论文标题
面对空白：克服多视图图像中缺少数据
Facing the Void: Overcoming Missing Data in Multi-View Imagery
论文作者
论文摘要
在某些情况下，单个输入图像可能不足以允许对象分类。在这种情况下，至关重要的是探索从从多个角度（或视图）展示相同对象的图像中提取的互补信息，以增强一般场景的理解，从而提高性能。但是，此任务通常称为多视图图像分类，面临着一个重大挑战：丢失数据。在本文中，我们提出了一种针对此问题的多视图图像分类的新技术。基于最先进的基于深度学习的方法和度量学习的建议方法可以轻松地在其他应用程序和域中进行调整和利用。使用具有非常不同属性的两个多视空地数据集对所提出的算法进行系统评估。结果表明，与最先进的方法相比，所提出的算法可改善多视图图像分类精度。可在\ url {https://github.com/gabriellm2003/remote_sensing_missing_data}获得代码。
In some scenarios, a single input image may not be enough to allow the object classification. In those cases, it is crucial to explore the complementary information extracted from images presenting the same object from multiple perspectives (or views) in order to enhance the general scene understanding and, consequently, increase the performance. However, this task, commonly called multi-view image classification, has a major challenge: missing data. In this paper, we propose a novel technique for multi-view image classification robust to this problem. The proposed method, based on state-of-the-art deep learning-based approaches and metric learning, can be easily adapted and exploited in other applications and domains. A systematic evaluation of the proposed algorithm was conducted using two multi-view aerial-ground datasets with very distinct properties. Results show that the proposed algorithm provides improvements in multi-view image classification accuracy when compared to state-of-the-art methods. Code available at \url{https://github.com/Gabriellm2003/remote_sensing_missing_data}.
