Generalized zero-shot learning (GZSL) has achieved significant progress, with many efforts dedicated to overcoming the problems of visual-semantic domain gap and seen-unseen bias. However, most existing methods directly use feature extraction models trained on ImageNet alone, ignoring the cross-dataset bias between ImageNet and GZSL benchmarks. Such a bias inevitably results in poor-quality visual features for GZSL tasks, which potentially limits the recognition performance on both seen and unseen classes. In this paper, we propose a simple yet effective GZSL method, termed feature refinement for generalized zero-shot learning (FREE), to tackle the above problem. FREE employs a feature refinement (FR) module that incorporates \textit{semantic$\rightarrow$visual} mapping into a unified generative model to refine the visual features of seen and unseen class samples. Furthermore, we propose a self-adaptive margin center loss (SAMC-loss) that cooperates with a semantic cycle-consistency loss to guide FR to learn class- and semantically-relevant representations, and concatenate the features in FR to extract the fully refined features. Extensive experiments on five benchmark datasets demonstrate the significant performance gain of FREE over its baseline and current state-of-the-art methods. Our codes are available at https://github.com/shiming-chen/FREE .
翻译:普遍零光学习(GZSL)取得了显著进展,许多努力都致力于克服视觉-语义领域差距和可见的不见偏差问题。然而,大多数现有方法直接使用仅通过图像网络培训的特效提取模型,忽视图像网络和GZSL基准之间的交叉数据偏差。这种偏差不可避免地导致GZSL任务视觉特征质量差,这有可能限制在可见和看不见的类别上的识别性能。在本文中,我们提议一种简单而有效的GZSL方法,称为普遍零光学习的改进功能(FREE),以解决上述问题。 FREE使用一个功能改进模块,将“textit{semantic$\rightrowr$视觉”的绘图纳入一个统一的基因化模型,以完善所见和不可见的类样本的视觉特征。此外,我们提议一种自我调整的边际中心损失(SAMC-loss)与语义周期性损失合作,以指导FR学习等级和语义性相关表达方式,并将FRFR的特性配置纳入其现有基准/REEEF标准。在完全完善的常规上展示其现有基准性数据。