Multi-Label Zero-Shot Learning with Structured Knowledge Graphs
It addresses the problem of predicting multiple unseen labels in classification tasks, which is incremental as it builds on existing zero-shot learning approaches.
The paper tackles multi-label zero-shot learning by incorporating knowledge graphs to model label relationships, achieving comparable or improved performance over state-of-the-art methods.
In this paper, we propose a novel deep learning architecture for multi-label zero-shot learning (ML-ZSL), which is able to predict multiple unseen class labels for each input instance. Inspired by the way humans utilize semantic knowledge between objects of interests, we propose a framework that incorporates knowledge graphs for describing the relationships between multiple labels. Our model learns an information propagation mechanism from the semantic label space, which can be applied to model the interdependencies between seen and unseen class labels. With such investigation of structured knowledge graphs for visual reasoning, we show that our model can be applied for solving multi-label classification and ML-ZSL tasks. Compared to state-of-the-art approaches, comparable or improved performances can be achieved by our method.