论文标题
无监督的域从合成到真实图像的适应无锚定对象检测
Unsupervised Domain Adaptation from Synthetic to Real Images for Anchorless Object Detection
论文作者
论文摘要
合成图像是避免与生成带注释的数据集相关的高成本的最有前途的解决方案之一，以培训监督的卷积神经网络（CNN）。但是，为了允许网络从合成图像概括知识，必须采用域适应方法。本文在无锚对象检测器上实现了无监督的域适应性（UDA）方法。鉴于其良好的性能，无锚探测器越来越吸引对象检测领域的注意力。尽管它们的结果与建立的基于锚固的方法相当，但无锚探测器的速度要快得多。在我们的工作中，我们将Centernet（最新的无锚体体系结构之一）用于涉及合成图像的域适应问题。利用无锚检测器的结构，我们建议调整两种UDA方法，即熵最小化和最大正方形损失，最初是用于分割的，以进行对象检测。我们的结果表明，提出的UDA方法可以将MAPFROM61％提高到69％，以直接转移对所考虑的无锚定检测器的直接转移。代码可用：https：//github.com/scheckmedia/centernet-uda。
Synthetic images are one of the most promising solutions to avoid high costs associated with generating annotated datasets to train supervised convolutional neural networks (CNN). However, to allow networks to generalize knowledge from synthetic to real images, domain adaptation methods are necessary. This paper implements unsupervised domain adaptation (UDA) methods on an anchorless object detector. Given their good performance, anchorless detectors are increasingly attracting attention in the field of object detection. While their results are comparable to the well-established anchor-based methods, anchorless detectors are considerably faster. In our work, we use CenterNet, one of the most recent anchorless architectures, for a domain adaptation problem involving synthetic images. Taking advantage of the architecture of anchorless detectors, we propose to adjust two UDA methods, viz., entropy minimization and maximum squares loss, originally developed for segmentation, to object detection. Our results show that the proposed UDA methods can increase the mAPfrom61 %to69 %with respect to direct transfer on the considered anchorless detector. The code is available: https://github.com/scheckmedia/centernet-uda.
