论文标题
匹配空间立体网络用于跨域泛化
Matching-space Stereo Networks for Cross-domain Generalization
论文作者
论文摘要
端到端的深网代表立体声匹配的艺术状态。尽管在与训练集类似的图像框架环境中脱颖而出，但准确性的主要下降在看不见的域中（例如，从合成到真实场景中移动时）。在本文中，我们介绍了一个新型的体系结构家族，即匹配的空间网络（MS-NETS），具有改进的概括属性。通过用匹配的功能和传统智慧的置信度替换基于学习的特征提取，我们将学习过程从颜色空间移动到匹配空间，避免过度专业化到域特定特征。在四个真实数据集上的广泛实验结果凸显了我们的提案会导致较高的概括，从而使环境比传统的深度架构相比，从而使源域上的准确性几乎没有改变。我们的代码可从https://github.com/ccj5351/ms-nets获得。
End-to-end deep networks represent the state of the art for stereo matching. While excelling on images framing environments similar to the training set, major drops in accuracy occur in unseen domains (e.g., when moving from synthetic to real scenes). In this paper we introduce a novel family of architectures, namely Matching-Space Networks (MS-Nets), with improved generalization properties. By replacing learning-based feature extraction from image RGB values with matching functions and confidence measures from conventional wisdom, we move the learning process from the color space to the Matching Space, avoiding over-specialization to domain specific features. Extensive experimental results on four real datasets highlight that our proposal leads to superior generalization to unseen environments over conventional deep architectures, keeping accuracy on the source domain almost unaltered. Our code is available at https://github.com/ccj5351/MS-Nets.
