2016/12/14 by Kenneth Marino, Ruslan Salakhutdinov, Marino, Kenneth +3 · 11 citations
Computer Science · #Advanced Graph Neural Networks #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Multimodal Machine Learning Applications #cs.CV
paper · pdf · doi:10.48550/arxiv.1612.04844
CVPR 2017
openalex publication_date 2016/12/14 · arxiv created 2017/04/22 · arxiv updated 2017/04/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
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 occur between them to learn a large variety of visual concepts, often 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 performance 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 outperforms standard neural network baselines for multi-label classification.