ARUBA：一种用于航空目标检测的架构无关平衡损失
ARUBA: An Architecture-Agnostic Balanced Loss for Aerial Object Detection
AI总结：
本文提出一种名为ARUBA的架构无关平衡损失，作为插件解决无人机航空图像数据集中目标尺寸不平衡问题，在多个航空数据集上取得持续性能提升。
摘要：
深度神经网络倾向于复制其训练数据集的偏差。在目标检测中，这种偏差以各种不平衡的形式存在，例如类别、背景-前景和目标尺寸。在本文中，我们将目标的尺寸定义为其在图像中覆盖的像素数，并将尺寸不平衡定义为数据集中某些尺寸目标的过度表征。我们旨在解决基于无人机的航空图像数据集中的尺寸不平衡问题。解决尺寸不平衡的现有方法基于架构更改，利用多尺度图像或特征图来检测不同尺寸的目标。另一方面，我们提出了一种新颖的架构无关平衡损失（ARUBA），它可以作为插件应用于任何目标检测模型之上。它遵循受目标尺寸有序性启发的邻域驱动方法。我们通过在HRSC2016、DOTAv1.0、DOTAv1.5和VisDrone等航空数据集上的全面实验评估了该方法的有效性，并获得了持续的性能提升。
英文摘要：
Deep neural networks tend to reciprocate the bias of their training dataset. In object detection, the bias exists in the form of various imbalances such as class, background-foreground, and object size. In this paper, we denote size of an object as the number of pixels it covers in an image and size imbalance as the over-representation of certain sizes of objects in a dataset. We aim to address the problem of size imbalance in drone-based aerial image datasets. Existing methods for solving size imbalance are based on architectural changes that utilize multiple scales of images or feature maps for detecting objects of different sizes. We, on the other hand, propose a novel ARchitectUre-agnostic BAlanced Loss (ARUBA) that can be applied as a plugin on top of any object detection model. It follows a neighborhood-driven approach inspired by the ordinality of object size. We evaluate the effectiveness of our approach through comprehensive experiments on aerial datasets such as HRSC2016, DOTAv1.0, DOTAv1.5 and VisDrone and obtain consistent improvement in performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
