图 书 馆
视频标注的大规模训练框架Large-Scale Training Framework for Video Annotation |
|
| 课程网址: | http://videolectures.net/kdd2019_hwang_lee_varadarajan/ |
| 主讲教师: | Seong Jae Hwang |
| 开课单位: | 威斯康辛大学麦迪逊分校 |
| 开课时间: | 2020-03-02 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Video is one of the richest sources of information available online but extracting deep insights from video content at internet scale is still an open problem, both in terms of depth and breadth of understanding, as well as scale. Over the last few years, the field of video understanding has made great strides due to the availability of large-scale video datasets and core advances in image, audio, and video modeling architectures. However, the state-of-the-art architectures on small scale datasets are frequently impractical to deploy at internet scale, both in terms of the ability to train such deep networks on hundreds of millions of videos, and to deploy them for inference on billions of videos. In this paper, we present a MapReduce-based training framework, which exploits both data parallelism and model parallelism to scale training of complex video models. The proposed framework uses alternating optimization and full-batch fine-tuning, and supports large Mixture-of-Experts classifiers with hundreds of thousands of mixtures, which enables a trade-off between model depth and breadth, and the ability to shift model capacity between shared (generalization) layers and per-class (specialization) layers. We demonstrate that the proposed framework is able to reach state-of-the-art performance on the largest public video datasets, YouTube-8M and Sports-1M, and can scale to 100 times larger datasets. |
| 关 键 词: | 视频标注; 大规模训练框架; 数据科学 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2022-09-19：cyh |
| 最后编审: | 2022-09-19：cyh |
| 阅读次数: | 25 |