arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.07325cs.CV
收藏

面向多标签图像识别的语义特定图表示学习

Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition

Sun Yat-sen University(中山大学);DarkMatter AI Research(DarkMatter AI研究机构)

Tianshui Chen, Muxin Xu, Xiaolu Hui, Hefeng Wu, Liang Lin

摘要:

图像多标签识别是一个具有实际意义和挑战性的任务,通过搜索语义感知区域和建立标签依赖模型已经取得了重大进展。然而,目前的方法不能准确定位的语义区域,由于缺乏部分级的监督或语义指导。此外,它们不能充分探索语义区域之间的相互作用,也没有显式地对标签共现进行建模。为了解决这些问题,我们提出了一个语义特定图表示学习(SSGRL)框架,该框架由两个关键模块组成:1)语义解耦模块,该模块将类别语义结合起来,以指导学习语义特定的表示; 2)语义交互模块,该模块将这些表示与基于统计标签共现的图相关联,并通过图传播机制探索它们的交互。在公共基准测试上进行的大量实验表明,我们的SSGRL框架在相当大的幅度上优于当前最先进的方法,例如,在PASCAL VOC 2007和2012,Microsoft-COCO和Visual Genome基准测试中,mAP分别提高了2.5%,2.6%,6.7%和3.1%。我们的代码和型号可在https://github.com/HCPLab-SYSU/SSGRL上获得。

英文摘要:

Recognizing multiple labels of images is a practical and challenging task, and significant progress has been made by searching semantic-aware regions and modeling label dependency. However, current methods cannot locate the semantic regions accurately due to the lack of part-level supervision or semantic guidance. Moreover, they cannot fully explore the mutual interactions among the semantic regions and do not explicitly model the label co-occurrence. To address these issues, we propose a Semantic-Specific Graph Representation Learning (SSGRL) framework that consists of two crucial modules: 1) a semantic decoupling module that incorporates category semantics to guide learning semantic-specific representations and 2) a semantic interaction module that correlates these representations with a graph built on the statistical label co-occurrence and explores their interactions via a graph propagation mechanism. Extensive experiments on public benchmarks show that our SSGRL framework outperforms current state-of-the-art methods by a sizable margin, e.g. with an mAP improvement of 2.5%, 2.6%, 6.7%, and 3.1% on the PASCAL VOC 2007 & 2012, Microsoft-COCO and Visual Genome benchmarks, respectively. Our codes and models are available at https://github.com/HCPLab-SYSU/SSGRL.

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。

↑