{
  "id": "1610.00824",
  "version": "v1",
  "published": "2016-10-04T02:20:18.000Z",
  "updated": "2016-10-04T02:20:18.000Z",
  "title": "Real Time Fine-Grained Categorization with Accuracy and Interpretability",
  "authors": [
    "Shaoli Huang",
    "Dacheng Tao"
  ],
  "comment": "arXiv admin note: text overlap with arXiv:1512.08086",
  "categories": [
    "cs.CV"
  ],
  "abstract": "A well-designed fine-grained categorization system usually has three contradictory requirements: accuracy (the ability to identify objects among subordinate categories); interpretability (the ability to provide human-understandable explanation of recognition system behavior); and efficiency (the speed of the system). To handle the trade-off between accuracy and interpretability, we propose a novel \"Deeper Part-Stacked CNN\" architecture armed with interpretability by modeling subtle differences between object parts. The proposed architecture consists of a part localization network, a two-stream classification network that simultaneously encodes object-level and part-level cues, and a feature vectors fusion component. Specifically, the part localization network is implemented by exploring a new paradigm for key point localization that first samples a small number of representable pixels and then determine their labels via a convolutional layer followed by a softmax layer. We also use a cropping layer to extract part features and propose a scale mean-max layer for feature fusion learning. Experimentally, our proposed method outperform state-of-the-art approaches both in part localization task and classification task on Caltech-UCSD Birds-200-2011. Moreover, by adopting a set of sharing strategies between the computation of multiple object parts, our single model is fairly efficient running at 32 frames/sec.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2016-10-04T02:20:18.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "real time fine-grained categorization",
      "interpretability",
      "part localization network",
      "fine-grained categorization system",
      "method outperform state-of-the-art approaches"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}