In this paper, we first investigate why typical two-stage methods are not as
fast as single-stage, fast detectors like YOLO and SSD. We find that Faster
R-CNN and R-FCN perform an intensive computation after or before RoI warping.
Faster R-CNN involves two fully connected layers for RoI recognition, while
R-FCN produces a large score maps. Thus, the speed of these networks is slow
due to the heavy-head design in the architecture. Even if we significantly
reduce the base model, the computation cost cannot be largely decreased
accordingly.
We propose a new two-stage detector, Light-Head R-CNN, to address the
shortcoming in current two-stage approaches. In our design, we make the head of
network as light as possible, by using a thin feature map and a cheap R-CNN
subnet (pooling and single fully-connected layer). Our ResNet-101 based
light-head R-CNN outperforms state-of-art object detectors on COCO while
keeping time efficiency. More importantly, simply replacing the backbone with a
tiny network (e.g, Xception), our Light-Head R-CNN gets 30.7 mmAP at 102 FPS on
COCO, significantly outperforming the single-stage, fast detectors like YOLO
and SSD on both speed and accuracy. Code will be made publicly available.

提出了一种新的基于 ResNet-101 的双阶段目标检测器 Light-Head R-CNN，通过使用一个轻量级的特征图和一个便宜的 R-CNN 子网络来实现网络头部的最小化，而且在 COCO 上表现良好，在保持时间效率的同时也比单阶段的快速检测器像 YOLO 和 SSD 更准确。