2017/05/30 by David Rolnick, Yaron Meirovitch, Rolnick, David +13 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · Materials Science · Mathematics · #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Cell Image Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (stat.ML) #Machine Learning in Materials Science #Neurons and Cognition (q-bio.NC) #cs.AI #cs.CV #q-bio.NC #stat.ML
paper · pdf · doi:10.48550/arxiv.1705.10882
13 pages, 6 figures
arxiv created 2017/05/30 · openalex publication_date 2017/05/30 · arxiv updated 2017/06/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Deep learning algorithms for connectomics rely upon localized classification, rather than overall morphology. This leads to a high incidence of erroneously merged objects. Humans, by contrast, can easily detect such errors by acquiring intuition for the correct morphology of objects. Biological neurons have complicated and variable shapes, which are challenging to learn, and merge errors take a multitude of different forms. We present an algorithm, MergeNet, that shows 3D ConvNets can, in fact, detect merge errors from high-level neuronal morphology. MergeNet follows unsupervised training and operates across datasets. We demonstrate the performance of MergeNet both on a variety of connectomics data and on a dataset created from merged MNIST images.