{
  "id": "1612.04844",
  "version": "v1",
  "published": "2016-12-14T21:18:30.000Z",
  "updated": "2016-12-14T21:18:30.000Z",
  "title": "The More You Know: Using Knowledge Graphs for Image Classification",
  "authors": [
    "Kenneth Marino",
    "Ruslan Salakhutdinov",
    "Abhinav Gupta"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "Humans have the remarkable capability to learn a large variety of visual concepts, often with very few examples, whereas current state-of-the-art vision algorithms require hundreds or thousands of examples per category and struggle with ambiguity. One characteristic that sets humans apart is our ability to acquire knowledge about the world and reason using this knowledge. 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. Specifically, we introduce the Graph Search Neural Network as a way of efficiently incorporating large knowledge graphs into a fully end-to-end learning system. We show in a number of experiments that our method outperforms baselines for multi-label classification, even under low data and few-shot settings.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2016-12-14T21:18:30.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "image classification",
      "current state-of-the-art vision algorithms",
      "graph search neural network",
      "sets humans apart",
      "efficiently incorporating large knowledge graphs"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}