Modern object detection methods can be divided into one-stage approaches and two-stage ones. One-stage detectors are more efficient owing to straightforward architectures, but the two-stage detectors still take the lead in accuracy. Although recent work try to improve the one-stage detectors by imitating the structural design of the two-stage ones, the accuracy gap is still significant. In this paper, we propose MimicDet, a novel and efficient framework to train a one-stage detector by directly mimic the two-stage features, aiming to bridge the accuracy gap between one-stage and two-stage detectors. Unlike conventional mimic methods, MimicDet has a shared backbone for one-stage and two-stage detectors, then it branches into two heads which are well designed to have compatible features for mimicking. Thus MimicDet can be end-to-end trained without the pre-train of the teacher network. And the cost does not increase much, which makes it practical to adopt large networks as backbones. We also make several specialized designs such as dual-path mimicking and staggered feature pyramid to facilitate the mimicking process. Experiments on the challenging COCO detection benchmark demonstrate the effectiveness of MimicDet. It achieves 46.1 mAP with ResNeXt-101 backbone on the COCO test-dev set, which significantly surpasses current state-of-the-art methods.

中文翻译：

---

MimicDet：弥合一级和二级目标检测之间的差距

现代目标检测方法可以分为一阶段方法和两阶段方法。由于结构简单，一级检测器效率更高，但二级检测器在准确性方面仍处于领先地位。尽管最近的工作试图通过模仿两级探测器的结构设计来改进一级探测器，但精度差距仍然很大。在本文中，我们提出了 MimicDet，这是一种新颖有效的框架，通过直接模仿两级特征来训练单级检测器，旨在弥合一级和两级检测器之间的精度差距。与传统的模仿方法不同，MimicDet 具有用于一级和二级探测器的共享主干，然后它分为两个头部，这些头部经过精心设计，具有用于模仿的兼容特征。因此 MimicDet 可以在没有教师网络预训练的情况下进行端到端训练。并且成本不会增加太多，这使得采用大型网络作为骨干网是可行的。我们还进行了一些专门的设计，例如双路径模仿和交错特征金字塔，以促进模仿过程。在具有挑战性的 COCO 检测基准上的实验证明了 MimicDet 的有效性。它在 COCO 测试开发集上使用 ResNeXt-101 主干实现了 46.1 mAP，显着超过了当前最先进的方法。在具有挑战性的 COCO 检测基准上的实验证明了 MimicDet 的有效性。它在 COCO 测试开发集上使用 ResNeXt-101 主干实现了 46.1 mAP，显着超过了当前最先进的方法。在具有挑战性的 COCO 检测基准上的实验证明了 MimicDet 的有效性。它在 COCO 测试开发集上使用 ResNeXt-101 主干实现了 46.1 mAP，显着超过了当前最先进的方法。