arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2002.11433cs.CV
收藏

基于逐帧推理的高效语义视频分割

Efficient Semantic Video Segmentation with Per-frame Inference

The University of Adelaide(阿德莱德大学);Huazhong University of Science and Technology(华中科技大学);Microsoft Research(微软研究院)

Yifan Liu, Chunhua Shen, Changqian Yu, Jingdong Wang

摘要:

对于语义分割,大多数现有的利用每个帧独立训练的实时深度模型可能对视频序列产生不一致的结果。高级方法考虑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,或者提取具有其它帧的帧表示,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,我们在推理过程中以每帧的方式处理高效的语义视频分割。与以往的逐帧模型不同,我们在训练过程中明确考虑帧间的时间一致性作为额外的约束,并将时间一致性嵌入到分割网络中。因此,在推理过程中,我们可以独立地处理每一帧,没有延迟,并提高时间一致性,没有额外的计算成本和后处理。我们采用紧凑的模型进行实时执行。为了缩小紧凑模型和大型模型之间的性能差距,设计了新的知识蒸馏方法。我们的结果优于以前的基于关键帧的方法,在流行的基准测试(包括Cityscapes和Camvid)上,准确性和推理速度之间有更好的权衡。与用每帧独立训练的相应基线相比,时间一致性也得到了改善。代码可在:https://tinyurl.com/segment-video

英文摘要:

For semantic segmentation, most existing real-time deep models trained with each frame independently may produce inconsistent results for a video sequence. Advanced methods take into considerations the correlations in the video sequence, e.g., by propagating the results to the neighboring frames using optical flow, or extracting the frame representations with other frames, which may lead to inaccurate results or unbalanced latency. In this work, we process efficient semantic video segmentation in a per-frame fashion during the inference process. Different from previous per-frame models, we explicitly consider the temporal consistency among frames as extra constraints during the training process and embed the temporal consistency into the segmentation network. Therefore, in the inference process, we can process each frame independently with no latency, and improve the temporal consistency with no extra computational cost and post-processing. We employ compact models for real-time execution. To narrow the performance gap between compact models and large models, new knowledge distillation methods are designed. Our results outperform previous keyframe based methods with a better trade-off between the accuracy and the inference speed on popular benchmarks, including the Cityscapes and Camvid. The temporal consistency is also improved compared with corresponding baselines which are trained with each frame independently. Code is available at: https://tinyurl.com/segment-video

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。

↑