Abstract In generalized zero-shot learning (GZSL), it is imperative to solve the bias problem due to extreme data imbalance between seen and unseen classes, i.e., unseen classes are misclassified as seen classes. We alleviate the bias problem by generating synthetic images of unseen classes. The most challenging part is that existing GAN methods are only focused on producing authentic seen images, so realistic unseen images cannot be generated. Specifically, we propose a novel zero-shot generative adversarial network (ZSGAN) which learns the relationship between images and attributes shared by seen and unseen classes. Unlike existing works that generate synthetic features of unseen classes, we can generate more generalizable realistic unseen images. For instance, generated unseen images can be used for zero-shot detection, segmentation, and image translation since images have spatial information. We also propose domain-free networks (DFN) that can effectively distinguish seen and unseen domains for input images. We evaluate our approaches on three challenging GZSL datasets, including CUB, FLO, and AWA2. We outperform the state-of-the-art methods and also empirically verify that our proposed method is a network-agnostic approach, i.e., the generated unseen images can improve performance regardless of the neural network type.

中文翻译：

---

用于广义零镜头学习的看不见的图像生成无域网络

摘要 在广义零样本学习（GZSL）中，由于可见类和不可见类之间的极端数据不平衡，即不可见类被错误分类为可见类，必须解决偏差问题。我们通过生成未见过类的合成图像来缓解偏差问题。最具挑战性的部分是现有的 GAN 方法只专注于生成真实的可见图像，因此无法生成逼真的看不见的图像。具体来说，我们提出了一种新颖的零镜头生成对抗网络（ZSGAN），它学习图像和可见类和不可见类共享的属性之间的关系。与生成不可见类的合成特征的现有作品不同，我们可以生成更通用的真实不可见图像。例如，生成的看不见的图像可用于零镜头检测、分割、和图像翻译，因为图像具有空间信息。我们还提出了无域网络（DFN），它可以有效区分输入图像的可见域和不可见域。我们在三个具有挑战性的 GZSL 数据集上评估我们的方法，包括 CUB、FLO 和 AWA2。我们优于最先进的方法，并且还凭经验验证了我们提出的方法是一种与网络无关的方法，即，无论神经网络类型如何，生成的看不见的图像都可以提高性能。