Explore the vast range of titles available.

Deep learning algorithms have seen a massive rise in popularity for remote sensing over the past few years. Recently, studies on applying deep learning techniques to graph data in remote sensing (e.g., public transport networks) have been conducted. In graph node classification tasks, traditional graph neural network (GNN) models assume that different types of misclassifications have an equal loss and thus seek to maximize the posterior probability of the sample nodes under labeled classes. The graph data used in realistic scenarios tend to follow unbalanced long-tailed class distributions, where a few majority classes contain most of the vertices and the minority classes contain only a small number of nodes, making it difficult for the GNN to accurately predict the minority class samples owing to the classification tendency of the majority classes. In this paper, we propose a dual cost-sensitive graph convolutional network (DCSGCN) model. The DCSGCN is a two-tower model containing two subnetworks that compute the posterior probability and the misclassification cost. The model uses the cost as ”complementary information” in a prediction to correct the posterior probability under the perspective of minimal risk. Furthermore, we propose a new method for computing the node cost labels based on topological graph information and the node class distribution. The results of extensive experiments demonstrate that DCSGCN outperformed other competitive baselines on different real-world imbalanced long-tailed graphs.

Semi-supervised learning(SSL) can substantially improve the performance of deep neural networks by utilizing unlabeled data when labeled data is scarce. The state-of-the-art(SOTA) semi-supervised algorithms implicitly assume that the class distribution of labeled datasets and unlabeled datasets are balanced, which means the different classes have the same numbers of training samples. However, they can hardly perform well on minority classes when the class distribution of training data is imbalanced. Recent work has found several ways to decrease the degeneration of semi-supervised learning models in class-imbalanced learning. In this article, we comprehensively review class-imbalanced semi-supervised learning (CISSL), starting with an introduction to this field, followed by a realistic evaluation of existing class-imbalanced semi-supervised learning algorithms and a brief summary of them.

In this paper, we propose a Stack Auto-encoder (SAE)-Driven and Semi-Supervised (SSL)-Based Deep Neural Network (DNN) to extract buildings from relatively low-cost satellite near infrared images. The novelty of our scheme is that we employ only an extremely small portion of labeled data for training the deep model which constitutes less than 0.08% of the total data. This way, we significantly reduce the manual effort needed to complete an annotation process, and thus the time required for creating a reliable labeled dataset. On the contrary, we apply novel semi-supervised techniques to estimate soft labels (targets) of the vast amount of existing unlabeled data and then we utilize these soft estimates to improve model training. Overall, four SSL schemes are employed, the Anchor Graph, the Safe Semi-Supervised Regression (SAFER), the Squared-loss Mutual Information Regularization (SMIR), and an equal importance Weighted Average of them (WeiAve). To retain only the most meaning information of the input data, labeled and unlabeled ones, we also employ a Stack Autoencoder (SAE) trained under an unsupervised manner. This way, we handle noise in the input signals, attributed to dimensionality redundancy, without sacrificing meaningful information. Experimental results on the benchmarked dataset of Vaihingen city in Germany indicate that our approach outperforms all state-of-the-art methods in the field using the same type of color orthoimages, though the fact that a limited dataset is utilized (10 times less data or better, compared to other approaches), while our performance is close to the one achieved by high expensive and much more precise input information like the one derived from Light Detection and Ranging (LiDAR) sensors. In addition, the proposed approach can be easily expanded to handle any number of classes, including buildings, vegetation, and ground.

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.

In vehicular networks, federated learning (FL) has been used for secure and distributed edge intelligence to support deep neural network (DNN) model training. In the FL, the roadside units (RSUs) and vehicles act as the parameter servers and clients, respectively. However, the raw data collected by the vehicles are normally unlabeled, which can hardly meet the requirements of the supervised learning tasks. To resolve the related issues, a federated semi‐supervised learning (FSSL) framework is proposed in this paper. By leveraging semi‐supervised learning (SSL), the framework can implement the model training with unlabeled data in vehicles and a small set of manually annotated data in the RSU. Furthermore, a pseudo‐label selection method is developed for the vehicles to improve the local pseudo‐label prediction accuracy and the convergence of global model training. Simulation experiments have been conducted to evaluate the performance of the proposed FSSL framework. The experimental results show that the proposed framework can effectively utilize unlabeled data in vehicular networks and complete the task of DNN model training. A federated semi‐supervised learning (FSSL) framework is proposed for vehicular networks in this paper. By leveraging semi‐supervised learning (SSL), the framework can implement the model training with unlabeled data in vehicles and a small set of manually annotated data in the RSU. Furthermore, a pseudo‐label selection method is developed for the vehicles to improve the local pseudo‐label prediction accuracy and the convergence of global model training.

Existing knowledge distillation methods mostly focus on distillation of teacher’s prediction and intermediate activation. However, the structured representation, which arguably is one of the most critical ingredients of deep models, is largely overlooked. In this work, we propose a novel semantic representational distillation (SRD) method dedicated for distilling representational knowledge semantically from a pretrained teacher to a target student. The key idea is that we leverage the teacher’s classifier as a semantic critic for evaluating the representations of both teacher and student and distilling the semantic knowledge with high-order structured information over all feature dimensions. This is accomplished by introducing a notion of cross-network logit computed through passing student’s representation into teacher’s classifier. Further, considering the set of seen classes as a basis for the semantic space in a combinatorial perspective, we scale SRD to unseen classes for enabling effective exploitation of largely available, arbitrary unlabeled training data. At the problem level, this establishes an interesting connection between knowledge distillation with open-set semi-supervised learning (SSL). Extensive experiments show that our SRD outperforms significantly previous state-of-the-art knowledge distillation methods on both coarse object classification and fine face recognition tasks, as well as less studied yet practically crucial binary network distillation. Under more realistic open-set SSL settings we introduce, we reveal that knowledge distillation is generally more effective than existing out-of-distribution sample detection, and our proposed SRD is superior over both previous distillation and SSL competitors. The source code is available at https://github.com/jingyang2017/SRD_ossl .

The challenge in sourcing attribution for forgery faces has gained widespread attention due to the rapid development of generative techniques. While many recent works have taken essential steps on GAN-generated faces, more threatening attacks related to identity swapping or diffusion models are still overlooked. And the forgery traces hidden in unknown attacks from the open-world unlabeled faces remain under-explored. To push the related frontier research, we introduce a novel task named Open-World DeepFake Attribution, and the corresponding benchmark OW-DFA++, which aims to evaluate attribution performance against various types of fake faces in open-world scenarios. Meanwhile, we propose a Multi-Perspective Sensory Learning (MPSL) framework that aims to address the challenge of OW-DFA++. Since different forged faces have different tampering regions and frequency artifacts, we introduce the Multi-Perception Voting (MPV) module, which aligns inter-sample features based on global, multi-scale local, and frequency relations. The MPV module effectively filters and groups together samples belonging to the same attack type. Pseudo-labeling is another common and effective strategy in semi-supervised learning tasks, and we propose the Confidence-Adaptive Pseudo-labeling (CAP) module, using soft pseudo-labeling to enhance the class compactness and mitigate pseudo-noise induced by similar novel attack methods. The CAP module imposes strong constraints and adaptively filters samples with high uncertainty to improve the accuracy of the pseudo-labeling. In addition, we extend the MPSL framework with a multi-stage paradigm that leverages pre-train technique and iterative learning to further enhance traceability performance. Extensive experiments and visualizations verify the superiority of our proposed method on the OW-DFA++ and demonstrate the interpretability of the deepfake attribution task and its impact on improving the security of the deepfake detection area.

Infrared small target detection faces significant challenges due to limited labelled data and complex background interference. This paper proposes a semi‐supervised learning framework that integrates pseudo‐labelling and two‐dimensional Gaussian prediction modelling to address these challenges. By leveraging unlabelled data through adaptive pseudo‐label generation, the framework enhances model generalisation. A novel two‐dimensional Gaussian prediction model is introduced during inference to characterise target spatial distributions, enabling precise localisation under noisy backgrounds. Additionally, a correlation‐aware loss function optimises the prediction model parameters by enforcing physical constraints between amplitude and spatial spread. Experiments on the SIRST dataset demonstrate state‐of‐the‐art performance, achieving 0.05 higher F1‐score and 4.9% higher AP compared to existing methods. This framework provides a robust solution for infrared small target detection in surveillance and remote sensing applications. 1.Pseudo‐labelling for limited labelled data: Our framework leverages unlabelled data and assigns pseudo‐labels to expand the training dataset, improving model performance and generalisation in the presence of limited labelled samples. 2.Two‐dimensional Gaussian prediction modelling: Instead of preprocessing, our approach performs Gaussian prediction during inference, accurately capturing complex background interference and generating high‐quality pseudo‐labels for more accurate target detection. 3.Novel loss function for parameter correlation: Our designed loss function optimises the prediction model parameters by considering their correlation, ensuring accurate capture of target and background interference characteristics, and enhancing the overall framework's performance.

Recently, graph-based semi-supervised learning (GSSL) has received much attention. On the other hand, less attention has been paid to the problem of large-scale GSSL for inductive multi-class classification. Existing scalable GSSL methods rely on a hard linear constraint. They cannot predict the labelling of test samples, or use predefined graphs, which limits their applications and performance. In this paper, we propose an inductive algorithm that can handle large databases by using anchors. The main contribution compared to existing scalable semi-supervised models is the integration of the anchor graph computation into the learned model. We develop a criterion to jointly estimate the unlabeled sample labels, the mapping of the feature space to the label space, and the affinity matrix of the anchor graph. Furthermore, the fusion of labels and features of anchors is used to construct the graph. Using the projection matrix, it can also predict the labels of the test samples by linear transformation. Experimental results on the large datasets NORB, RCV1 and Covtype show the effectiveness, scalability and superiority of the proposed method. The code of the proposed method can be found at the following link https://github.com/ZoulfikarIB/SGRFME .

INTRODUCTION Identifying dementia neuropathology is critical for guiding effective therapies and clinical trials. To tackle this, we developed semi‐supervised models for identifying neuropathology using low‐burden data to improve generalizability. METHODS We defined low‐burden data as being reasonably obtainable at a primary care setting. By using a semi‐supervised learning paradigm, we can amplify the utility of low‐burden data. We trained a clustering and a semi‐supervised prediction model to yield clustering and prediction results for different neuropathology lesion types. RESULTS Our clustering model identified two clinically meaningful outlier groups that were either neuropathology‐enriched or ‐scarce. We predicted neuropathology burden across different pathology types and found that using low‐burden data over multiple clinical visits can predict neuropathology on par with using higher‐burden data. DISCUSSION This work fills a critical gap in the field by using low‐burden clinical data to predict neuropathology, thereby improving dementia screening, therapy, and targeted clinical trials. Highlights Clinical data are useful for neuropathology screening in future clinical trials. Novel application of semi‐supervised learning for identifying neuropathology. Clustering model found groups with highly different neuropathology prevalence. Low‐burden data can provide relatively accurate predictions of pathology load. Higher‐burden, longitudinal data are most helpful for predicting vascular lesions.