arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.11566cs.CVcs.AI
收藏

广义零样本学习中多知识融合的新特征生成

Multi-Knowledge Fusion for New Feature Generation in Generalized Zero-Shot Learning

National Pilot School of Software, Yunnan University(云南大学国家软件学院)

Hongxin Xiang, Cheng Xie, Ting Zeng, Yun Yang

摘要:

现有的零样本学习(Zero-Shot Learning,简称ZRL)方法存在语义不足和领域转移等问题,无法取得令人满意的效果。为了缓解这些问题,我们提出了一种新的生成式语义学习方法,从多知识中学习更多的广义特征,并在语义到视觉嵌入中不断生成新的语义。在我们的方法中,建议的多知识融合网络(MKFNet)采取不同的语义特征从多个知识作为输入,这使得更多的相关语义特征被训练语义到视觉嵌入,并最终产生更广义的视觉特征,通过自适应融合视觉特征从不同的知识领域。新特征生成器(New Feature Generator,NFG)采用自适应遗传策略,一方面丰富了语义信息,另一方面极大地提高了MKFNet生成的视觉特征与不可见视觉特征的交集。从经验上讲,我们表明,我们的方法可以实现显着更好的性能相比,现有的国家的最先进的方法在大量的基准测试的几个CNOL任务,包括传统的CNOL,广义CNOL和zero-shot检索。

英文摘要:

Suffering from the semantic insufficiency and domain-shift problems, most of existing state-of-the-art methods fail to achieve satisfactory results for Zero-Shot Learning (ZSL). In order to alleviate these problems, we propose a novel generative ZSL method to learn more generalized features from multi-knowledge with continuously generated new semantics in semantic-to-visual embedding. In our approach, the proposed Multi-Knowledge Fusion Network (MKFNet) takes different semantic features from multi-knowledge as input, which enables more relevant semantic features to be trained for semantic-to-visual embedding, and finally generates more generalized visual features by adaptively fusing visual features from different knowledge domain. The proposed New Feature Generator (NFG) with adaptive genetic strategy is used to enrich semantic information on the one hand, and on the other hand it greatly improves the intersection of visual feature generated by MKFNet and unseen visual faetures. Empirically, we show that our approach can achieve significantly better performance compared to existing state-of-the-art methods on a large number of benchmarks for several ZSL tasks, including traditional ZSL, generalized ZSL and zero-shot retrieval.

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。

↑