Focal Loss for Dense Object Detection
Focal Loss for Dense Object Detection
复制标题
DOI：
10.1109/tpami.2018.2858826
复制
发表时间：
2020-02-01
影响因子：
23.6
通讯作者：
Dollar, Piotr
中科院分区：
文献类型：
--
作者：
Lin, Tsung-Yi;Goyal, Priya;Dollar, Piotr
迄今为止，最高精度的对象检测器是基于R-CNN推广的两阶段方法，其中分类器应用于候选对象位置的稀疏集合。相比之下，应用于可能的对象位置的规则的、密集的采样的一级检测器具有更快和更简单的潜力，但是到目前为止已经落后于两级检测器的准确性。在本文中，我们将探讨为什么会出现这种情况。我们发现，在密集检测器的训练过程中遇到的极端前景-背景类不平衡是核心原因。我们建议通过重塑标准交叉熵损失来解决这种类别不平衡，使其降低分配给分类良好的示例的损失。我们的新Focal Loss将训练集中在一组稀疏的硬样本上，并防止大量的简单否定在训练过程中压倒检测器。为了评估损失的有效性，我们设计并训练了一个简单的密集检测器，我们称之为RetinaNet。我们的研究结果表明，当使用焦点损失进行训练时，RetinaNet能够匹配以前的一级检测器的速度，同时超过所有现有的最先进的两级检测器的准确性。代码在：https://github.com/facebookresearch/Detectron。
The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a regular, dense sampling of possible object locations have the potential to be faster and simpler, but have trailed the accuracy of two-stage detectors thus far. In this paper, we investigate why this is the case. We discover that the extreme foreground-background class imbalance encountered during training of dense detectors is the central cause. We propose to address this class imbalance by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples. Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training. To evaluate the effectiveness of our loss, we design and train a simple dense detector we call RetinaNet. Our results show that when trained with the focal loss, RetinaNet is able to match the speed of previous one-stage detectors while surpassing the accuracy of all existing state-of-the-art two-stage detectors. Code is at: https://github.com/facebookresearch/Detectron.