Deep Semi-supervised Zero-shot Learning with Maximum Mean Discrepancy
Deep Semi-supervised Zero-shot Learning with Maximum Mean Discrepancy
复制标题
具有最大平均差异的深度半监督零样本学习
DOI：
10.1162/neco_a_01071
复制
发表时间：
2018
影响因子：
2.9
通讯作者：
Qinghua Zheng
中科院分区：
文献类型：
--
作者：
Lingling Zhang;Jun Liu;Minnan Luo;Xiaojun Chang;Qinghua Zheng
由于收集数十万个视觉类别的标记图像非常困难，零样本学习（即在训练阶段未见过的类别没有任何标记图像）引起了更多关注。过去，许多研究侧重于通过将所有类别标签投影到语义空间中，将知识从可见类别转移到不可见类别。然而，标签嵌入无法充分表达类别的语义。此外，无法准确捕获已见和未见实例的共同语义，因为这些实例的分布可能非常不同。针对这些问题，我们通过共同考虑不同模态之间的异质性差距和单模态实例之间的相关性，提出了一种新颖的深度半监督方法。该方法用相应的文本描述替换原始标签，以更好地捕获类别语义。该方法还通过最小化已见实例分布和未见实例分布之间的最大平均差异来克服分布差异问题。对两个基准数据集 CU200-Birds 和 Oxford Flowers-102 的广泛实验结果表明，我们的方法比以前的方法取得了显着的改进。
Due to the difficulty of collecting labeled images for hundreds of thousands of visual categories, zero-shot learning, where unseen categories do not have any labeled images in training stage, has attracted more attention. In the past, many studies focused on transferring knowledge from seen to unseen categories by projecting all category labels into a semantic space. However, the label embeddings could not adequately express the semantics of categories. Furthermore, the common semantics of seen and unseen instances cannot be captured accurately because the distribution of these instances may be quite different. For these issues, we propose a novel deep semisupervised method by jointly considering the heterogeneity gap between different modalities and the correlation among unimodal instances. This method replaces the original labels with the corresponding textual descriptions to better capture the category semantics. This method also overcomes the problem of distribution difference by minimizing the maximum mean discrepancy between seen and unseen instance distributions. Extensive experimental results on two benchmark data sets, CU200-Birds and Oxford Flowers-102, indicate that our method achieves significant improvements over previous methods.