Translational Concept Embedding for Generalized Compositional Zero-shot Learning
This work addresses a challenging problem in AI for improving zero-shot learning in compositional settings, but it is incremental as it builds on existing methods with specific enhancements.
The paper tackles generalized compositional zero-shot learning by addressing the gap between seen and unseen concepts and contextual dependencies between attributes and objects, achieving a good balance in predicting both seen and unseen concepts in classification tasks.
Generalized compositional zero-shot learning means to learn composed concepts of attribute-object pairs in a zero-shot fashion, where a model is trained on a set of seen concepts and tested on a combined set of seen and unseen concepts. This task is very challenging because of not only the gap between seen and unseen concepts but also the contextual dependency between attributes and objects. This paper introduces a new approach, termed translational concept embedding, to solve these two difficulties in a unified framework. It models the effect of applying an attribute to an object as adding a translational attribute feature to an object prototype. We explicitly take into account of the contextual dependency between attributes and objects by generating translational attribute features conditionally dependent on the object prototypes. Furthermore, we design a ratio variance constraint loss to promote the model's generalization ability on unseen concepts. It regularizes the distances between concepts by utilizing knowledge from their pretrained word embeddings. We evaluate the performance of our model under both the unbiased and biased concept classification tasks, and show that our model is able to achieve good balance in predicting unseen and seen concepts.