In compositional zero-shot learning, the goal is to recognize unseen
compositions (e.g. old dog) of observed visual primitives states (e.g. old,
cute) and objects (e.g. car, dog) in the training set. This is challenging
because the same state can for example alter the visual appearance of a dog
drastically differently from a car. As a solution, we propose a novel graph
formulation called Compositional Graph Embedding (CGE) that learns image
features, compositional classifiers, and latent representations of visual
primitives in an end-to-end manner. The key to our approach is exploiting the
dependency between states, objects, and their compositions within a graph
structure to enforce the relevant knowledge transfer from seen to unseen
compositions. By learning a joint compatibility that encodes semantics between
concepts, our model allows for generalization to unseen compositions without
relying on an external knowledge base like WordNet. We show that in the
challenging generalized compositional zero-shot setting our CGE significantly
outperforms the state of the art on MIT-States and UT-Zappos. We also propose a
new benchmark for this task based on the recent GQA dataset. Code is available
at: this https URL

本研究提出了一种名为 Compositional Graph Embedding（CGE）的图形学习方法，可以实现对已出现的视觉对象和视觉基元状态的组合的识别和理解，进而实现了基于组合的零样本学习，避免了外部知识库的依赖。CGE 不仅可以学习图像特征，合成分类器，还可以学习视觉基元的潜在特征，最终可以进行对未出现过的组合图像识别，相比其他方法，CGE 在 MIT-States 和 UT-Zappos 等数据集上具有更好的性能表现。