论文标题
集成的多尺度域自适应Yolo
Integrated Multiscale Domain Adaptive YOLO
论文作者
论文摘要
域的适应区域对解决许多应用程序遇到的域移位问题发挥了重要作用。由于与现实测试方案中使用的目标数据相比，用于培训的源数据的分布之间的差异是由于训练源数据的分布之间的差异。在本文中，我们引入了一种新型的多尺度域自适应Yolo（MS-Dayolo）框架，该框架在最近引入的Yolov4对象检测器的不同尺度上采用了多个域自适应路径和相应的域分类器。在我们的基线多尺度Dayolo框架的基础上，我们为域名适应网络（DAN）引入了三个新颖的深度学习体系结构，它们生成了域，不变性功能。特别是，我们提出了一个渐进式功能减少（PFR），统一分类器（UC）和集成体系结构。我们使用流行的数据集训练和测试与Yolov4结合的DAN架构。当使用拟议的MS-Dayolo架构训练Yolov4时，我们的实验显示了对象检测性能的显着改善，并且在对目标数据进行自动驾驶应用程序进行测试时。此外，MS-Dayolo框架相对于更快的R-CNN解决方案实现了实时速度的数量级，同时提供了可比的对象检测性能。
The area of domain adaptation has been instrumental in addressing the domain shift problem encountered by many applications. This problem arises due to the difference between the distributions of source data used for training in comparison with target data used during realistic testing scenarios. In this paper, we introduce a novel MultiScale Domain Adaptive YOLO (MS-DAYOLO) framework that employs multiple domain adaptation paths and corresponding domain classifiers at different scales of the recently introduced YOLOv4 object detector. Building on our baseline multiscale DAYOLO framework, we introduce three novel deep learning architectures for a Domain Adaptation Network (DAN) that generates domain-invariant features. In particular, we propose a Progressive Feature Reduction (PFR), a Unified Classifier (UC), and an Integrated architecture. We train and test our proposed DAN architectures in conjunction with YOLOv4 using popular datasets. Our experiments show significant improvements in object detection performance when training YOLOv4 using the proposed MS-DAYOLO architectures and when tested on target data for autonomous driving applications. Moreover, MS-DAYOLO framework achieves an order of magnitude real-time speed improvement relative to Faster R-CNN solutions while providing comparable object detection performance.
