基于语义引导生成式随机游走的持续零样本学习
Continual Zero-Shot Learning through Semantically Guided Generative Random Walks
AI总结：
针对训练阶段无未见类信息的持续零样本学习问题，提出带语义引导生成式随机游走损失的算法，从理论上解释生成式建模的作用，在多个数据集上取得3-7%的性能提升。
摘要：
人类一生中会同时发生学习新概念、记住已有知识并将其适配到未来任务的过程。为建模这类综合能力，学界近期提出了持续零样本学习（CZSL）。但现有多数方法过度依赖未见类语义信息，而这类信息在真实场景中可能无法持续获取。本文针对训练阶段不提供未见类信息的持续零样本学习挑战，采用生成式建模方法加以解决。生成式方法的核心是从已见类中学习高质量表征，以提升模型对未见视觉空间的生成理解。受此启发，我们引入泛化界工具，首次从理论层面解释了生成式建模对CZSL任务的增益作用。在理论分析的指导下，我们提出了一种采用全新语义引导生成式随机游走（GRW）损失的学习算法。GRW损失通过持续激励模型生成真实且具类别区分度的样本以表征未见空间，实现了训练增强。我们的算法在AWA1、AWA2、CUB和SUN数据集上取得了当前最优性能，较现有CZSL方法提升3-7%。代码已公开于https://github.com/wx-zhang/IGCZSL。
英文摘要：
Learning novel concepts, remembering previous knowledge, and adapting it to future tasks occur simultaneously throughout a human's lifetime. To model such comprehensive abilities, continual zero-shot learning (CZSL) has recently been introduced. However, most existing methods overused unseen semantic information that may not be continually accessible in realistic settings. In this paper, we address the challenge of continual zero-shot learning where unseen information is not provided during training, by leveraging generative modeling. The heart of the generative-based methods is to learn quality representations from seen classes to improve the generative understanding of the unseen visual space. Motivated by this, we introduce generalization-bound tools and provide the first theoretical explanation for the benefits of generative modeling to CZSL tasks. Guided by the theoretical analysis, we then propose our learning algorithm that employs a novel semantically guided Generative Random Walk (GRW) loss. The GRW loss augments the training by continually encouraging the model to generate realistic and characterized samples to represent the unseen space. Our algorithm achieves state-of-the-art performance on AWA1, AWA2, CUB, and SUN datasets, surpassing existing CZSL methods by 3-7\%. The code has been made available here \url{https://github.com/wx-zhang/IGCZSL}
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
