Scholarlink

<p>Analysis of biological images relies heavily on segmenting the biological objects of interest in the image before performing quantitative analysis. Deep learning (DL) is ubiquitous in such segmentation tasks, but can be cumbersome to apply, as it often requires a large amount of manual labeling to produce ground-truth data, and expert knowledge to train the models. More recently, large foundation models, such as SAM, have shown promising results on scientific images. They, however, require manual prompting for each object or tedious post-processing to selectively segment these objects. Here, we present FeatureForest, a method that leverages the feature embeddings of large foundation models to train a random forest classifier, thereby providing users with a rapid way of semantically segmenting complex images using only a few labeling strokes. We demonstrate the improvement in performance over a variety of datasets and provide an open-source implementation in napari that can be extended to new models.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

FeatureForest: the power of foundation models, the usability of random forests

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月8日

查看全文
  • Mehdi Seifi,
  • Damian Dalle Nogare,
  • Juan Manuel Battagliotti,
  • Vera Galinova,
  • Ananya Kedige Rao,
  • Pierre-Henri Jouneau,
  • Anwai Archit,
  • Fynn Beuttenmueller,
  • Dorothea Dörr,
  • Mariana G. Ferreira,
  • Caterina Fuster-Barceló,
  • Vera Galinova,
  • Carlos García-López-de-Haro,
  • Estibaliz Gómez-de-Mariscal,
  • Matthew Hartley,
  • Ricardo Henriques,
  • Iván Hidalgo-Cenalmor,
  • Florian Jug,
  • Anna Kreshuk,
  • Emma Lundberg,
  • Nils Mechtel,
  • Arrate Muñoz-Barrutia,
  • Wei Ouyang,
  • Constantin Pape,
  • Craig T. Russell,
  • Mehdi Seifi,
  • Beatriz Serrano-Solano,
  • Tomaz Vieira,
  • Teresa Zulueta-Coarasa,
  • Constantin Pape,
  • Johan Decelle,
  • Florian Jug,
  • Joran Deschamps

摘要

Analysis of biological images relies heavily on segmenting the biological objects of interest in the image before performing quantitative analysis. Deep learning (DL) is ubiquitous in such segmentation tasks, but can be cumbersome to apply, as it often requires a large amount of manual labeling to produce ground-truth data, and expert knowledge to train the models. More recently, large foundation models, such as SAM, have shown promising results on scientific images. They, however, require manual prompting for each object or tedious post-processing to selectively segment these objects. Here, we present FeatureForest, a method that leverages the feature embeddings of large foundation models to train a random forest classifier, thereby providing users with a rapid way of semantically segmenting complex images using only a few labeling strokes. We demonstrate the improvement in performance over a variety of datasets and provide an open-source implementation in napari that can be extended to new models.