Do Not Have Enough Data? Deep Learning to the Rescue!

Even if recent Transformer-based architectures, such as BERT, achieved impressive results in semantic processing tasks, their fine-tuning stage still requires large scale training resources. Usually, Data Augmentation (DA) techniques can help to deal with low resource settings. In Text Classification tasks, the objective of DA is the generation of well-formed sentences that i) represent the desired task category and ii) are novel with respect to existing sentences. In this paper, we propose a neural approach to automatically learn to generate new examples using a pre-trained sequence-to-sequence model. We first learn a task-oriented similarity function that we use to pair similar examples. Then, we use these example pairs to train a model to generate examples. Experiments in low resource settings show that augmenting the training material with the proposed strategy systematically improves the results on text classification and natural language inference tasks by up to 10% accuracy, outperforming existing DA approaches.

Most Facial Expression Recognition (FER) systems rely on machine learning approaches that require large databases for an effective training. As these are not easily available, a good solution is to augment the databases with appropriate data augmentation (DA) techniques, which are typically based on either geometric transformation or oversampling augmentations (e.g., generative adversarial networks (GANs)). However, it is not always easy to understand which DA technique may be more convenient for FER systems because most state-of-the-art experiments use different settings which makes the impact of DA techniques not comparable. To advance in this respect, in this paper, we evaluate and compare the impact of using well-established DA techniques on the emotion recognition accuracy of a FER system based on the well-known VGG16 convolutional neural network (CNN). In particular, we consider both geometric transformations and GAN to increase the amount of training images. We performed cross-database evaluations: training with the "augmented" KDEF database and testing with two different databases (CK+ and ExpW). The best results were obtained combining horizontal reflection, translation and GAN, bringing an accuracy increase of approximately 30%. This outperforms alternative approaches, except for the one technique that could however rely on a quite bigger database.

Improving the prediction of extreme wind speed events with generative data augmentation techniques

One of the common challenges in medical artificial intelligence (AI) applications using echocardiography is the lack of image data harmonization. This study aims to improve the prediction accuracy of left ventricular ejection fraction (LVEF) AI models by incorporating data augmentation (DA) techniques to address the variability in image data across different vendor machines. A database comprising 15,770 echocardiographic videos from 3154 patients across five different centers was utilized, with the data acquired using various vendor machines. We prepared datasets specific to GE healthcare (GE), philips (PH), and canon medical systems (CA) vendors, including 1911, 804, and 427 cohorts, respectively. A three-dimensional convolutional neural network (3D-CNN) was trained to predict LVEF, using videos consisting of 20 images per heartbeat as input, with training performed exclusively on data from GE machines (GE-based model). DA techniques, including gamma correction, scaling, median filtering, unsharp masking, translation, rotation, noise correction, and image conversion using a cycle generative adversarial network, were applied. A regression analysis using five different chamber views was performed on the GE test data. The accuracy of LVEF prediction using the GE-based model with DA—specifically gamma correction, scaling, and translation corrections—was excellent. The mean absolute error (root mean square error) in test cohorts was 4.33 (5.58) for GE, 4.42 (5.57) for PH, and 4.89 (6.57) for CA, which were comparable to the results of a model developed using data from all vendors, demonstrating the effectiveness of DA in harmonizing images. This study demonstrates that echocardiographic videos are transferable across vendors and that DA is highly effective in improving LVEF predictions from data acquired using different vendor machines.Supplementary InformationThe online version contains supplementary material available at 10.1038/s41598-025-21277-y.

Objective: The only possible solution to increase the patients’ fatality rate is lung cancer early-stage detection. Recently, deep learning techniques became the most promising methods in medical image analysis compared with other numerous computer-aided diagnostic techniques. However, deep learning models always get lower performance when the model is overfitting. Methods: We present a Lung Cancer Data Augmented Ensemble (LCDAE) framework to solve the overfitting and lower performance problems in the lung cancer classification tasks. The LCDAE has 3 parts: The Lung Cancer Deep Convolutional GAN, which can synthesize images of lung cancer; A Data Augmented Ensemble model (DA-ENM), which ensembled 6 fine-tuned transfer learning models for training, testing, and validating on a lung cancer dataset; The third part is a Hybrid Data Augmentation (HDA) which combines all the data augmentation techniques in the LCDAE. Results: By comparing with existing state-of-the-art methods, the LCDAE obtains the best accuracy of 99.99%, the precision of 99.99%, and the F1-score of 99.99%. Conclusion: Our proposed LCDAE can overcome the overfitting issue for the lung cancer classification tasks by applying different data augmentation techniques, our method also has the best performance compared to state-of-the-art approaches.

Mammography is the primary procedure for breast cancer screening, attempting to reduce breast cancer mortality risk with early detection. Deep learning methods have shown strong applicability to various medical images datasets. Due to paucity of available labeled medical images, accurate computer assisted diagnosis requires intensive data augmentation (DA) techniques, such as geometric/intensity transformations of original images. This data when used along with the training data helps to address the limited medical image dataset collected from various sources. Generative Adversarial Networks (GANs) is one of the DA techniques. GAN trained on images can generate new images that contain many authentic characteristics and look realistic to human observers. Therefore, this paper focuses on overcoming the problem of limited labeled dataset, using Deep Convolution GANs (DCGANs). To analyze the closeness between the original and synthetic images, a visualization tool ImageJ was used. In order to validate the proposed model, a visual Turing test was conducted with the help of medical experts.

Eye-tracking technology enables communication for individuals with muscle control difficulties, making it a valuable assistive tool. Traditional systems rely on electrooculography (EOG) or infrared devices, which are accurate but costly and invasive. While vision-based systems offer a more accessible alternative, they have not been extensively explored for eye-writing recognition. Additionally, the natural instability of eye movements and variations in writing styles result in inconsistent signal lengths, which reduces recognition accuracy and limits the practical use of eye-writing systems. To address these challenges, we propose a novel vision-based eye-writing recognition approach that utilizes a webcam-captured dataset. A key contribution of our approach is the introduction of a Discrete Fourier Transform (DFT)-based length normalization method that standardizes the length of each eye-writing sample while preserving essential spectral characteristics. This ensures uniformity in input lengths and improves both efficiency and robustness. Moreover, we integrate a hybrid deep learning model that combines 1D Convolutional Neural Networks (CNN) and Temporal Convolutional Networks (TCN) to jointly capture spatial and temporal features of eye-writing. To further improve model robustness, we incorporate data augmentation and initial-point normalization techniques. The proposed system was evaluated using our new webcam-captured Arabic numbers dataset and two existing benchmark datasets, with leave-one-subject-out (LOSO) cross-validation. The model achieved accuracies of 97.68% on the new dataset, 94.48% on the Japanese Katakana dataset, and 98.70% on the EOG-captured Arabic numbers dataset—outperforming existing systems. This work provides an efficient eye-writing recognition system, featuring robust preprocessing techniques, a hybrid deep learning model, and a new webcam-captured dataset.

Recent deep neural network models trained on smaller and less diverse datasets use data augmentation to alleviate limitations such as overfitting, reduced robustness, and lower generalization. Methods using 3D datasets are among the most common to use data augmentation techniques such as random point drop, scaling, translation, rotations, and jittering. However, these data augmentation techniques are fixed and are often applied to the entire object, ignoring the object’s local geometry. Different local neighborhoods on the object surface hold a different amount of geometric complexity. Applying the same data augmentation techniques at the object level is less effective in augmenting local neighborhoods with complex structures. This paper presents PatchAugment, a data augmentation framework to apply different augmentation techniques to the local neighborhoods. Our experimental studies on PointNet++ and DGCNN models demonstrate the effectiveness of PatchAugment on the task of 3D Point Cloud Classification. We evaluated our technique against these models using four benchmark datasets, ModelNet40 (synthetic), ModelNetlO (synthetic), SHREC’16 (synthetic) and ScanObjectNN (real-world).

目的 基于计算机的胸腔X线影像疾病检测和分类目前存在误诊率高，准确率低的问题。本文在视觉Transformer（vision Transformer，ViT）预训练模型的基础上，通过迁移学习方法，实现胸腔X线影像辅助诊断，提高诊断准确率和效率。方法 选用带有卷积神经网络（convolutional neural network，CNN）的ViT模型，其在超大规模自然图像数据集中进行了预训练；通过微调模型结构，使用预训练的ViT模型参数初始化主干网络，并迁移至胸腔X线影像数据集中再次训练，实现疾病多标签分类。结果 在IU X-Ray数据集中对ViT迁移学习前、后模型平均AUC（area under ROC curve）得分进行对比分析实验。结果表明，预训练ViT模型平均AUC得分为0.774，与不使用迁移学习相比提升了0.208。并针对模型结构和数据预处理进行了消融实验，对ViT中的注意力机制进行可视化，进一步验证了模型有效性。最后使用Chest X-Ray14和CheXpert数据集训练微调后的ViT模型，平均AUC得分为0.839和0.806，与对比方法相比分别有0.014～0.031的提升。结论 与其他方法相比，ViT模型胸腔X线影像的多标签分类精确度更高，且迁移学习可以在降低训练成本的同时提升ViT模型的分类性能和泛化性。消融实验与模型可视化表明，包含CNN结构的ViT模型能重点关注有意义的区域，高效获取胸腔X线影像的视觉特征。;Objective The chest X-ray-relevant screening and diagnostic method is essential for radiology nowadays. Most of chest X-ray images interpretation is still restricted by clinical experience and challenged for misdiagnose and missed diagnoses. To detect and identify one or more potential diseases in images automatically，it is beneficial for improving diagnostic efficiency and accuracy using computer-based technique. Compared to natural images，multiple lesions are challenged to be detected and distinguished accurately in a single image because abnormal areas have a small proportion and complex representations in chest X-ray images. Current convolutional neural network（CNN）based deep learning models have been widely used in the context of medical imaging. The structure of the CNN convolution kernel has sensitive to local detail information，and it is possible to extract richer image features. However，the convolution kernel cannot be used to get global information，and the features-extracted are restricted of redundant information like its relevance of background， muscles，and bones. The model’s performance in multi-label classification tasks are affected to a certain extent. At present，the vision Transformer（ViT）model has achieved its priorities in computer vision-related tasks. The ViT can be used to capture information simultaneously and effectively for multiple regions of the entire image. However，it is required to use large-scale dataset training to achieve good performance. Due to some factors like patient privacy and manual annotate costs，the size of the chest X-ray image data set has been limited. To reduce the model's dependence on data scale and improve the performance of multi-label classification，we develop the CNN-based ViT pre-training model in terms of the transfer learning method for diagnosis-assisted of chest X-ray image and multi-label classification. Method The CNN-based ViT model is pre-trained on a huge scale ground truth dataset，and it is used to obtain the initial parameters of the model. The model structure is fine-tuned according to the features of chest X-ray dataset. A 1×1 convolution layer is used to convert the chest X-ray images channels between 1 to 3. The number of output nodes of the linear layer in the classifier is balanced from 1 000 to the number of chest X-ray classification labels，and the Sigmoid is used as an activation function. The parameters of the backbone network are initialized in terms of the pre-trained ViT model parameters，and it is trained in the chest X-ray dataset after that to complete multi-label classification. The experiment is configured of Python3. 7 and PyTorch1. 8 to construct the model and RTX3090 GPU for training. Stochastic gradient descent（SGD）optimizer，binary cross-entropy（BCE）loss function，an initial learning rate of 1E-3，the cosine annealing learning rate decay are used. For training，each image is scaled to a size of 512×512 pixels，and a 224×224 pixels area and it is then cropped in random as the model input，and data augmentation is performed randomly by some of the flipping，perspective transformation， shearing，translation，zooming，and changing brightness. For testing，the chest X-ray image is scaled to 256×256 pixels and center crop a 224×224 area to input the trained model. Result The experiment is performed on the IU X-Ray，which is a small-scale chest X-ray dataset. This model is evaluated in quantitative using the average of area under ROC curve （AUC）scores across all classification labels. The results show that the average AUC score of the pre-trained ViT model is 0. 774. The accuracy and training efficiency of the non-pre-trained ViT model is dropped significantly. The average AUC score is reached to 0. 566 only，which is 0. 208 lower. In addition，the attention mechanism heat map is generated based on the ViT model，which can strengthen the interpretability of the model. A series of ablation experiments are carried out for data augmentation，model structure，and batch size design. The fine-tuned ViT model is trained on the Chest-Ray14 and CheXpert dataset as well. The average AUC score is reached to 0. 839 and 0. 806，which is optimized by 0. 014 and 0. 031. Conclusion A pre-trained ViT model is used for the multi-label classification of chest X-ray images via transfer learning. The experimental results illustrate that the ViT has its stronger multi-label classification performance in chest Xray images，and its attention mechanism is beneficial for lesions precision-focused like the interior of the chest cavity and the heart. Transfer learning is potential to improve the classification performance and model generalization of the ViT in small-scale datasets，and the training cost is reduced greatly. Ablation experiments demonstrate that the incorporated model of CNN and Transformer has its priority beyond single-structure model. Data enhancement and the batch size cutting can improve the performance of the model，but smaller scale of batch is still interlinked to longer training span. To improve the model's ability，we predict that future research direction can be focused on the extraction for complex disease and highlevel semantic information，such as their small lesions，disease location，and severity.

Deep learning has revolutionized the performance of classification and object detection, but meanwhile demands sufficient labeled data for training. Given insufficient data, while many techniques have been developed to help combat overfitting, the challenge remains if one tries to train deep networks, especially in the ill-posed <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">extremely low data regimes</i> : only a small set of labeled data are available, and nothing – including unlabeled data – else. Such regimes arise from practical situations where not only data labeling but also data collection itself is expensive. We propose a deep adversarial data augmentation (DADA) technique to address the problem, in which we elaborately formulate data augmentation as a problem of training a class-conditional and supervised generative adversarial network (GAN). Specifically, a new discriminator loss is proposed to fit the goal of data augmentation, through which both real and augmented samples are enforced to contribute to and be consistent in finding the decision boundaries. Tailored training techniques are developed accordingly. To quantitatively validate its effectiveness, we first perform extensive simulations to show that DADA substantially outperforms both traditional data augmentation and a few GAN-based options. We then extend experiments to three real-world small labeled classification datasets where existing data augmentation and/or transfer learning strategies are either less effective or infeasible. We also demonstrate that DADA to can be extended to the detection task. We improve the pedestrian synthesis work by substitute for our discriminator and training scheme. Validation experiment shows that DADA can improve the detection mean average precision (mAP) compared with some traditional data augmentation techniques in object detection. Source code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/SchafferZhang/DADA</uri> .

The extensive utilization of drones has led to numerous scenarios that encompass both advantageous and perilous outcomes. By using deep learning techniques, this study aimed to reduce the dangerous effects of drone use through early detection of drones. The purpose of this study is the evaluation of deep learning approaches such as pre-trained YOLOv8 drone detection for security issues. This study focuses on the YOLOv8 model to achieve optimal performance in object detection tasks using a publicly available dataset collected by Mehdi Özel for a UAV competition that is sourced from GitHub. These images are labeled using Roboflow, and the model is trained on Google Colab. YOLOv8, known for its advanced architecture, was selected due to its suitability for real-time detection applications and its ability to process complex visual data. Hyperparameter tuning and data augmentation techniques were applied to maximize the performance of the model. Basic hyperparameters such as learning rate, batch size, and optimization settings were optimized through iterative experiments to provide the best performance. In addition to hyperparameter tuning, various data augmentation strategies were used to increase the robustness and generalization ability of the model. Techniques such as rotation, scaling, flipping, and color adjustments were applied to the dataset to simulate different conditions and variations. Among the augmentation techniques applied to the specific dataset in this study, rotation was found to deliver the highest performance. Blurring and cropping methods were observed to follow closely behind. The combination of optimized hyperparameters and strategic data augmentation allowed YOLOv8 to achieve high detection accuracy and reliable performance on the publicly available dataset. This method demonstrates the effectiveness of YOLOv8 in real-world scenarios, while also highlighting the importance of hyperparameter tuning and data augmentation in increasing model capabilities. To enhance model performance, dataset augmentation techniques including rotation and blurring are implemented. Following these steps, a significant precision value of 0.946, a notable recall value of 0.9605, and a considerable precision–recall curve value of 0.978 are achieved, surpassing many popular models such as Mask CNN, CNN, and YOLOv5.

In analysis of data, data augmentation pertains to ways to raise the availability of data yappending slightly tweaked copies of current data or creating new generated information from the collected data. Data augmentation can assist improve the performance and output of machine learning models by producing new and varied cases to train datasets. Data augmentation techniques, which produce deviations that the model could meet in the real world, might make machine learning models more robust. This research study suggest the use of such audio data augmentation to solve the challenges of data scarcity, and further the impact of various part of this approach is also investigated. The suggested model generates cutting-edge findings for system environmental sound prediction. With the aid of the function, we can also use the 4 kinds of data augmentation to improve the data and show the outcome in an effective manner. Data augmentation is well known for combating over fitting and improving the generalization capabilities of both the input and output systems. The proposed system's recognition performance has improved as a result of the experiments done with four augmentation techniques those are Random Sequential, Random Independent, Specified Sequential, Specified Independent.

Deep learning (DL) has been shown to obtain superior results for classification tasks in the field of remote sensing hyperspectral imaging. Superpixel-based techniques can be applied to DL, significantly decreasing training and prediction times, but the results are usually far from satisfactory due to overfitting. Data augmentation techniques alleviate the problem by synthetically generating new samples from an existing dataset in order to improve the generalization capabilities of the classification model. In this paper we propose a novel data augmentation framework in the context of superpixel-based DL called dual-window superpixel (DWS). With DWS, data augmentation is performed over patches centered on the superpixels obtained by the application of simple linear iterative clustering (SLIC) superpixel segmentation. DWS is based on dividing the input patches extracted from the superpixels into two regions and independently applying transformations over them. As a result, four different data augmentation techniques are proposed that can be applied to a superpixel-based CNN classification scheme. An extensive comparison in terms of classification accuracy with other data augmentation techniques from the literature using two datasets is also shown. One of the datasets consists of small hyperspectral small scenes commonly found in the literature. The other consists of large multispectral vegetation scenes of river basins. The experimental results show that the proposed approach increases the overall classification accuracy for the selected datasets. In particular, two of the data augmentation techniques introduced, namely, dual-flip and dual-rotate, obtained the best results.

The emergent of machine learning (ML) and deep learning (DL) methods have created a substantial window of chance for their use in the industry. Given that both ML and DL algorithms are capable of identifying links between enormous amounts of data, one of the jobs for which these techniques have the most potential is visual inspection. These methods, nevertheless, call for a lot of photographs, which are not always possible to capture. Techniques for data augmentation are used as a remedy for this. Many datasets are created utilizing data augmentation approaches based on geometric transformations, starting from a very unbalanced dataset containing photos of various medical images. Many datasets are created utilizing data augmentation approaches based on geometric transformations, starting from a very unbalanced dataset containing photos of various medical images. The geometric transformation-based data augmentation segments the infected area and the classification process is proposed to highlight the severity of the disease. The proposed suggests an impartial and all-encompassing framework of evaluation for various information augmentation techniques. With this cutting-edge procedure, various augmented techniques are thoroughly and accurately assessed regarding data diversity and classification accurateness utilizing massive public datasets already available. In order to replicate the typical moderate size datasets used in deep learning, a regular-interval sampling strategy constructed on similarity ranking is described that can be used to choice samples from enormous open datasets and produce a subset that can accurately represent the original set. Then, using a variety of data augmentation methods, the augmented datasets are created from the small-sized datasets.

This investigation investigates the influence of a variety of data augmentation techniques on sentiment analysis in low-resource languages, with a particular emphasis on Bulgarian, Croatian, Slovak, and Slovene. The following primary research topic is addressed: is it possible to improve sentiment analysis efficacy in low-resource languages through data augmentation? Our sub-questions look at how different augmentation methods affect performance, how effective WordNet-based augmentation is compared to other methods, and whether lemma-based augmentation techniques can be used, especially for Croatian sentiment tasks. The sentiment-labelled evaluations in the selected languages are included in our data sources, which were curated with additional annotations to standardise labels and mitigate ambiguities. Our findings show that techniques like replacing words with synonyms, masked language model (MLM)-based generation, and permuting and combining sentences can only make training datasets slightly bigger. However, they provide limited improvements in model accuracy for low-resource language sentiment classification. WordNet-based techniques, in particular, exhibit a marginally superior performance compared to other methods; however, they fail to substantially improve classification scores. From a practical perspective, this study emphasises that conventional augmentation techniques may require refinement to address the complex linguistic features that are inherent to low-resource languages, particularly in mixed-sentiment and context-rich instances. Theoretically, our results indicate that future research should concentrate on the development of augmentation strategies that introduce novel syntactic structures rather than solely relying on lexical variations, as current models may not effectively leverage synonymic or lemmatised data. These insights emphasise the nuanced requirements for meaningful data augmentation in low-resource linguistic settings and contribute to the advancement of sentiment analysis approaches.