面向学习驱动科学可视化的数据增强研究。

Jun Han, Hao Zheng, Jun Tao
{"title":"面向学习驱动科学可视化的数据增强研究。","authors":"Jun Han, Hao Zheng, Jun Tao","doi":"10.1109/TVCG.2025.3587685","DOIUrl":null,"url":null,"abstract":"<p><p>The success of deep learning heavily relies on the large amount of training samples. However, in scientific visualization, due to the high computational cost, only few data are available during training, which limits the performance of deep learning. A common technique to address the data sparsity issue is data augmentation. In this paper, we present a comprehensive study on nine data augmentation techniques (i.e., noise injection, interpolation, scale, flip, rotation, variational auto-encoder, generative adversarial network, diffusion model, and implicit neural representation) for understanding their effectiveness on two scientific visualization tasks, i.e., spatial super-resolution and ambient occlusion prediction. We compare the data quality, rendering fidelity, optimization time, and memory consumption of these data augmentation techniques using several scientific datasets with various characteristics. We investigate the effects of data augmentation on the method, quantity, and diversity for these tasks with various deep learning models. Our study shows that increasing the quantity and single-domain diversity of augmented data can boost model performance, while the method and cross-domain diversity of the augmented data do not have the same impact. Based on our findings, we discuss the opportunities and future directions for scientific data augmentation.</p>","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Study of Data Augmentation for Learning-Driven Scientific Visualization.\",\"authors\":\"Jun Han, Hao Zheng, Jun Tao\",\"doi\":\"10.1109/TVCG.2025.3587685\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>The success of deep learning heavily relies on the large amount of training samples. However, in scientific visualization, due to the high computational cost, only few data are available during training, which limits the performance of deep learning. A common technique to address the data sparsity issue is data augmentation. In this paper, we present a comprehensive study on nine data augmentation techniques (i.e., noise injection, interpolation, scale, flip, rotation, variational auto-encoder, generative adversarial network, diffusion model, and implicit neural representation) for understanding their effectiveness on two scientific visualization tasks, i.e., spatial super-resolution and ambient occlusion prediction. We compare the data quality, rendering fidelity, optimization time, and memory consumption of these data augmentation techniques using several scientific datasets with various characteristics. We investigate the effects of data augmentation on the method, quantity, and diversity for these tasks with various deep learning models. Our study shows that increasing the quantity and single-domain diversity of augmented data can boost model performance, while the method and cross-domain diversity of the augmented data do not have the same impact. Based on our findings, we discuss the opportunities and future directions for scientific data augmentation.</p>\",\"PeriodicalId\":94035,\"journal\":{\"name\":\"IEEE transactions on visualization and computer graphics\",\"volume\":\"PP \",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2025-07-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE transactions on visualization and computer graphics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/TVCG.2025.3587685\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on visualization and computer graphics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TVCG.2025.3587685","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

深度学习的成功很大程度上依赖于大量的训练样本。然而,在科学可视化中,由于计算成本高,训练过程中可用的数据很少,这限制了深度学习的性能。解决数据稀疏性问题的一种常用技术是数据扩充。在本文中,我们全面研究了九种数据增强技术(即噪声注入,插值,缩放,翻转,旋转,变分自编码器,生成对抗网络,扩散模型和隐式神经表示),以了解它们在两个科学可视化任务(即空间超分辨率和环境遮挡预测)中的有效性。我们使用几个具有不同特征的科学数据集来比较这些数据增强技术的数据质量、渲染保真度、优化时间和内存消耗。我们用各种深度学习模型研究了数据增强对这些任务的方法、数量和多样性的影响。我们的研究表明,增加增广数据的数量和单域多样性可以提高模型的性能,而增加增广数据的方法和跨域多样性则没有相同的影响。基于我们的发现,我们讨论了科学数据增强的机会和未来方向。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A Study of Data Augmentation for Learning-Driven Scientific Visualization.

The success of deep learning heavily relies on the large amount of training samples. However, in scientific visualization, due to the high computational cost, only few data are available during training, which limits the performance of deep learning. A common technique to address the data sparsity issue is data augmentation. In this paper, we present a comprehensive study on nine data augmentation techniques (i.e., noise injection, interpolation, scale, flip, rotation, variational auto-encoder, generative adversarial network, diffusion model, and implicit neural representation) for understanding their effectiveness on two scientific visualization tasks, i.e., spatial super-resolution and ambient occlusion prediction. We compare the data quality, rendering fidelity, optimization time, and memory consumption of these data augmentation techniques using several scientific datasets with various characteristics. We investigate the effects of data augmentation on the method, quantity, and diversity for these tasks with various deep learning models. Our study shows that increasing the quantity and single-domain diversity of augmented data can boost model performance, while the method and cross-domain diversity of the augmented data do not have the same impact. Based on our findings, we discuss the opportunities and future directions for scientific data augmentation.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信