Mixed Sample Data Augmentation (MSDA) has received increasing attention in recent years, with many successful variants such as MixUp and CutMix. By studying the mutual information between the function learned by a VAE on the original data and on the augmented data we show that MixUp distorts learned functions in a way that CutMix does not. We further demonstrate this by showing that MixUp acts as a form of adversarial training, increasing robustness to attacks such as Deep Fool and Uniform Noise which produce examples similar to those generated by MixUp. We argue that this distortion prevents models from learning about sample specific features in the data, aiding generalisation performance. In contrast, we suggest that CutMix works more like a traditional augmentation, improving performance by preventing memorisation without distorting the data distribution. However, we argue that an MSDA which builds on CutMix to include masks of arbitrary shape, rather than just square, could further prevent memorisation whilst preserving the data distribution in the same way. To this end, we propose FMix, an MSDA that uses random binary masks obtained by applying a threshold to low frequency images sampled from Fourier space. These random masks can take on a wide range of shapes and can be generated for use with one, two, and three dimensional data. FMix improves performance over MixUp and CutMix, without an increase in training time, for a number of models across a range of data sets and problem settings, obtaining a new single model state-of-the-art result on CIFAR-10 without external data. Finally, we show that a consequence of the difference between interpolating MSDA such as MixUp and masking MSDA such as FMix is that the two can be combined to improve performance even further. Code for all experiments is provided at https://github.com/ecs-vlc/FMix .
Indian Institute of Science（印度科学学院）；Indian Institute of Technology (BHU) Varanasi（印度理工学院（瓦拉纳西））
Adversarial training of Deep Neural Networks is known to be significantly more data-hungry when compared to standard training. Furthermore, complex data augmentations such as AutoAugment, which have led to substantial gains in standard training of image classifiers, have not been successful with Adversarial Training. We first explain this contrasting behavior by viewing augmentation during training as a problem of domain generalization, and further propose Diverse Augmentation-based Joint Adversarial Training (DAJAT) to use data augmentations effectively in adversarial training. We aim to hand…
ETH Zürich（苏黎世联邦理工学院）；University Hospital Zürich（苏黎世大学医院）
Supervised deep learning relies on the assumption that enough training data is available, which presents a problem for its application to several fields, like medical imaging. On the example of a binary image classification task (breast cancer recognition), we show that pretraining a generative model for meaningful image augmentation helps enhance the performance of the resulting classifier. By augmenting the data, performance on downstream classification tasks could be improved even with a relatively small training set. We show that this "adversarial augmentation" yields promising results com…
University of Surrey（萨里大学）；Amazon Web Services, Inc.（亚马逊云科技公司）
Data augmentation is an inexpensive way to increase training data diversity and is commonly achieved via transformations of existing data. For tasks such as classification, there is a good case for learning representations of the data that are invariant to such transformations, yet this is not explicitly enforced by classification losses such as the cross-entropy loss. This paper investigates the use of training objectives that explicitly impose this consistency constraint and how it can impact downstream audio classification tasks. In the context of deep convolutional neural networks in the s…
Imperial College London（帝国理工学院）；University of Edinburgh（爱丁堡大学）；Fudan University（复旦大学）；City, University of London（伦敦城市大学）；Technical University of Munich（慕尼黑工业大学）
The success of neural networks on medical image segmentation tasks typically relies on large labeled datasets for model training. However, acquiring and manually labeling a large medical image set is resource-intensive, expensive, and sometimes impractical due to data sharing and privacy issues. To address this challenge, we propose AdvChain, a generic adversarial data augmentation framework, aiming at improving both the diversity and effectiveness of training data for medical image segmentation tasks. AdvChain augments data with dynamic data augmentation, generating randomly chained photo-met…
Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation
Chung-Ang University（中央大学）；Graduate School of Advanced Imaging Sciences, Multimedia and Film, Chung-Ang University（中央大学高级影像科学、多媒体与电影研究生院）；Department of Artificial Intelligence, Chung-Ang University（中央大学人工智能系）
VoteGCL: Enhancing Graph-based Recommendations with Majority-Voting LLM-Rerank Augmentation
Center for AI Research, VinUniversity（越南 Vin 大学人工智能研究中心）；The Chinese University of Hong Kong（香港中文大学）；RMIT University（皇家墨尔本理工大学）；VNU University of Engineering and Technology（越南工程与技术大学）
The data scarcity problem in emotion recognition from electroencephalography (EEG) leads to difficulty in building an affective model with high accuracy using machine learning algorithms or deep neural networks. Inspired by emerging deep generative models, we propose three methods for augmenting EEG training data to enhance the performance of emotion recognition models. Our proposed methods are based on two deep generative models, variational autoencoder (VAE) and generative adversarial network (GAN), and two data augmentation strategies. For the full usage strategy, all of the generated data …
Enhancing Activity Recognition After Stroke: Generative Adversarial Networks for Kinematic Data Augmentation
Hadley Research, LLC（哈德利研究有限责任公司）；Case Western Reserve University（凯斯西储大学）；Louis Stokes Cleveland Department of Veterans Affairs Medical Center（路易斯·斯托克斯克利夫兰退伍军人事务部医疗中心）
Malicious attackers can generate targeted adversarial examples by imposing tiny noises, forcing neural networks to produce specific incorrect outputs. With cross-model transferability, network models remain vulnerable even in black-box settings. Recent studies have shown the effectiveness of ensemble-based methods in generating transferable adversarial examples. To further enhance transferability, model augmentation methods aim to produce more networks participating in the ensemble. However, existing model augmentation methods are only proven effective in untargeted attacks. In this work, we p…
Enhancing Noise Robustness of Parkinson's Disease Telemonitoring via Contrastive Feature Augmentation
Ministry of Education Key Laboratory of Bioinformatics, Department of Automation（教育部生物信息学重点实验室、自动化系）；Tsinghua University（清华大学）；School of Computing and Artificial Intelligence（计算与人工智能学院）；Fuyao University of Science and Technology（福耀科技大学）；National Engineering Laboratory for Big Data System Computing Technology（大数据系统计算技术国家工程实验室）；Shenzhen University（深圳大学）；School of Computer Science and Engineering（计算机科学与工程学院）
According to the World Health Organization, distracted driving is one of the leading cause of motor accidents and deaths in the world. In our study, we tackle the problem of distracted driving by aiming to build a robust multi-class classifier to detect and identify different forms of driver inattention using the State Farm Distracted Driving Dataset. We utilize combinations of pretrained image classification models, classical data augmentation, OpenCV based image preprocessing and skin segmentation augmentation approaches. Our best performing model combines several augmentation techniques, in…
Data Augmentation in Graph Neural Networks: The Role of Generated Synthetic Graphs
Istanbul Technical University（伊斯坦布尔理工大学）；ITU, AI Research and Application Center（伊斯坦布尔理工大学AI研究与应用中心）；ITU, Department of Computer Engineering（伊斯坦布尔理工大学计算机工程系）；BTS Group（BTS集团）；Gazi University（加齐大学）
Arizona State University（亚利桑那州立大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Graph neural networks, a powerful deep learning tool to model graph-structured data, have demonstrated remarkable performance on numerous graph learning tasks. To address the data noise and data scarcity issues in deep graph learning, the research on graph data augmentation has intensified lately. However, conventional data augmentation methods can hardly handle graph-structured data which is defined in non-Euclidean space with multi-modality. In this survey, we formally formulate the problem of graph data augmentation and further review the representative techniques and their applications in …
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Tencent（腾讯）
Recently, Graph Neural Networks (GNNs) achieve remarkable success in Recommendation. To reduce the influence of data sparsity, Graph Contrastive Learning (GCL) is adopted in GNN-based CF methods for enhancing performance. Most GCL methods consist of data augmentation and contrastive loss (e.g., InfoNCE). GCL methods construct the contrastive pairs by hand-crafted graph augmentations and maximize the agreement between different views of the same node compared to that of other nodes, which is known as the InfoMax principle. However, improper data augmentation will hinder the performance of GCL. …
Enhancing Generalization in Evolutionary Feature Construction for Symbolic Regression through Vicinal Jensen Gap Minimization
Centre for Data Science and Artificial Intelligence & School of Engineering and Computer Science, Victoria University of Wellington（数据科学与人工智能中心及工程与计算机科学学院，维多利亚大学）
