Zero-shot learning (ZSL) aims to recognize unseen classes by transferring semantic knowledge from seen classes to unseen ones. Since only seen classes are available during training, the domain bias issue, i.e., the trained model is biased toward seen classes, is the key issue for ZSL. To alleviate the bias problem, generation-based approaches are proposed to build generative models that can generate fake visual features of unseen classes by utilizing semantic vectors. However, most of the existing generative methods still suffer some degree of domain bias caused by the ambiguous generation of fake features. In this paper, we propose a cross-modal propagation network (CMPN), which adopts an episode-based meta-learning strategy. CMPN incorporates the adaptive graph construction and label propagation into the generative ZSL framework for guaranteeing an unambiguous and discriminative fake feature generating. By further leveraging the manifold structure of different modalities in the latent space, CMPN can implicitly ensure intra-class compactness and inter-class separation through label propagation classification in latent space. Extensive experiments on four datasets validate the effectiveness of CMPN under both ZSL and generalized ZSL (GZSL) settings.

零样本学习 (ZSL) 旨在通过将语义知识从已见类转移到未见类来识别未见类。由于在训练期间只有看到的类可用，域偏差问题，即训练的模型偏向于看到的类，是 ZSL 的关键问题。为了缓解偏差问题，提出了基于生成的方法来构建生成模型，该模型可以利用语义向量生成看不见的类别的虚假视觉特征。然而，大多数现有的生成方法仍然存在一定程度的域偏差，原因是虚假特征的生成不明确。在本文中，我们提出了一种跨模态传播网络（CMPN），它采用基于情节的元学习策略。CMPN 将自适应图构建和标签传播结合到生成式 ZSL 框架中，以确保生成明确和有区别的假特征。通过进一步利用潜在空间中不同模态的流形结构，CMPN 可以通过潜在空间中的标签传播分类隐式地确保类内紧凑性和类间分离。在四个数据集上进行的大量实验验证了 CMPN 在 ZSL 和广义 ZSL (GZSL) 设置下的有效性。