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 2301.03322cs.CV
收藏

利用对比学习简化开集视频领域自适应

Simplifying Open-Set Video Domain Adaptation with Contrastive Learning

University of Trento(特伦托大学);Fondazione Bruno Kessler(布鲁诺·凯斯勒基金会)

Giacomo Zara, Victor Guilherme Turrisi da Costa, Subhankar Roy, Paolo Rota, Elisa Ricci

摘要:

为了减少动作识别中的注释成本,已经提出了无监督视频领域自适应方法,其目的是从标记的数据集(即,源域)到未标记的数据集(即,目标域)。在这项工作中,我们解决了一个更现实的情况下,称为开放集视频领域自适应(OUVDA),目标数据集包含“未知”的语义类别,不与源共享。挑战在于对齐两个域的共享类,同时将共享类与未知类分开。在这项工作中,我们建议解决OUVDA与一个统一的对比学习框架,学习歧视和良好的聚类功能。我们还提出了一个面向视频的时间对比损失,使我们的方法,以更好地利用视频数据中的免费时间信息的特征空间聚类。我们发现,判别特征空间有利于更好地分离未知类,从而使我们能够使用一个简单的基于相似性的分数来识别它们。我们对多个OUVDA基准进行了彻底的实验评估,并显示了我们所提出的方法对现有技术的有效性。

英文摘要:

In an effort to reduce annotation costs in action recognition, unsupervised video domain adaptation methods have been proposed that aim to adapt a predictive model from a labelled dataset (i.e., source domain) to an unlabelled dataset (i.e., target domain). In this work we address a more realistic scenario, called open-set video domain adaptation (OUVDA), where the target dataset contains "unknown" semantic categories that are not shared with the source. The challenge lies in aligning the shared classes of the two domains while separating the shared classes from the unknown ones. In this work we propose to address OUVDA with an unified contrastive learning framework that learns discriminative and well-clustered features. We also propose a video-oriented temporal contrastive loss that enables our method to better cluster the feature space by exploiting the freely available temporal information in video data. We show that discriminative feature space facilitates better separation of the unknown classes, and thereby allows us to use a simple similarity based score to identify them. We conduct thorough experimental evaluation on multiple OUVDA benchmarks and show the effectiveness of our proposed method against the prior art.

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。

↑