arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.07032cs.CV
收藏

面向零样本学习的结构感知特征生成

Structure-Aware Feature Generation for Zero-Shot Learning

University of Technology Sydney(悉尼科技大学);University of Sydney(悉尼大学);National University of Singapore(新加坡国立大学);JD Explore Academy, JD.com(京东探索研究院)

Lianbo Zhang, Shaoli Huang, Xinchao Wang, Wei Liu, Dacheng Tao

摘要:

零样本学习(Zero-Shot Learning,缩写为ZRL)的目标是通过利用辅助信息(如属性嵌入)来识别不可见的类别。尽管取得了令人鼓舞的结果,以前的CNOL方法专注于提高所见类别特征的判别能力,但在很大程度上忽略了样本和原型的几何结构。因此,随后的基于属性的生成对抗网络(GAN)也忽略了样本生成中的拓扑信息,并进一步在分类未见过类的视觉特征方面产生较差的性能。在本文中,我们介绍了一种新的结构感知的特征生成方案,称为SA-GAN,明确说明在学习潜在空间和生成网络的拓扑结构。具体来说,我们引入了一个约束损失,以保持初始的几何结构时,学习一个有区别的潜在空间,并进行我们的GAN训练与额外的监督信号从结构感知的神经网络和重建模块。前者根据样本与类原型的相似性来区分真假样本,后者则从生成的特征空间中重构原始特征空间。这种拓扑保持机制使我们的方法,以显着提高泛化能力的unseen类,从而提高分类性能。四个基准测试的实验表明,所提出的方法始终优于最先进的。我们的代码可以在补充材料中找到,也将公开提供。

英文摘要:

Zero-Shot Learning (ZSL) targets at recognizing unseen categories by leveraging auxiliary information, such as attribute embedding. Despite the encouraging results achieved, prior ZSL approaches focus on improving the discriminant power of seen-class features, yet have largely overlooked the geometric structure of the samples and the prototypes. The subsequent attribute-based generative adversarial network (GAN), as a result, also neglects the topological information in sample generation and further yields inferior performances in classifying the visual features of unseen classes. In this paper, we introduce a novel structure-aware feature generation scheme, termed as SA-GAN, to explicitly account for the topological structure in learning both the latent space and the generative networks. Specifically, we introduce a constraint loss to preserve the initial geometric structure when learning a discriminative latent space, and carry out our GAN training with additional supervising signals from a structure-aware discriminator and a reconstruction module. The former supervision distinguishes fake and real samples based on their affinity to class prototypes, while the latter aims to reconstruct the original feature space from the generated latent space. This topology-preserving mechanism enables our method to significantly enhance the generalization capability on unseen-classes and consequently improve the classification performance. Experiments on four benchmarks demonstrate that the proposed approach consistently outperforms the state of the art. Our code can be found in the supplementary material and will also be made publicly available.

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。

↑