arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1608.01441cs.CV
收藏

利用结构化语义相关性改进缺失标签的多标签学习

Improving Multi-label Learning with Missing Labels by Structured Semantic Correlations

IHPC, A*STAR(高性能计算研究所,新加坡科技研究局);School of Computer Science and Engineering, NTU(南洋理工大学计算机科学与工程学院)

Hao Yang, Joey Tianyi Zhou, Jianfei Cai

摘要:

多标记学习近年来在计算机视觉领域引起了广泛的关注,在多目标识别、图像自动标注等视觉任务中得到了广泛的应用。将多个标签与复杂图像相关联是非常困难的,这不仅是由于描述图像的复杂性,而且还因为观察到的标签的不完整性。现有的作品在这个问题上要么忽略了标签和实例的相关性,或只是假设这些相关性是线性和非结构化的。考虑到图像之间的语义相关性实际上是结构化的,本文提出将结构化的语义相关性结合起来,以解决多标签学习中的标签缺失问题。具体来说,我们将图像投影到具有有效语义描述符的语义空间。然后在这些图像上构建语义图以捕获它们之间的结构化关联。我们利用语义图拉普拉斯算子作为多标签学习公式中的平滑项,将结构化的语义相关性结合起来。实验结果表明,所提出的语义描述符的有效性和有用的结构化的语义相关性。我们在四个基准数据集上取得了比最先进的多标签学习方法更好的结果。

英文摘要:

Multi-label learning has attracted significant interests in computer vision recently, finding applications in many vision tasks such as multiple object recognition and automatic image annotation. Associating multiple labels to a complex image is very difficult, not only due to the intricacy of describing the image, but also because of the incompleteness nature of the observed labels. Existing works on the problem either ignore the label-label and instance-instance correlations or just assume these correlations are linear and unstructured. Considering that semantic correlations between images are actually structured, in this paper we propose to incorporate structured semantic correlations to solve the missing label problem of multi-label learning. Specifically, we project images to the semantic space with an effective semantic descriptor. A semantic graph is then constructed on these images to capture the structured correlations between them. We utilize the semantic graph Laplacian as a smooth term in the multi-label learning formulation to incorporate the structured semantic correlations. Experimental results demonstrate the effectiveness of the proposed semantic descriptor and the usefulness of incorporating the structured semantic correlations. We achieve better results than state-of-the-art multi-label learning methods on four benchmark datasets.

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。

↑