Abstract
One characteristic that sets humans apart from modern learning-based computer vision algorithms is the ability to acquire knowledge about the world and use that knowledge to reason about the visual world.Humans can learn about the characteristics of objects and the relationships that oc-cur between them to learn a large variety of visual con-cepts,ofien with few examples.This paper investigates the use of structured prior knowledge in the form of knowledge graphs and shows that using this knowledge improves per-formance on image classification.We build on recent work on end-to-end learning on graphs,introducing the Graph Search Neural Network as a way of efficiently incorporating large knowledge graphs into a vision classification pipeline.We show in a number of experiments that our method out-performs standard neural network baselines for multi-label classification.