# Light-Head R-CNN: In Defense of Two-Stage Object Detector Source: [Light-Head R-CNN: In Defense of Two-Stage Object Detector]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:50:10.530Z Authors: Zeming Li, Chao Peng, Gang Yu, Xiangyu Zhang, Yangdong Deng, Jian Sun Published: 2017-11-20T11:50:19.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Object Detection on PASCAL VOC 2012 (test)](): Object Detection; PASCAL VOC 2012 (test); mAP: 80.8. - [Object Detection on DOTA](): Object Detection; DOTA; mAP: 66.95. - [Object Detection on COCO (test-dev)](): Object Detection; COCO (test-dev); mAP: 41.5. - [Object Detection on MS COCO (test-dev)](): Object Detection; MS COCO (test-dev); mAP@.5: not recorded. ## Original sources and implementation [Original paper]() [PDF]()