当前位置: X-MOL 学术ISPRS J. Photogramm. Remote Sens. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Variational Autoencoder with Gaussian Random Field prior: Application to unsupervised animal detection in aerial images
ISPRS Journal of Photogrammetry and Remote Sensing ( IF 10.6 ) Pub Date : 2024-10-03 , DOI: 10.1016/j.isprsjprs.2024.09.028
Hugo Gangloff, Minh-Tan Pham, Luc Courtrai, Sébastien Lefèvre

In real world datasets of aerial images, the objects of interest are often missing, hard to annotate and of varying aspects. The framework of unsupervised Anomaly Detection (AD) is highly relevant in this context, and Variational Autoencoders (VAEs), a family of popular probabilistic models, are often used. We develop on the literature of VAEs for AD in order to take advantage of the particular textures that appear in natural aerial images. More precisely we propose a new VAE model with a Gaussian Random Field (GRF) prior (VAE-GRF), which generalizes the classical VAE model, and we provide the necessary procedures and hypotheses required for the model to be tractable. We show that, under some assumptions, the VAE-GRF largely outperforms the traditional VAE and some other probabilistic models developed for AD. Our results suggest that the VAE-GRF could be used as a relevant VAE baseline in place of the traditional VAE with very limited additional computational cost. We provide competitive results on the MVTec reference dataset for visual inspection, and two other datasets dedicated to the task of unsupervised animal detection in aerial images.

中文翻译:


具有高斯随机场先验的变分自动编码器:在航空图像中无监督动物检测中的应用



在航空图像的真实数据集中,感兴趣的对象经常缺失、难以注释且方面各不相同。在这种情况下,无监督异常检测 (AD) 的框架高度相关,并且经常使用变分自动编码器 (VAE),这是一系列流行的概率模型。我们以 AD 的 VAE 文献为基础进行开发,以利用自然航拍图像中出现的特定纹理。更准确地说,我们提出了一种具有高斯随机场 (GRF) 先验 (VAE-GRF) 的新 VAE 模型,它概括了经典的 VAE 模型,并提供了该模型易于处理所需的必要程序和假设。我们表明,在某些假设下,VAE-GRF 在很大程度上优于传统的 VAE 和为 AD 开发的其他一些概率模型。我们的结果表明,VAE-GRF 可以用作相关的 VAE 基线,以代替传统的 VAE,而额外的计算成本非常有限。我们在用于目视检查的 MVTec 参考数据集和另外两个专门用于航空图像中无监督动物检测任务的数据集上提供了有竞争力的结果。
更新日期:2024-10-03
down
wechat
bug