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 1905.04424cs.CVcs.LG
收藏

无监督领域自适应的结构化判别张量字典学习

Structured Discriminative Tensor Dictionary Learning for Unsupervised Domain Adaptation

Nanjing University of Posts and Telecommunications(南京邮电大学);Texas State University(得克萨斯州立大学);University of Trento(特伦托大学);Nanjing University of Science and Technology(南京理工大学);University of Technology Sydney(悉尼科技大学);Wuhan University(武汉大学)

Songsong Wu, Yan Yan, Hao Tang, Jianjun Qian, Jian Zhang, Xiao-Yuan Jing

摘要:

无监督领域自适应(UDA)解决了在计算机视觉应用中常见的由于训练集和测试集之间的领域移位而导致的性能下降的问题。现有的UDA方法大多是基于矢量形式的数据,虽然在可视化应用中的数据或特征的典型格式是多维张量。此外,目前的方法,包括深度网络方法,假设提供了大量的标记源样本用于训练。然而,在实际应用中,标注源样本的数量总是有限的,由于昂贵的注释成本,使得次优性能被观察到。在本文中,我们提出了通过学习张量空间中的结构化字典来寻求多维数据的判别表示。该字典将领域信息和类信息分离,保证了表示对领域的鲁棒性。此外,为了避免外部分类器的设计,提出了一种伪标签估计方案,在算法迭代中结合判别分析。我们在有限的源样本的不同数据集上进行了广泛的结果。实验结果表明,该方法优于国家的最先进的方法。

英文摘要:

Unsupervised Domain Adaptation (UDA) addresses the problem of performance degradation due to domain shift between training and testing sets, which is common in computer vision applications. Most existing UDA approaches are based on vector-form data although the typical format of data or features in visual applications is multi-dimensional tensor. Besides, current methods, including the deep network approaches, assume that abundant labeled source samples are provided for training. However, the number of labeled source samples are always limited due to expensive annotation cost in practice, making sub-optimal performance been observed. In this paper, we propose to seek discriminative representation for multi-dimensional data by learning a structured dictionary in tensor space. The dictionary separates domain-specific information and class-specific information to guarantee the representation robust to domains. In addition, a pseudo-label estimation scheme is developed to combine with discriminant analysis in the algorithm iteration for avoiding the external classifier design. We perform extensive results on different datasets with limited source samples. Experimental results demonstrates that the proposed method outperforms the state-of-the-art approaches.

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。

↑