论文标题
从锚生成到分配对齐：学习零拍识别的歧视性嵌入空间
From Anchor Generation to Distribution Alignment: Learning a Discriminative Embedding Space for Zero-Shot Recognition
论文作者
论文摘要
在零射击学习（ZSL）中，要分类的样本通常被投影到诸如属性之类的侧面信息模板中。但是，模板的不规则分布使分类结果感到困惑。为了减轻此问题，我们提出了一个新颖的框架，称为歧视性锚生成和分布对齐模型（DAGDA）。首先，为了纠正原始模板的分布，提出了一个基于扩散的图形卷积网络，该网络可以显式地对班级和侧面信息之间的相互作用进行建模，以产生歧视性锚。其次，为了进一步将样品与锚固空间中的相应锚点对齐，旨在以细粒度的方式完善分布，我们在锚空间中引入了语义关系正则化。按照归纳学习的方式，我们的方法在几个基准数据集上都超过了一些现有的最新方法，用于传统和广义ZSL设置。同时，消融实验强烈证明了每个组件的有效性。
In zero-shot learning (ZSL), the samples to be classified are usually projected into side information templates such as attributes. However, the irregular distribution of templates makes classification results confused. To alleviate this issue, we propose a novel framework called Discriminative Anchor Generation and Distribution Alignment Model (DAGDA). Firstly, in order to rectify the distribution of original templates, a diffusion based graph convolutional network, which can explicitly model the interaction between class and side information, is proposed to produce discriminative anchors. Secondly, to further align the samples with the corresponding anchors in anchor space, which aims to refine the distribution in a fine-grained manner, we introduce a semantic relation regularization in anchor space. Following the way of inductive learning, our approach outperforms some existing state-of-the-art methods, on several benchmark datasets, for both conventional as well as generalized ZSL setting. Meanwhile, the ablation experiments strongly demonstrate the effectiveness of each component.
