Skip to yearly menu bar Skip to main content


Poster

R-FCN: Object Detection via Region-based Fully Convolutional Networks

jifeng dai · Yi Li · Kaiming He · Jian Sun

Area 5+6+7+8 #200

Keywords: [ Deep Learning or Neural Networks ] [ (Application) Computer Vision ] [ (Application) Object and Pattern Recognition ]


Abstract:

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, 2.5-20 times faster than the Faster R-CNN counterpart. Code is made publicly available at: https://github.com/daijifeng001/r-fcn.

Live content is unavailable. Log in and register to view live content