论文标题
Aruba：空中对象检测的建筑 - 不足的平衡损失
ARUBA: An Architecture-Agnostic Balanced Loss for Aerial Object Detection
论文作者
论文摘要
深层神经网络倾向于回报其培训数据集的偏见。在对象检测中，偏见以各种不平衡的形式（例如类，背景前景和对象大小）存在。在本文中，我们将对象的大小表示为图像和大小不平衡的像素数量，因为数据集中某些尺寸的对象的代表过多。我们旨在解决基于无人机的空中图像数据集中的大小不平衡问题。解决尺寸不平衡的现有方法基于架构变化，该变化利用了多个图像或特征图来检测不同尺寸的对象。另一方面，我们提出了一种新颖的体系结构敏锐的平衡损失（Aruba），可以在任何对象检测模型的顶部用作插件。它遵循以对象大小的条例启发的邻里驱动方法。我们通过在HRSC2016，Dotav1.0，Dotav1.5和Visdrone等空中数据集上进行全面实验来评估方法的有效性，并获得性能的一致改善。
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.
