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 2111.04080cs.CVcs.AIcs.LGcs.MM
收藏

基于标签属性嵌入的跨模态Zero-shot哈希算法

Cross-modal Zero-shot Hashing by Label Attributes Embedding

Southwest University(西南大学);Shandong University(山东大学);Joint SDU-NTU Centre for Artificial Intelligence Research(山东大学-南洋理工大学人工智能联合研究中心);King Abdullah University of Science and Technology(阿卜杜拉国王科技大学);George Mason University(乔治梅森大学)

Runmin Wang, Guoxian Yu, Lei Liu, Lizhen Cui, Carlotta Domeniconi, Xiangliang Zhang

摘要:

跨模态哈希算法是跨模态近似最近邻搜索中最有前途的方法之一。大多数CMH解决方案理想地假设训练集和测试集的标签是相同的。然而,该假设经常被违反,导致zero-shot CMH问题。最近的努力,以解决这个问题的重点是转移知识从可见的类看不见的标签属性。然而,属性是孤立的多模态数据的特征。为了减少信息差距,我们引入了一种方法,称为LAEH(标签属性嵌入zero-shot跨模态哈希)。LAEH首先通过word2vec模型得到标签的初始语义属性向量,然后使用一个转换网络将它们转换到一个公共子空间中。接下来,它利用哈希向量和特征相似性矩阵来指导不同模态的特征提取网络。同时,利用属性相似度作为标签相似度的补充,对标签嵌入和公共子空间进行修正。实验表明,LAEH算法优于相关的代表性的zero-shot和跨模态散列方法。

英文摘要:

Cross-modal hashing (CMH) is one of the most promising methods in cross-modal approximate nearest neighbor search. Most CMH solutions ideally assume the labels of training and testing set are identical. However, the assumption is often violated, causing a zero-shot CMH problem. Recent efforts to address this issue focus on transferring knowledge from the seen classes to the unseen ones using label attributes. However, the attributes are isolated from the features of multi-modal data. To reduce the information gap, we introduce an approach called LAEH (Label Attributes Embedding for zero-shot cross-modal Hashing). LAEH first gets the initial semantic attribute vectors of labels by word2vec model and then uses a transformation network to transform them into a common subspace. Next, it leverages the hash vectors and the feature similarity matrix to guide the feature extraction network of different modalities. At the same time, LAEH uses the attribute similarity as the supplement of label similarity to rectify the label embedding and common subspace. Experiments show that LAEH outperforms related representative zero-shot and cross-modal hashing methods.

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。

↑