Zero-shot learning (ZSL) in visual classification aims to recognize novel categories for which few or even no training samples are available. Through recent advances using generative adversarial networks (GANs) for cross-modal generation, several generative methods have been investigated for ZSL to classify unseen categories with synthetic samples. However, these GAN-based ZSL approaches still struggle to generate samples with semantic consistency and significant between-class discrepancy while preserving within-class diversity, which are vital to building classifiers for unseen classes. Accordingly, in this paper, we propose a robust dual-stream GAN to synthesize satisfactory samples for zero-shot visual classification. In more detail, the inter-class discrepancy is maximized by a backbone compatibility loss, which drives the center of the synthesized samples to move towards the center of real samples of the same class while moving further away from samples of different classes. Secondly, in order to preserve the intra-class diversity ignored by most extant paradigms, we propose a stochastic dispersion regularization to encourage the synthesized samples to be distributed at arbitrary points in the visual space of their categories. Finally, unlike previous methods that project visual samples back into semantic space and consequently cause an information degradation problem, we design a dual-stream generator to synthesize visual samples and reconstruct semantic embedding simultaneously, thereby ensuring semantic consistency. Our model outperforms the state-of-the-arts by 4.7% and 3.0% on average in two metrics over four real-world datasets, demonstrating its effectiveness and superiority.

视觉分类中的零镜头学习（ZSL）旨在识别很少甚至没有培训样本的新颖类别。通过使用生成对抗网络（GAN）进行交叉模式生成的最新进展，已经研究了ZSL的几种生成方法，以使用合成样本对看不见的类别进行分类。但是，这些基于GAN的ZSL方法仍然难以在保持类内多样性的同时生成具有语义一致性和显着的类间差异的样本，这对于为看不见的类建立分类器至关重要。因此，在本文中，我们提出了一种鲁棒的双流GAN来合成令人满意的零镜头视觉分类样本。更详细地说，由于骨干网的兼容性损失，最大程度地提高了类间差异，它驱使合成样本的中心移向同一类别的真实样本的中心，同时远离不同类别的样本。其次，为了保持大多数现存范式所忽略的类内多样性，我们提出了一种随机色散正则化方法，以鼓励将合成样本分布在其类别的可视空间中的任意点上。最后，与以前的将视觉样本投射回语义空间并因此导致信息降级的方法不同，我们设计了一种双流生成器来合成视觉样本并同时重建语义嵌入，从而确保语义一致性。在四个真实数据集的两个指标中，我们的模型分别比最新技术高出4.7％和3.0％，