Compositional Zero-Shot Learning (CZSL) aims to train models to recognize novel compositional concepts based on learned concepts such as attribute-object combinations. One of the challenges is to model attributes interacted with different objects, e.g., the attribute ``wet" in ``wet apple" and ``wet cat" is different. As a solution, we provide analysis and argue that attributes are conditioned on the recognized object and input image and explore learning conditional attribute embeddings by a proposed attribute learning framework containing an attribute hyper learner and an attribute base learner. By encoding conditional attributes, our model enables to generate flexible attribute embeddings for generalization from seen to unseen compositions. Experiments on CZSL benchmarks, including the more challenging C-GQA dataset, demonstrate better performances compared with other state-of-the-art approaches and validate the importance of learning conditional attributes. Code is available at https://github.com/wqshmzh/CANet-CZSL

翻译：组合零样本学习（CZSL）旨在训练模型基于已习得的概念（如属性-对象组合）来识别新颖的组合概念。其中一个挑战在于建模与不同对象交互的属性，例如“湿苹果”和“湿猫”中的“湿”属性存在差异。作为解决方案，我们通过分析提出观点：属性以被识别对象和输入图像为条件，并探索通过一个包含属性超学习器和属性基学习器的属性学习框架来学习条件属性嵌入。通过编码条件属性，我们的模型能够生成灵活的属性嵌入，以泛化从已见组合到未见组合。在CZSL基准数据集（包括更具挑战性的C-GQA数据集）上的实验表明，与当前最先进方法相比，本方法取得了更优性能，并验证了学习条件属性的重要性。代码开源于 https://github.com/wqshmzh/CANet-CZSL