{
  "id": "1511.09209",
  "version": "v1",
  "published": "2015-11-30T09:14:10.000Z",
  "updated": "2015-11-30T09:14:10.000Z",
  "title": "Fine-Grained Classification via Mixture of Deep Convolutional Neural Networks",
  "authors": [
    "ZongYuan Ge",
    "Alex Bewley",
    "Christopher McCool",
    "Ben Upcroft",
    "Peter Corke",
    "Conrad Sanderson"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "We present a novel deep convolutional neural network (DCNN) system for fine-grained image classification, called a mixture of DCNNs (MixDCNN). The fine-grained image classification problem is characterised by large intra-class variations and small inter-class variations. To overcome these problems our proposed MixDCNN system partitions images into K subsets of similar images and learns an expert DCNN for each subset. The output from each of the K DCNNs is combined to form a single classification decision. In contrast to previous techniques, we provide a formulation to perform joint end-to-end training of the K DCNNs simultaneously. Extensive experiments, on three datasets using two network structures (AlexNet and GoogLeNet), show that the proposed MixDCNN system consistently outperforms other methods. It provides a relative improvement of 12.7% and achieves state-of-the-art results on two datasets.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2015-11-30T09:14:10.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "fine-grained classification",
      "novel deep convolutional neural network",
      "fine-grained image classification",
      "mixdcnn system partitions images",
      "small inter-class variations"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable",
      "adsabs": "2015arXiv151109209G"
    }
  }
}