arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.03260cs.LGcs.AI
收藏

面向零样本学习的语义归纳属性选择

Semantic-Inductive Attribute Selection for Zero-Shot Learning

Department of Computer Science and Artificial Intelligence, University of Granada(格拉纳达大学计算机科学与人工智能系);Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI)(安达卢西亚数据科学与计算智能研究所);School of Computer Science, University of Nottingham(诺丁汉大学计算机科学学院)

Juan Jose Herrera-Aranda, Guillermo Gomez-Trenado, Francisco Herrera, Isaac Triguero

AI总结:

针对零样本学习中语义空间属性存在噪声、冗余的问题,提出归纳设置下的划分方案,结合两种互补特征选择策略,在五个基准数据集上均提升了未见类准确率,验证了语义空间冗余性与方案有效性。

摘要:

零样本学习(Zero-Shot Learning,ZSL)是通用人工智能系统中的重要范式,尤其适用于系统必须动态适应新任务的开放世界场景。语义空间在连接已见类和未见类方面发挥着关键作用,但无论是人工标注的还是由机器学习模型生成的语义空间,通常都包含噪声、冗余或不相关的属性,会阻碍性能表现。为解决这一问题,我们提出了一种划分方案,在最具挑战性的归纳设置下模拟未见类条件,使得无需获取未见类的语义信息即可评估属性的相关性。在该框架内,我们研究了两种互补的特征选择策略并评估了它们的泛化能力。第一种策略将嵌入式特征选择适配于ZSL的特定需求,将模型驱动的排序转化为有意义的语义剪枝;第二种策略利用进化计算更广泛地直接探索属性子集空间。在五个基准数据集(AWA2、CUB、SUN、aPY、FLO)上的实验表明,两种方法都能通过减少冗余持续提升未见类的准确率,但作用方式互补:RFS高效且具有竞争力,但依赖关键超参数;而GA计算成本更高,但能更广泛地探索搜索空间,且不存在这种超参数依赖。这些结果证实了语义空间本质上具有冗余性,同时凸显了所提出的划分方案是在归纳条件下优化语义空间的有效工具。

英文摘要:

Zero-Shot Learning is an important paradigm within General-Purpose Artificial Intelligence Systems, particularly in those that operate in open-world scenarios where systems must adapt to new tasks dynamically. Semantic spaces play a pivotal role as they bridge seen and unseen classes, but whether human-annotated or generated by a machine learning model, they often contain noisy, redundant, or irrelevant attributes that hinder performance. To address this, we introduce a partitioning scheme that simulates unseen conditions in an inductive setting (which is the most challenging), allowing attribute relevance to be assessed without access to semantic information from unseen classes. Within this framework, we study two complementary feature-selection strategies and assess their generalisation. The first adapts embedded feature selection to the particular demands of ZSL, turning model-driven rankings into meaningful semantic pruning; the second leverages evolutionary computation to directly explore the space of attribute subsets more broadly. Experiments on five benchmark datasets (AWA2, CUB, SUN, aPY, FLO) show that both methods consistently improve accuracy on unseen classes by reducing redundancy, but in complementary ways: RFS is efficient and competitive though dependent on critical hyperparameters, whereas GA is more costly yet explores the search space more broadly and avoids such dependence. These results confirm that semantic spaces are inherently redundant and highlight the proposed partitioning scheme as an effective tool to refine them under inductive conditions.

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。

↑