快速R-CNNFast R-CNN |
|
课程网址: | http://videolectures.net/iccv2015_girshick_fast_r_cnn/ |
主讲教师: | Ross B. Girshick |
开课单位: | 脸书公司 |
开课时间: | 2016-04-10 |
课程语种: | 英语 |
中文简介: | 本文提出了一种基于快速区域的卷积网络方法(Fast R CNN)用于对象检测。 Fast R CNN 建立在先前工作的基础上,使用深度卷积网络对对象提议进行有效分类。与之前的工作相比,Fast R CNN 采用了多项创新来提高训练和测试速度,同时提高检测精度。 Fast R CNN 训练非常深的 VGG16 网络比 R CNN 快 9 倍,在测试时快 213 倍,并且在 PASCAL VOC2012 上实现了更高的 mAP。与 SPPnet 相比,Fast R CNN 训练 VGG16 快 3 倍,测试快 10 倍,并且更准确。 Fast R CNN 是用 Python 和 C(使用 Caffe)实现的,在开源 MIT 许可证下可用,位于 |
课程简介: | This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection. Fast R-CNN builds on previous work to efficiently classify object proposals using deep convolutional networks. Compared to previous work, Fast R-CNN employs several innovations to improve training and testing speed while also increasing detection accuracy. Fast R-CNN trains the very deep VGG16 network 9×faster than R-CNN, is 213×faster at test-time, and achieves a higher mAP on PASCAL VOC2012. Compared to SPPnet, Fast R-CNN trains VGG16 3×faster, tests 10×faster, and is more accurate. Fast R-CNN is implemented in Python and C++ (using Caffe) and is available under the open-source MIT License at |
关 键 词: | Fast R CNN; 深度卷积网络; 检测精度 |
课程来源: | 视频讲座网 |
数据采集: | 2021-07-05:liyy |
最后编审: | 2021-07-05:liyy |
阅读次数: | 41 |