无需标注数据，通过时间匹配生成高质量视频实例分割伪标签。
FlowCut: Unsupervised Video Instance Segmentation via Temporal Mask Matching
- 利用图像与光流特征关联生成初始伪实例掩码。
- 通过帧间时间匹配构建高质量、一致的短视频片段。
- 在多个基准上达到领先性能，适合无监督学习研究者。
我们提出FlowCut，一种用于无监督视频实例分割的简单而高效的方法，采用三阶段框架构建带有伪标签的高质量视频数据集。据我们所知，这是首次尝试为无监督视频实例分割构建带伪标签的视频数据集。第一阶段通过利用图像和光流特征的相似性生成伪实例掩码；第二阶段通过跨帧时间匹配构建包含高一致性伪实例掩码的短视频段；第三阶段从YouTubeVIS-2021数据集提取训练用实例分割样本并训练视频分割模型。FlowCut在YouTubeVIS-2019、YouTubeVIS-2021、DAVIS-2017及DAVIS-2017 Motion等多个基准上均取得当前最优性能。
原文摘要 · Abstract (English)
We propose FlowCut, a simple and capable method for unsupervised video instance segmentation consisting of a three-stage framework to construct a high-quality video dataset with pseudo labels. To our knowledge, our work is the first attempt to curate a video dataset with pseudo-labels for unsupervised video instance segmentation. In the first stage, we generate pseudo-instance masks by exploiting the affinities of features from both images and optical flows. In the second stage, we construct short video segments containing high-quality, consistent pseudo-instance masks by temporally matching them across the frames. In the third stage, we use the YouTubeVIS-2021 video dataset to extract our training instance segmentation set, and then train a video segmentation model. FlowCut achieves state-of-the-art performance on the YouTubeVIS-2019, YouTubeVIS-2021, DAVIS-2017, and DAVIS-2017 Motion benchmarks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。