_IHIC). Specifically, the similarity between two samples can be measured based on the Euclidean distance. Considering that heterogeneity exists in intra-view sub-features, hence, the weights are learned adaptively. Besides, based on the inter-view compatibility, the consensus similarity graph is constructed on which the labels are propagated. To verify the effectiveness, the proposed approach is conducted on four data sets including MSRC-v1, Handwritten (HW), Cal101-7 and Cal101-20. From the experimental results, we can see that the classification performance about proposed method outperforms the single view classification methods and the state-of-the-art multi-view classification methods.

Threshold Filtering Semi-Supervised Learning Method for SAR Target Recognition

The semi-supervised deep learning technology driven by a small part of labeled data and a large amount of unlabeled data has achieved excellent performance in the field of image processing. However, the existing semi-supervised learning techniques are all carried out under the assumption that the labeled data and the unlabeled data are in the same distribution, and its performance is mainly due to the two being in the same distribution state. When there is out-of-class data in unlabeled data, its performance will be affected. In practical applications, it is difficult to ensure that unlabeled data does not contain out-of-category data, especially in the field of Synthetic Aperture Radar (SAR) image recognition. In order to solve the problem that the unlabeled data contains out-of-class data which affects the performance of the model, this paper proposes a semi-supervised learning method of threshold filtering. In the training process, through the two selections of data by the model, unlabeled data outside the category is filtered out to optimize the performance of the model. Experiments were conducted on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset, and compared with existing several state-of-the-art semi-supervised classification approaches, the superiority of our method was confirmed, especially when the unlabeled data contained a large amount of out-of-category data.

Sample-Centric Feature Generation for Semi-Supervised Few-Shot Learning.

Semi-supervised few-shot learning aims to improve the model generalization ability by means of both limited labeled data and widely-available unlabeled data. Previous works attempt to model the relations between the few-shot labeled data and extra unlabeled data, by performing a label propagation or pseudo-labeling process using an episodic training strategy. However, the feature distribution represented by the pseudo-labeled data itself is coarse-grained, meaning that there might be a large distribution gap between the pseudo-labeled data and the real query data. To this end, we propose a sample-centric feature generation (SFG) approach for semi-supervised few-shot image classification. Specifically, the few-shot labeled samples from different classes are initially trained to predict pseudo-labels for the potential unlabeled samples. Next, a semi-supervised meta-generator is utilized to produce derivative features centering around each pseudo-labeled sample, enriching the intra-class feature diversity. Meanwhile, the sample-centric generation constrains the generated features to be compact and close to the pseudo-labeled sample, ensuring the inter-class feature discriminability. Further, a reliability assessment (RA) metric is developed to weaken the influence of generated outliers on model learning. Extensive experiments validate the effectiveness of the proposed feature generation approach on challenging one- and few-shot image classification benchmarks.

Semisupervised Hyperspectral Image Classification via Superpixel-Based Graph Regularization With Local and Nonlocal Features

Although a graph-based Semi-supervised learning (SSL) approach can utilize limited numbers of labeled samples for hyperspectral image (HSI) classification, it is difficult to use the large amount of pixels in an HSI to construct a large-scale graph. In this paper, we therefore propose a superpixel-based graph model for HSI classification, using anchor graph regularization to improve the extraction of local and non-local spatial information. To avoid the large-scale graph problem, the superpixel-based graph model constructs a scalable anchor graph using a small number of anchor points for graph-based SSL. The proposed approach consists of three key components: (1) First, local and non-local features are extracted from the principal components of an HSI using the locally grouped order pattern (LGOP) and the non-local binary pattern (NLBP) approaches. (2) Second, the extracted features are combined with the original spectral information and used as input to an improved simple line iteration clustering method (ISLIC) to obtain superpixels, the centers of which are used as anchors in the anchor graph approach. (3) Third, we use superpixel-based graph regularization (SGR) to model the global information among the superpixels for better predictions of the label of each unlabeled pixel sample. Experimental results demonstrate that the proposed approach outperforms other state-of-the-art Semi-supervised HSI classification approaches for cases with a limited quantity of labeled samples.

A Novel Semi-Supervised Classification Approach for Evolving Data Streams

A Novel Semi-Supervised Classification Approach for Evolving Data Streams

Semi-Supervised Self-Training of Hate and Offensive Speech from Social Media

ABSTRACT Improving Offensive and Hate Speech (OHS) classifiers’ performances requires a large, confidently labeled textual training dataset. Our study devises a semi-supervised classification approach with self-training to leverage the abundant social media content and develop a robust OHS classifier. The classifier is self-trained iteratively using the most confidently predicted labels obtained from an unlabeled Twitter corpus of 5 million tweets. Hence, we produce the largest supervised Arabic OHS dataset. To this end, we first select the best classifier to conduct the semi-supervised learning by assessing multiple heterogeneous pairs of text vectorization algorithms (such as N-Grams, World2Vec Skip-Gram, AraBert and DistilBert) and machine learning algorithms (such as SVM, CNN and BiLSTM). Then, based on the best text classifier, we perform six groups of experiments to demonstrate our approach’s feasibility and efficacy based on several self-training iterations.

Evaluation of classification performances of minimum spanning trees by 13 different metrics

Minimum Spanning Tree (MST) is a well-known clustering algorithm that provides a graphical tree representation of the objects in a data set by exploiting local information to link each pair of similar objects. The a-posteriori analysis of this tree in terms of nodes and edges provides the basis to derive simple classifiers, namely semi-supervised classification approaches based on the minimum spanning tree approach. In this work, we propose different metrics to evaluate the MST ability to group objects of the same a-priori known classes. The classification capability of the proposed approach, using 13 different distance measures, was compared with that of classical supervised classification approaches such as N-Nearest Neighbour (N3), Binned Nearest Neighbour (BNN), Partial Least SquaresDiscriminant Analysis (PLS-DA), K-Nearest Neighbour (KNN), exponentially weighted K-Nearest Neighbour (wKNN) and Support Vector Machine with radial functions (SVMRBF) on 31 data sets. The proposed approach resulted to be competitive and comparable with the considered classical supervised classification methods. Finally, we analysed the role of the 13 different measures in terms of performance and percentage of not-assigned objects.

A weighted ensemble-based active learning model to label microarray data.

Classification of cancerous genes from microarray data is an important research area in bioinformatics. Large amount of microarray data are available, but it is very costly to label them. This paper proposes an active learning model, a semi-supervised classification approach, to label the microarray data using which predictions can be made even with lesser amount of labeled data. Initially, a pool of unlabeled instances is given from which some instances are randomly chosen for labeling. Successive selection of instances to be labeled from unlabeled pool is determined by selection algorithms. The proposed method is devised following an ensemble approach to combine the decisions of three classifiers in order to arrive at a consensus which provides a more accurate prediction of the class label to ensure that each individual classifier learns in an uncorrelated manner. Our method combines the heuristic techniques used by an active learning algorithm to choose training samples with the multiple learning paradigm attained by an ensemble to optimize the search space by choosing efficiently from an already sparse learning pool. On evaluating the proposed method on 10 microarray datasets, we achieve performance which is comparable with state-of-the-art methods. The code and datasets are given at https://github.com/anuran-Chakraborty/Active-learning. Flowchart of the proposed ensemble-based active learning framework.

Local Binary Ensemble based Self-training for Semi-supervised Classification of Hyperspectral Remote Sensing Images

Supervised classification of hyperspectral remote sensing images is still challenging due to the scarcity of enough labelled samples. Semi-supervised methods have been adopted to handle this issue. Self-training is a popular semi-supervised technique which is widely used for training a classifier with limited labelled data and a large quantity of unlabeled data. However, traditional self-training approaches often give poor classification results in high dimensional data. In the current work, a novel efficient self-training approach for handling the deficiency of labelled samples for semi-supervised classification of hyperspectral remote sensing images is proposed. The proposed method first trains an ensemble of locally specialized supervised binary classifiers independently by using the dimensionally reduced spectral feature vectors of few available labelled samples. The trained local binary classifiers are then used to extend the labelled set by iterative addition of highly informative unlabeled samples to it by exploiting both the spectral and spatial information of the hyperspectral image. The classifiers are then retrained with the extended dataset in a batchwise manner and the procedure is repeated until adequate quantity of labelled samples are generated. Finally, a supervised multiclass classifier is trained on the extended dataset to produce the final classification map. Experimental results on two benchmark hyperspectral image datasets prove the effectiveness of the proposed method over supervised and traditional self-training based semi-supervised pixelwise classification approach in terms of different classification measures.

A self-training hierarchical prototype-based approach for semi-supervised classification

This paper introduces a novel self-training hierarchical prototype-based approach for semi-supervised classification. The proposed approach firstly identifies meaningful prototypes from labelled samples at multiple levels of granularity and, then, self-organizes a highly transparent, multi-layered recognition model by arranging them in a form of pyramidal hierarchies. After this, the learning model continues to self-evolve its structure and self-expand its knowledge base to incorporate new patterns recognized from unlabelled samples by exploiting the pseudo-label technique. Thanks to its prototype-based nature, the overall computational process of the proposed approach is highly explainable and traceable. Experimental studies with various benchmark image recognition problems demonstrate the state-of-the-art performance of the proposed approach, showing its strong capability to mine key information from unlabelled data for classification.

Semisupervised Scene Classification for Remote Sensing Images: A Method Based on Convolutional Neural Networks and Ensemble Learning

The scarcity of labeled samples has been the main obstacle to the development of scene classification for remote sensing images. To alleviate this problem, the efforts have been dedicated to semisupervised classification which exploits both labeled and unlabeled samples for training classifiers. In this letter, we propose a novel semisupervised method that utilizes the effective residual convolutional neural network (ResNet) to extract preliminary image features. Moreover, the strategy of ensemble learning (EL) is adopted to establish discriminative image representations by exploring the intrinsic information of all available data. Finally, supervised learning is performed for scene classification. To verify the effectiveness of the proposed method, it is further compared with several state-of-the-art feature representation and semisupervised classification approaches. The experimental results show that by combining ResNet features with EL, the proposed method can obtain more effective image representations and achieve superior results.

Gaia Data Release 2

Context. More than half a million of the 1.69 billion sources in Gaia Data Release 2 (DR2) are published with photometric time series that exhibit light variations during the 22 months of observation. Aims. An all-sky classification of common high-amplitude pulsators (Cepheids, long-period variables, δ Scuti/SX Phoenicis, and RR Lyrae stars) is provided for stars with brightness variations greater than 0.1 mag in G band. Methods. A semi-supervised classification approach was employed, firstly training multi-stage random forest classifiers with sources of known types in the literature, followed by a preliminary classification of the Gaia data and a second training phase that included a selection of the first classification results to improve the representation of some classes, before the improved classifiers were applied to the Gaia data. Dedicated validation classifiers were used to reduce the level of contamination in the published results. A relevant fraction of objects were not yet sufficiently sampled for reliable Fourier series decomposition, consequently classifiers were based on features derived from statistics of photometric time series in the G, GBP, and GRP bands, as well as from some astrometric parameters. Results. The published classification results include 195 780 RR Lyrae stars, 150 757 long-period variables, 8550 Cepheids, and 8882 δ Scuti/SX Phoenicis stars. All of these results represent candidates whose completeness and contamination are described as a function of variability type and classification reliability. Results are expressed in terms of class labels and classification scores, which are available in the vari_classifier_result table of the Gaia archive.