Light-Head R-CNN: In Defense of Two-Stage Object Detector
This work addresses the speed-accuracy trade-off in object detection for computer vision applications, offering a significant improvement over existing methods.
The paper tackles the speed inefficiency of two-stage object detectors by proposing Light-Head R-CNN, which uses a thin feature map and a cheap R-CNN subnet to reduce computation, achieving 30.7 mmAP at 102 FPS on COCO with a tiny backbone, outperforming fast single-stage detectors like YOLO and SSD in both speed and accuracy.
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.