The key of zero-shot learning is to use the visual-semantic embedding to transfer the knowledge from seen classes to unseen classes. In this paper, we propose to build the visual-semantic embedding by maximizing the mutual information between visual features and corresponding attributes. Then, the mutual information between visual and semantic features can be utilized to guide the knowledge transfer from seen domain to unseen domain. Since we are primarily interested in maximizing mutual information, we introduce the noise-contrastive estimation to calculate lower-bound value of mutual information. Through the noise-contrastive estimation, we reformulate zero-shot learning as a binary classification problem, i.e., classifying the matching visual-semantic pairs (positive samples) and mismatching visual-semantic pairs (negative/noise samples). Experiments conducted on five datasets demonstrate that the proposed mutual information estimators outperforms current state-of-the-art methods both in conventional and generalized zero-shot learning settings.

零镜头学习的关键是使用视觉语义嵌入将知识从可见的班级转移到看不见的班级。在本文中，我们建议通过最大化视觉特征与相应属性之间的相互信息来构建视觉语义嵌入。然后，可以利用视觉和语义特征之间的相互信息来指导知识从可见域转移到不可见域。由于我们主要对最大化互信息感兴趣，因此我们引入了噪声对比估计来计算互信息的下界值。通过噪声对比估计，我们将零镜头学习重新定义为二进制分类问题，即将匹配的视觉语义对（正样本）和不匹配的视觉语义对（负样本/噪声样本）分类。