Tag completion with defective tag assignments via image-tag re-weighting
Tag completion with defective tag assignments via image-tag re-weighting
复制标题
DOI：
10.1109/icme.2014.6890154
复制
发表时间：
2014-07
期刊：
影响因子：
--
通讯作者：
Xing Xu;Atsushi Shimada;R. Taniguchi
中科院分区：
文献类型：
--
作者：
Xing Xu;Atsushi Shimada;R. Taniguchi
用户提供的图像标签通常是不完整或有噪声的，以描述相应图像的可视内容。在本文中，我们考虑了覆盖不完整和噪声两种情况的有缺陷标注，并解决了训练图像的标记分配有缺陷时的标记补全问题。虽然以前关于标签补全的研究通常在处理每幅图像的每个缺失或噪声标签时对经验损失给予相同的惩罚，但我们表明这可能是次优的，因为每个标签与每幅图像的相关性因缺陷设置而不同。为此，我们引入了一种图像标签重加权方案，综合考虑了图像相似度和标签关联度，对每个标签对每幅图像的惩罚项进行重新加权，并建立了统一的加权经验损失函数。实验结果表明，在现有的标签补全算法中嵌入重新加权的经验损失函数，在处理有缺陷的标签分配问题上取得了显著的改进。
User-provided image tags are usually incomplete or noisy to describe the visual content of corresponding images. In this paper, we consider defective tagging which covers both incomplete and noisy situations, and address the problem of tag completion where tag assignments of training images are defective. While previous studies on tag completion usually assign equal penalty to empirical loss when processing each missing or noisy tag for each image, we show that this may be suboptimal as the relatedness of each tag to each image varies due to the defective setting. Thus, we introduce an image-tag re-weighting scheme to re-weight the penalty term of each tag to each image considering both image similarities and tag associations, and formulate a unified re-weighted empirical loss function. Experimental evaluations show that embedding proposed re-weighted empirical loss function in state-of-the-art tag completion algorithms achieves significant improvement in dealing with defective tag assignments.