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 2104.00682cs.CVcs.AIcs.LG
收藏

视频半监督学习的多视点伪标记

Multiview Pseudo-Labeling for Semi-supervised Learning from Video

Facebook AI Research (FAIR)(脸书人工智能研究院)

Bo Xiong, Haoqi Fan, Kristen Grauman, Christoph Feichtenhofer

摘要:

我们提出了一个多视图伪标记的方法来视频学习,一个新的框架,使用互补的意见的形式的外观和运动信息的半监督学习在视频。互补视图有助于在未标记的视频上获得更可靠的伪标签,以学习比纯监督数据更强的视频表示。虽然我们的方法利用了多个视图,但它仍然训练了一个跨外观和运动输入共享的模型,因此,通过设计,在推理时不会产生额外的计算开销。在多个视频识别数据集上,我们的方法大大优于其监督对应,并与以前在自监督视频表示学习中的标准基准上的工作相比毫不逊色。

英文摘要:

We present a multiview pseudo-labeling approach to video learning, a novel framework that uses complementary views in the form of appearance and motion information for semi-supervised learning in video. The complementary views help obtain more reliable pseudo-labels on unlabeled video, to learn stronger video representations than from purely supervised data. Though our method capitalizes on multiple views, it nonetheless trains a model that is shared across appearance and motion input and thus, by design, incurs no additional computation overhead at inference time. On multiple video recognition datasets, our method substantially outperforms its supervised counterpart, and compares favorably to previous work on standard benchmarks in self-supervised video representation learning.

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。

↑