计算机科学
帕斯卡(单位)
子网
人工智能
目标检测
模式识别(心理学)
残余物
分类器(UML)
探测器
计算
翻译(生物学)
卷积神经网络
算法
基因
程序设计语言
化学
信使核糖核酸
电信
生物化学
计算机安全
作者
Jifeng Dai,Yang Li,Kai He,Jian Sun
出处
期刊:Cornell University - arXiv
日期:2016-01-01
被引量:2060
标识
DOI:10.48550/arxiv.1605.06409
摘要
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
科研通智能强力驱动
Strongly Powered by AbleSci AI