arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.04730cs.CV
收藏

X3D:扩展架构以实现高效视频识别

X3D: Expanding Architectures for Efficient Video Recognition

Facebook AI Research (FAIR)(Facebook AI研究院(FAIR))

Christoph Feichtenhofer

摘要:

本文介绍了X3D,一个家庭的高效视频网络,逐步扩大一个微小的二维图像分类架构沿多个网络轴,在空间,时间,宽度和深度。受机器学习中的特征选择方法的启发,采用简单的逐步网络扩展方法,该方法在每个步骤中扩展单个轴,使得实现良好的精度与复杂度的折衷。为了将X3D扩展到特定的目标复杂度,我们执行渐进式向前扩展,然后向后收缩。X3D实现了最先进的性能,同时需要4.8倍和5.5倍的乘加和参数,以获得与以前工作相似的精度。我们最令人惊讶的发现是,具有高时空分辨率的网络可以表现良好,同时在网络宽度和参数方面非常轻。我们在视频分类和检测基准测试中以前所未有的效率报告了具有竞争力的准确性。代码将在:https://github.com/facebookresearch/SlowFast

英文摘要:

This paper presents X3D, a family of efficient video networks that progressively expand a tiny 2D image classification architecture along multiple network axes, in space, time, width and depth. Inspired by feature selection methods in machine learning, a simple stepwise network expansion approach is employed that expands a single axis in each step, such that good accuracy to complexity trade-off is achieved. To expand X3D to a specific target complexity, we perform progressive forward expansion followed by backward contraction. X3D achieves state-of-the-art performance while requiring 4.8x and 5.5x fewer multiply-adds and parameters for similar accuracy as previous work. Our most surprising finding is that networks with high spatiotemporal resolution can perform well, while being extremely light in terms of network width and parameters. We report competitive accuracy at unprecedented efficiency on video classification and detection benchmarks. Code will be available at: https://github.com/facebookresearch/SlowFast

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑