Compositional zero-shot learning (CZSL) aims at learning visual concepts (i.e., attributes and objects) from seen compositions and combining concept knowledge into unseen compositions. The key to CZSL is learning the disentanglement of the attribute-object composition. To this end, we propose to exploit cross-attentions as compositional disentanglers to learn disentangled concept embeddings. For example, if we want to recognize an unseen composition "yellow flower", we can learn the attribute concept "yellow" and object concept "flower" from different yellow objects and different flowers respectively. To further constrain the disentanglers to learn the concept of interest, we employ a regularization at the attention level. Specifically, we adapt the earth mover's distance (EMD) as a feature similarity metric in the cross-attention module. Moreover, benefiting from concept disentanglement, we improve the inference process and tune the prediction score by combining multiple concept probabilities. Comprehensive experiments on three CZSL benchmark datasets demonstrate that our method significantly outperforms previous works in both closed- and open-world settings, establishing a new state-of-the-art.

翻译：组合零样本学习（CZSL）旨在从已见组成中学习视觉概念（即属性和对象），并将概念知识结合到未见组合中。 CZSL的关键是学习属性-对象组合的解开。为此，我们建议将交叉关注作为组合分离器来学习分离的概念嵌入。例如，如果我们想识别一个未知的组合“黄色的花”，我们可以从不同的黄色物体和不同的花中分别学习属性概念“黄色”和对象概念“花”。为了进一步约束分离器学习感兴趣的概念，我们在关注水平上使用正则化。具体来说，我们采用Earth Mover's距离（EMD）作为跨中心模块中的特征相似性度量。此外，受益于概念分离，我们改进了推理过程，并通过组合多个概念概率来调整预测分数。对三个CZSL基准数据集的全面实验证明，我们的方法在封闭和开放世界的设置中都显著优于以前的作品，树立了新的最高水平。