论文标题
深层探测器中的前景背景不平衡问题：评论
Foreground-Background Imbalance Problem in Deep Object Detectors: A Review
论文作者
论文摘要
近年来，深度学习技术用于对象检测的显着发展，这是计算机视觉的根本性挑战性问题。然而，在训练准确的深对象探测器方面仍然存在困难，其中之一是由于前后背景不平衡问题。在本文中，我们调查了有关不平衡问题解决方案的最新进展。首先，我们在不同种类的深探测器（包括一个阶段和两个阶段）中分析了不平衡问题的特征。其次，我们将现有解决方案分为两类：采样启发式方法和非采样方案，并详细审查它们。第三，我们通过实验比较可可基准上某些最先进的解决方案的性能。还讨论了未来工作的有希望的指示。
Recent years have witnessed the remarkable developments made by deep learning techniques for object detection, a fundamentally challenging problem of computer vision. Nevertheless, there are still difficulties in training accurate deep object detectors, one of which is owing to the foreground-background imbalance problem. In this paper, we survey the recent advances about the solutions to the imbalance problem. First, we analyze the characteristics of the imbalance problem in different kinds of deep detectors, including one-stage and two-stage ones. Second, we divide the existing solutions into two categories: sampling heuristics and non-sampling schemes, and review them in detail. Third, we experimentally compare the performance of some state-of-the-art solutions on the COCO benchmark. Promising directions for future work are also discussed.
