论文标题
利用可见和看不见的语义关系来生成零射门学习
Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learning
论文作者
论文摘要
通过利用语义信息将知识从可见的类转移到看不见的类，零射击学习（ZSL）解决了看不见的类识别问题。生成模型综合了看不见的视觉特征，并将ZSL转换为经典的监督学习问题。这些生成模型是使用所见类培训的，并有望将知识从看不见的类中隐式地转移到看不见的类别。但是，它们的性能因过度拟合而受到阻碍，这会导致广义零射门学习（GZSL）的不合格性能。为了解决这一问题，我们提出了新颖的LSRGAN，这是一种生成模型，该模型利用了可见类别和看不见的类别之间的语义关系，并通过结合新的语义正则化损失（SR-loss）来明确执行知识转移。 SR-loss指导LSRGAN生成视觉特征，以反映看到和看不见的类之间的语义关系。在七个基准数据集上进行的实验，包括具有挑战性的Wikipedia基于文本的Cub和Nabirds拆分，以及基于属性的AWA，CUB和SUN，与ZSL和GZSL的先前最先进的方法相比，LSRGAN的优越性表明了LSRGAN的优势。代码可在https：// github上找到。 com/ maunil/ lsrgan
Zero-shot learning (ZSL) addresses the unseen class recognition problem by leveraging semantic information to transfer knowledge from seen classes to unseen classes. Generative models synthesize the unseen visual features and convert ZSL into a classical supervised learning problem. These generative models are trained using the seen classes and are expected to implicitly transfer the knowledge from seen to unseen classes. However, their performance is stymied by overfitting, which leads to substandard performance on Generalized Zero-Shot learning (GZSL). To address this concern, we propose the novel LsrGAN, a generative model that Leverages the Semantic Relationship between seen and unseen categories and explicitly performs knowledge transfer by incorporating a novel Semantic Regularized Loss (SR-Loss). The SR-loss guides the LsrGAN to generate visual features that mirror the semantic relationships between seen and unseen classes. Experiments on seven benchmark datasets, including the challenging Wikipedia text-based CUB and NABirds splits, and Attribute-based AWA, CUB, and SUN, demonstrates the superiority of the LsrGAN compared to previous state-of-the-art approaches under both ZSL and GZSL. Code is available at https: // github. com/ Maunil/ LsrGAN
