An open problem on the path to artificial intelligence is generalization from the known to the unknown, which is instantiated as Generalized Zero-Shot Learning (GZSL) task. In this work, we propose a novel Evolutionary Generalized Zero-Shot Learning setting, which (i) avoids the domain shift problem in inductive GZSL, and (ii) is more in line with the needs of real-world deployments than transductive GZSL. In the proposed setting, a zero-shot model with poor initial performance is able to achieve online evolution during application. We elaborate on three challenges of this special task, i.e., catastrophic forgetting, initial prediction bias, and evolutionary data class bias. Moreover, we propose targeted solutions for each challenge, resulting in a generic method capable of continuing to evolve on a given initial IGZSL model. Experiments on three popular GZSL benchmark datasets show that our model can learn from the test data stream while other baselines fail.

翻译：人工智能路径上的一个公开问题是从已知的到未知的简单化问题,即通用零热学习(GZSL)任务。在这项工作中,我们提出一个新的进化通用零热学习设置,即(一) 避免感化GZSL的域变问题,(二) 更符合真实世界部署的需要,而不是感化GZSL。在提议的设置中,初始性能差的零射线模型能够在应用过程中实现在线演变。我们详细介绍了这一特殊任务的三个挑战,即灾难性的遗忘、初步预测偏差和进化数据等级偏差。此外,我们提出了针对每一项挑战的有针对性的解决方案,从而形成了一种通用方法,能够继续发展给定的初始IGZSL模型。在三种流行的GZSL基准数据集上进行的实验表明,我们的模型可以在其他基线失败时从测试数据流中学习。