{
  "id": 53986,
  "title": "FYI: MULTICLASS WEIGHTED LOSS FOR INSTANCE SEGMENTATION OF CLUTTERED CELLS",
  "url": "/competitions/data-science-bowl-2018/discussion/53986",
  "author_name": "Morteza Milani",
  "post_date": "2018-04-08T01:02:29.617000",
  "votes": 0,
  "comment_count": 0,
  "views": 0,
  "content": "<p>\" Segmenting individual touching cells in cluttered regions is challenging as the feature distribution on shared borders and cell foreground are similar thus difficulting discriminating pixels into proper classes. We present two novel weight maps applied to the weighted cross entropy loss function which take into account both class imbalance and cell geometry. Binary ground truth training data is augmented so the learning model can handle not only foreground and background but also a third touching class. This framework allows training using U-Net. \"</p>\n\n<p><a href=\"https://arxiv.org/pdf/1802.07465.pdf\">https://arxiv.org/pdf/1802.07465.pdf</a></p>",
  "messages": [
    {
      "id": 310559,
      "postDate": "2018-04-08T01:02:29.617Z",
      "content": "<p>\" Segmenting individual touching cells in cluttered regions is challenging as the feature distribution on shared borders and cell foreground are similar thus difficulting discriminating pixels into proper classes. We present two novel weight maps applied to the weighted cross entropy loss function which take into account both class imbalance and cell geometry. Binary ground truth training data is augmented so the learning model can handle not only foreground and background but also a third touching class. This framework allows training using U-Net. \"</p>\n\n<p><a href=\"https://arxiv.org/pdf/1802.07465.pdf\">https://arxiv.org/pdf/1802.07465.pdf</a></p>",
      "rawMarkdown": "\" Segmenting individual touching cells in cluttered regions is challenging as the feature distribution on shared borders and cell foreground are similar thus difficulting discriminating pixels into proper classes. We present two novel weight maps applied to the weighted cross entropy loss function which take into account both class imbalance and cell geometry. Binary ground truth training data is augmented so the learning model can handle not only foreground and background but also a third touching class. This framework allows training using U-Net. \"\n\nhttps://arxiv.org/pdf/1802.07465.pdf"
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "310559": "\" Segmenting individual touching cells in cluttered regions is challenging as the feature distribution on shared borders and cell foreground are similar thus difficulting discriminating pixels into proper classes. We present two novel weight maps applied to the weighted cross entropy loss function which take into account both class imbalance and cell geometry. Binary ground truth training data is augmented so the learning model can handle not only foreground and background but also a third touching class. This framework allows training using U-Net. \"\n\nhttps://arxiv.org/pdf/1802.07465.pdf"
  }
}