计算机科学
水准点(测量)
推论
计算
失败
人工智能
过程(计算)
在飞行中
光学(聚焦)
钥匙(锁)
机器学习
模式识别(心理学)
算法
并行计算
物理
光学
操作系统
地理
计算机安全
大地测量学
作者
Amir Ghodrati,Babak Ehteshami Bejnordi,Amirhossein Habibian
出处
期刊:Proceedings
[Institute of Electrical and Electronics Engineers]
日期:2021-06-01
卷期号:: 15603-15613
被引量:98
标识
DOI:10.1109/cvpr46437.2021.01535
摘要
In this paper, we propose a conditional early exiting framework for efficient video recognition. While existing works focus on selecting a subset of salient frames to re-duce the computation costs, we propose to use a simple sampling strategy combined with conditional early exiting to enable efficient recognition. Our model automatically learns to process fewer frames for simpler videos and more frames for complex ones. To achieve this, we employ a cascade of gating modules to automatically determine the earliest point in processing where an inference is sufficiently reliable. We generate on-the-fly supervision signals to the gates to provide a dynamic trade-off between accuracy and computational cost. Our proposed model outperforms competing methods on three large-scale video benchmarks. In particular, on ActivityNet1.3 and mini-kinetics, we outperform the state-of-the-art efficient video recognition methods with 1.3× and 2.1 less GFLOPs, respectively. Addition-ally, our method sets× a new state of the art for efficient video understanding on the HVU benchmark.
科研通智能强力驱动
Strongly Powered by AbleSci AI