arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.12427cs.CV
收藏

基于逐帧推理的高效视频分割模型

Efficient Video Segmentation Models with Per-frame Inference

The University of Adelaide(阿德莱德大学);Zhejiang University(浙江大学);MeiTuan(美团);Baidu(百度)

Yifan Liu, Chunhua Shen, Changqian Yu, Jingdong Wang

摘要:

当在视频序列上测试时,用每个帧独立训练的大多数现有实时深度模型可能会在时间轴上产生不一致的结果。一些方法考虑了视频序列中的相关性,例如,通过使用光流将结果传播到相邻帧或使用多帧信息提取帧表示,这可能导致不准确的结果或不平衡的等待时间。在这项工作中,我们专注于提高时间的一致性,而不引入计算开销的推理。为此,我们在每一帧执行推理。通过在训练阶段从具有额外约束的视频帧中学习来实现时间一致性。为推理而引入。我们提出了几种技术来学习的视频序列,包括时间一致性损失和在线/离线知识蒸馏方法。在语义视频分割的任务中,在准确性,时间平滑性和效率之间进行权衡,我们提出的方法优于基于关键帧的方法和一些独立训练每帧的基线方法,包括Cityscapes,Camvid和300 VW-Mask。我们进一步将我们的训练方法应用于YouTubeVIS上的视频实例分割,并通过跨帧分割时间一致的实例级trimap,在视频序列中开发肖像抠图的应用程序。实验表明,优越的定性和定量结果。代码可从以下网址获得:https://git.io/vidseg。

英文摘要:

Most existing real-time deep models trained with each frame independently may produce inconsistent results across the temporal axis when tested on a video sequence. A few methods take the correlations in the video sequence into account,e.g., by propagating the results to the neighboring frames using optical flow or extracting frame representations using multi-frame information, which may lead to inaccurate results or unbalanced latency. In this work, we focus on improving the temporal consistency without introducing computation overhead in inference. To this end, we perform inference at each frame. Temporal consistency is achieved by learning from video frames with extra constraints during the training phase. introduced for inference. We propose several techniques to learn from the video sequence, including a temporal consistency loss and online/offline knowledge distillation methods. On the task of semantic video segmentation, weighing among accuracy, temporal smoothness, and efficiency, our proposed method outperforms keyframe-based methods and a few baseline methods that are trained with each frame independently, on datasets including Cityscapes, Camvid, and 300VW-Mask. We further apply our training method to video instance segmentation on YouTubeVISand develop an application of portrait matting in video sequences, by segmenting temporally consistent instance-level trimaps across frames. Experiments show superior qualitative and quantitative results. Code is available at: https://git.io/vidseg.

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。

↑