Log In Sign Up

Light-Head R-CNN: In Defense of Two-Stage Object Detector

by   Zeming Li, et al.

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.


FQDet: Fast-converging Query-based Detector

Recently, two-stage Deformable DETR introduced the query-based two-stage...

Rethinking Classification and Localization in R-CNN

Modern R-CNN based detectors share the RoI feature extractor head for bo...

Probabilistic two-stage detection

We develop a probabilistic interpretation of two-stage object detection....

CBNet: A Novel Composite Backbone Network Architecture for Object Detection

In existing CNN based detectors, the backbone network is a very importan...

3DSSD: Point-based 3D Single Stage Object Detector

Currently, there have been many kinds of voxel-based 3D single stage det...

SSH: Single Stage Headless Face Detector

We introduce the Single Stage Headless (SSH) face detector. Unlike two s...

BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision

We present a novel bird's-eye-view (BEV) detector with perspective super...