{
  "id": "2011.02719",
  "version": "v1",
  "published": "2020-11-05T09:24:33.000Z",
  "updated": "2020-11-05T09:24:33.000Z",
  "title": "Few-Shot Object Detection in Real Life: Case Study on Auto-Harvest",
  "authors": [
    "Kevin Riou",
    "Jingwen Zhu",
    "Suiyi Ling",
    "Mathis Piquet",
    "Vincent Truffault",
    "Patrick Le Callet"
  ],
  "comment": "6 pages",
  "categories": [
    "cs.CV",
    "cs.LG"
  ],
  "abstract": "Confinement during COVID-19 has caused serious effects on agriculture all over the world. As one of the efficient solutions, mechanical harvest/auto-harvest that is based on object detection and robotic harvester becomes an urgent need. Within the auto-harvest system, robust few-shot object detection model is one of the bottlenecks, since the system is required to deal with new vegetable/fruit categories and the collection of large-scale annotated datasets for all the novel categories is expensive. There are many few-shot object detection models that were developed by the community. Yet whether they could be employed directly for real life agricultural applications is still questionable, as there is a context-gap between the commonly used training datasets and the images collected in real life agricultural scenarios. To this end, in this study, we present a novel cucumber dataset and propose two data augmentation strategies that help to bridge the context-gap. Experimental results show that 1) the state-of-the-art few-shot object detection model performs poorly on the novel `cucumber' category; and 2) the proposed augmentation strategies outperform the commonly used ones.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-11-05T09:24:33.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "case study",
      "real life agricultural",
      "robust few-shot object detection model",
      "auto-harvest",
      "state-of-the-art few-shot object detection model"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 6,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}