IPF-RDA: An Information-Preserving Framework for Robust Data Augmentation.

Data augmentation (DA) is widely employed to improve the generalization performance of deep models. However, most existing DA methods employ augmentation operations with fixed or random magnitudes throughout the training process. While this fosters data diversity, it can also inevitably introduce uncontrolled variability in augmented data, which could potentially cause misalignment with the evolving training status of the target models. Both theoretical and empirical findings suggest that this misalignment increases the risks of both underfitting and overfitting. To address these limitations, we propose AdaAugment, an innovative and tuning-free adaptive augmentation method that leverages reinforcement learning to dynamically and adaptively adjust augmentation magnitudes for individual training samples based on real-time feedback from the target network. Specifically, AdaAugment features a dual-model architecture consisting of a policy network and a target network, which are jointly optimized to adapt augmentation magnitudes in accordance with the model's training progress effectively. The policy network optimizes the variability within the augmented data, while the target network utilizes the adaptively augmented samples for training. These two networks are jointly optimized and mutually reinforce each other. Extensive experiments across benchmark datasets and deep architectures demonstrate that AdaAugment consistently outperforms other state-of-the-art DA methods in effectiveness while maintaining remarkable efficiency. Code is available at https://github.com/Jackbrocp/AdaAugment.

Data augmentation (DA) increases the diversity of training data to improve the model generalization ability. Most of the DA methods focus on image classification or object detection. Directly using the existing DA methods on change detection tasks not only falls short of fully exploring the specificity of the change image pairs but also leads to longer training times. In this article, we first propose a mask-guided mixing (MGM) DA for change detection, which mixes the change regions of the current training sample based on prediction results and labels to generate high-quality samples with more positive samples. We then propose a new reinforcement learning (RL)-based Adaptive DA method, AdaAug+, to adaptively select the optimal DA policy for the training samples. An actor selects the best augmentation operation from the operation set according to the image pair. The augmented image pairs make it easier for the change detector to learn the optimal parameters and improve the final detection performance. To reduce the training time, we identify and remove the redundant training samples during the training process by our redundancy searching policy. We have conducted various experiments on four remote sensing change detection datasets with different change detectors. The experimental results demonstrate that AdaAug+ achieves promising performance compared to the state-of-the-art DA methods and requires less training time.

Achieving high classification accuracy in motor-imagery-based brain-computer interfaces (BCIs) requires substantial amounts of training data. A challenge arises because of the impracticality of measuring large amounts of data from users. Data augmentation (DA) has emerged as a promising solution for this challenge. We propose a novel DA method called channel&label-flip DA that involves not only flipping channels but also flipping class labels. This method is based on the neuroscience finding that motor imageries of left- and right-hand movements are roughly symmetrical. The efficiency of the proposed method was evaluated using the OpenBMI dataset, which comprises electroencephalograms collected from 54 participants engaged in left- and right-hand motor imagery tasks. To compare the impact on classifiers, we employed three classical machine learning models utilizing filter bank common spatial pattern features, along with a deep learning-based model that uses raw signal input. As a result, the channel&label-flip DA improved the classification accuracy on average, whereas simple flipping of the channels reduced the classification accuracy compared to the case without DA.

Discriminative feature constraints via supervised contrastive learning for few-shot forest tree species classification using airborne hyperspectral images

Pedestrian detection plays a crucial role in autonomous driving by identifying the position, size, orientation, and dynamic features of pedestrians in images or videos, assisting autonomous vehicles in making better decisions and controls. It’s worth noting that the performance of pedestrian detection models largely depends on the quality and diversity of available training data. Current datasets for autonomous driving have limitations in terms of diversity, scale, and quality. In recent years, numerous studies have proposed the use of data augmentation strategies to expand the coverage of datasets, aiming to maximize the utilization of existing training data. However, these data augmentation methods often overlook the diversity of data scenarios. To overcome this challenge, in this paper, we propose a more comprehensive method for data augmentation, based on image descriptions and diffusion models. This method aims to cover a wider range of scene variations, including different weather conditions and lighting situations. We have designed a classifier to select data samples for augmentation, followed by extracting visual features based on image captions and converting them into high-level semantic information as textual descriptions for the corresponding samples. Finally, we utilize diffusion models to generate new variants. Additionally, we have designed three modification patterns to increase diversity in aspects such as weather conditions, lighting, and pedestrian poses within the data. We conducted extensive experiments on the KITTI dataset and in real-world environments, demonstrating that our proposed method significantly enhances the performance of pedestrian detection models in complex scenarios. This meticulous consideration of data augmentation will notably enhance the applicability and robustness of pedestrian detection models in actual autonomous driving scenarios.

Intelligent fault diagnosis is an important method in rotating machinery fault diagnosis and equipment health management. To deal with co-frequency vibration faults, a type of typical fault in rotating machinery, this paper proposes a fault diagnosis method based on the stacked autoencoder (SAE) and ensembled ResNet-SVM. Furthermore, the time- and frequency-domain features of several co-frequency vibration faults are summarized based on the mechanism analysis and calculated using actual vibration data. To realize and validate the high-precision diagnosis method of rotating equipment with co-frequency faults proposed in this study, the following three criteria are required: First, to improve the effectiveness and robustness of the ensembled model and the sliding window using data augmentation, adding noise, autoencoder (AE) and SAE methods are analyzed in terms of principle and practical effects. Second, ResNet is used as the feature extractor for the ensembled ResNet-SVM model. Feature extraction is carried out twice, and the extracted co-frequency fault features are more comprehensive. Finally, the data augmentation method and ensemble ResNet-SVM are combined for fault diagnosis and compared with other methods. The experimental results show that the accuracy of the proposed method can exceed 99.9%.

The rapid serial visual presentation-based brain–computer interface (RSVP-BCI) system achieves the recognition of target images by extracting event-related potential (ERP) features from electroencephalogram (EEG) signals and then building target classification models. Currently, how to reduce the training and calibration time for classification models across different subjects is a crucial issue in the practical application of RSVP. To address this issue, a zero-calibration (ZC) method termed Attention-ProNet, which involves meta-learning with a prototype network integrating multiple attention mechanisms, was proposed in this study. In particular, multiscale attention mechanisms were used for efficient EEG feature extraction. Furthermore, a hybrid attention mechanism was introduced to enhance model generalization, and attempts were made to incorporate suitable data augmentation and channel selection methods to develop an innovative and high-performance ZC RSVP-BCI decoding model algorithm. The experimental results demonstrated that our method achieved a balance accuracy (BA) of 86.33% in the decoding task for new subjects. Moreover, appropriate channel selection and data augmentation methods further enhanced the performance of the network by affording an additional 2.3% increase in BA. The model generated by the meta-learning prototype network Attention-ProNet, which incorporates multiple attention mechanisms, allows for the efficient and accurate decoding of new subjects without the need for recalibration or retraining.

3D human pose estimation plays important roles in various human-machine interactive applications, but lacking diversity in existing labeled 3D human posture dataset restricts the generalization ability of deep learning based models. Data augmentation is therefore an important method to solve this problem. However, data augmentation and pose estimation network training are usually treated as two isolated processes, limiting the performance of pose estimation network. In this paper, we developed an improved data augmentation method which jointly performs pose network estimation and data augmentation by designing a reward/penalty strategy for effective joint training, making model training and data augmentation improve each other. In particular, an improved evolutionary data augmentation method is proposed to generate the distribution of nodes in crossover and rotation angles in mutation through the process of the evolution. Extensive experiments show that our approach not only significantly improves state-of-the-art models without additional data efforts but also is extremely competitive with other advanced methods.

Combinations of data augmentation methods and deep learning architectures for automatic pancreas segmentation on CT images are proposed and evaluated. Images from a public CT dataset of pancreas segmentation were used to evaluate the models. Baseline U-net and deep U-net were chosen for the deep learning models of pancreas segmentation. Methods of data augmentation included conventional methods, mixup, and random image cropping and patching (RICAP). Ten combinations of the deep learning models and the data augmentation methods were evaluated. Four-fold cross validation was performed to train and evaluate these models with data augmentation methods. The dice similarity coefficient (DSC) was calculated between automatic segmentation results and manually annotated labels and these were visually assessed by two radiologists. The performance of the deep U-net was better than that of the baseline U-net with mean DSC of 0.703–0.789 and 0.686–0.748, respectively. In both baseline U-net and deep U-net, the methods with data augmentation performed better than methods with no data augmentation, and mixup and RICAP were more useful than the conventional method. The best mean DSC was obtained using a combination of deep U-net, mixup, and RICAP, and the two radiologists scored the results from this model as good or perfect in 76 and 74 of the 82 cases.

A Brief Survey on Semantic-preserving Data Augmentation

Low-resource languages often face the problem of insufficient data, which leads to poor quality in machine translation. One approach to address this issue is data augmentation. Data augmentation involves creating new data by transforming existing data through methods such as flipping, cropping, rotating, and adding noise. Traditionally, pseudo-parallel corpora are generated by randomly replacing words in low-resource language machine translation. However, this method can introduce ambiguity, as the same word may have different meanings in different contexts. This study proposes a new approach for low-resource language machine translation, which involves generating pseudo-parallel corpora by replacing phrases. The performance of this approach is compared with other data augmentation methods, and it is observed that combining it with other data augmentation methods further improves performance. To enhance the robustness of the model, R-Drop regularization is also used. R-Drop is an effective method for improving the quality of machine translation. The proposed method was tested on Chinese–Kazakh (Arabic script) translation tasks, resulting in performance improvements of 4.99 and 7.7 for Chinese-to-Kazakh and Kazakh-to-Chinese translations, respectively. By combining the generation of pseudo-parallel corpora through phrase replacement with the application of R-Drop regularization, there is a significant advancement in machine translation performance for low-resource languages.

The success of training deep Convolutional Neural Networks (CNNs) heavily depends on a significant amount of labelled data. Recent research has found that neural style transfer algorithms can apply the artistic style of one image to another image without changing the latter's high-level semantic content, which makes it feasible to employ neural style transfer as a data augmentation method to add more variation to the training dataset. The contribution of this paper is a thorough evaluation of the effectiveness of the neural style transfer as a data augmentation method for image classification tasks. We explore the state-of-the-art neural style transfer algorithms and apply them as a data augmentation method on Caltech 101 and Caltech 256 dataset, where we found around 2% improvement from 83% to 85% of the image classification accuracy with VGG16, compared with traditional data augmentation strategies. We also combine this new method with conventional data augmentation approaches to further improve the performance of image classification. This work shows the potential of neural style transfer in computer vision field, such as helping us to reduce the difficulty of collecting sufficient labelled data and improve the performance of generic image-based deep learning algorithms.

Data augmentation has been broadly applied in training deep-learning models to increase the diversity of data. This study ingestigates the effectiveness of different data augmentation methods for deep-learningbased human intention prediction when only limited training data is available. A human participant pitches a ball to nine potential targets in our experiment. We expect to predict which target the participant pitches the ball to. Firstly, the effectiveness of 10 data augmentation groups is evaluated on a single-participant data set using RGB images. Secondly, the best data augmentation method (i.e., random cropping) on the single-participant data set is further evaluated on a multi-participant data set to assess its generalization ability. Finally, the effectiveness of random cropping on fusion data of RGB images and optical flow is evaluated on both single- and multi-participant data sets. Experiment results show that: 1) Data augmentation methods that crop or deform images can improve the prediction performance; 2) Random cropping can be generalized to the multi-participant data set (prediction accuracy is improved from 50% to 57.4%); and 3) Random cropping with fusion data of RGB images and optical flow can further improve the prediction accuracy from 57.4% to 63.9% on the multi-participant data set.

As an essential part of the telemedicine system, teleradiology not only realizes mutual recognition of image diagnosis among medical institutions, but also ensures the quality of medical image diagnosis. In this paper, an edge computing (EC) driven 5G teleradiology framework is proposed to segment glioma accurately. In our framework, through the high-speed transmission and sharing mechanism of medical image data under 5G condition, the high-definition magnetic resonance imaging (MRI) images data of glioma patients are delivered to the edge server for data augmentation and training. Three typical data augmentation methods, i.e., traditional geometric transformation, DCGAN, and CycleGAN, are used to study the impact of the proportions of synthetic images generated by the above data augmentation methods to original MRI images on the performance of glioma segmentation. It is observed that training with different proportions leads to different segmentation results. Based on this observation, an efficient data augmentation strategy is established, which exploits the optimal proportions of synthetic and original data to yield the best glioma segmentation results in terms of sensitivity, specificity, accuracy, and Dice score. Experiments on the BraTS dataset show that the proposed data augmentation strategy improves the average Dice score of Dense U-net compared to the conventional data augmentation method. With the aid of our EC driven 5G teleradiology framework, accurate glioma segmentation results can be acquired rapidly at the terminal equipment to facilitate the online diagnosis.

Deep learning has recently been applied to automatically classify the modulation categories of received radio signals without manual experience. However, training deep learning models requires massive volume of data. An insufficient training data will cause serious overfitting problem and degrade the classification accuracy. To cope with small dataset, data augmentation has been widely used in image processing to expand the dataset and improve the robustness of deep learning models. However, in wireless communication areas, the effect of different data augmentation methods on radio modulation classification has not been studied yet. In this paper, we evaluate different data augmentation methods via a state-of-the-art deep learning-based modulation classifier. Based on the characteristics of modulated signals, three augmentation methods are considered, i.e., rotation, flip, and Gaussian noise, which can be applied in both training phase and inference phase of the deep learning algorithm. Numerical results show that all three augmentation methods can improve the classification accuracy. Among which, the rotation augmentation method outperforms the flip method, both of which achieve higher classification accuracy than the Gaussian noise method. Given only 12.5% of training dataset, a joint rotation and flip augmentation policy can achieve even higher classification accuracy than the baseline with initial 100% training dataset without augmentation. Furthermore, with data augmentation, radio modulation categories can be successfully classified using shorter radio samples, leading to a simplified deep learning model and shorter the classification response time.