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 2001.11091cs.CVcs.LGeess.IV
收藏

合成数据对行动分类的好处

The benefits of synthetic data for action categorization

American University of Beirut(贝鲁特美国大学)

Mohamad Ballout, Mohammad Tuqan, Daniel Asmar, Elie Shammas, George Sakr

摘要:

在本文中,我们研究的价值,使用综合制作的视频作为训练数据的神经网络用于动作分类。基于视频的纹理和背景在光流中几乎没有重要作用的事实,我们生成了简化的无纹理和无背景的视频,并利用合成数据来训练时间段网络(TSN)。结果表明,使用简化的合成数据增强TSN提高了原始网络的准确性(68.5%),当添加4,000个视频时,在HMDB-51上达到71.8%,当添加8,000个视频时达到72.4%。此外,在25个类的UCF-101上单独使用简化的合成视频进行训练,在2500个视频上训练时达到30.71%,在5000个视频上训练时达到52.7%。最后,结果表明,当将UCF-25的真实视频数量减少到10%并将其与合成视频相结合时,准确率下降到只有85.41%,而不添加合成数据时则下降到77.4%。

英文摘要:

In this paper, we study the value of using synthetically produced videos as training data for neural networks used for action categorization. Motivated by the fact that texture and background of a video play little to no significant roles in optical flow, we generated simplified texture-less and background-less videos and utilized the synthetic data to train a Temporal Segment Network (TSN). The results demonstrated that augmenting TSN with simplified synthetic data improved the original network accuracy (68.5%), achieving 71.8% on HMDB-51 when adding 4,000 videos and 72.4% when adding 8,000 videos. Also, training using simplified synthetic videos alone on 25 classes of UCF-101 achieved 30.71% when trained on 2500 videos and 52.7% when trained on 5000 videos. Finally, results showed that when reducing the number of real videos of UCF-25 to 10% and combining them with synthetic videos, the accuracy drops to only 85.41%, compared to a drop to 77.4% when no synthetic data is added.

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。

↑