Data Augmentation
Data augmentation is a technique used to artificially expand datasets by creating modified versions of existing data, primarily to improve the performance and robustness of machine learning models, especially when training data is scarce. Current research focuses on developing more sophisticated augmentation methods, including those leveraging generative models like GANs and diffusion models, and integrating augmentation with other techniques such as contrastive learning and transfer learning, often applied within architectures like transformers and convolutional neural networks. This work is significant because it addresses the limitations of limited datasets across various domains, from image classification and object detection to natural language processing and time series forecasting, leading to more accurate and generalizable models for diverse applications.
Papers
Posterior Uncertainty Quantification in Neural Networks using Data Augmentation
Luhuan Wu, Sinead Williamson
SETA: Semantic-Aware Token Augmentation for Domain Generalization
Jintao Guo, Lei Qi, Yinghuan Shi, Yang Gao
Automated data processing and feature engineering for deep learning and big data applications: a survey
Alhassan Mumuni, Fuseini Mumuni
Analyzing Data Augmentation for Medical Images: A Case Study in Ultrasound Images
Adam Tupper, Christian Gagné
Don't Judge by the Look: Towards Motion Coherent Video Representation
Yitian Zhang, Yue Bai, Huan Wang, Yizhou Wang, Yun Fu
EventRPG: Event Data Augmentation with Relevance Propagation Guidance
Mingyuan Sun, Donghao Zhang, Zongyuan Ge, Jiaxu Wang, Jia Li, Zheng Fang, Renjing Xu
Leveraging Foundation Model Automatic Data Augmentation Strategies and Skeletal Points for Hands Action Recognition in Industrial Assembly Lines
Liang Wu, X. -G. Ma