One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This paper alleviates this issue by proposing a novel framework to replace the classification task in one-stage detectors with a ranking task, and adopting the average-precision loss (AP-loss) for the ranking problem. Due to its non-differentiability and non-convexity, the AP-loss cannot be optimized directly. For this purpose, we develop a novel optimization algorithm, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks. We provide in-depth analyses on the good convergence property and computational complexity of the proposed algorithm, both theoretically and empirically. Experimental results demonstrate notable improvement in addressing the imbalance issue in object detection over existing AP-based optimization algorithms. An improved state-of-the-art performance is achieved in one-stage detectors based on AP-loss over detectors using classification-losses on various standard benchmarks. The proposed framework is also highly versatile in accommodating different network architectures. Code is available at https://github.com/cccorn/AP-loss.

中文翻译：

---

用于准确的一级物体检测的 AP 损失


一阶段目标检测器是通过同时优化分类损失和定位损失来训练的，前者由于大量的锚点而遭受极端的前景-背景类不平衡问题。本文通过提出一种新颖的框架来缓解这个问题，用排序任务代替单级检测器中的分类任务，并采用平均精度损失（AP-loss）来解决排序问题。由于其不可微性和非凸性，AP-loss 不能直接优化。为此，我们开发了一种新颖的优化算法，它将感知器学习中的误差驱动更新方案和深度网络中的反向传播算法无缝地结合起来。我们从理论上和实证上对所提出算法的良好收敛性和计算复杂性进行了深入分析。实验结果表明，与现有的基于 AP 的优化算法相比，该算法在解决目标检测不平衡问题方面有显着改进。基于 AP 损失的单级检测器比在各种标准基准上使用分类损失的检测器实现了改进的最先进性能。所提出的框架在适应不同的网络架构方面也具有高度的通用性。代码可在 https://github.com/cccorn/AP-loss 获取。