R-FCN: Object Detection via Region-based Fully Convolutional Networks
This work addresses the need for faster and more accurate object detection in computer vision, with incremental improvements over existing methods.
The paper tackled the problem of inefficient object detection in region-based detectors by proposing R-FCN, a fully convolutional network that shares computation across the entire image, achieving 83.6% mAP on PASCAL VOC 2007 and a test-time speed of 170ms per image, which is 2.5-20x faster than Faster R-CNN.
We present region-based, fully convolutional networks for accurate and efficient object detection. In contrast to previous region-based detectors such as Fast/Faster R-CNN that apply a costly per-region subnetwork hundreds of times, our region-based detector is fully convolutional with almost all computation shared on the entire image. To achieve this goal, we propose position-sensitive score maps to address a dilemma between translation-invariance in image classification and translation-variance in object detection. Our method can thus naturally adopt fully convolutional image classifier backbones, such as the latest Residual Networks (ResNets), for object detection. We show competitive results on the PASCAL VOC datasets (e.g., 83.6% mAP on the 2007 set) with the 101-layer ResNet. Meanwhile, our result is achieved at a test-time speed of 170ms per image, 2.5-20x faster than the Faster R-CNN counterpart. Code is made publicly available at: https://github.com/daijifeng001/r-fcn