Timezone: »
An agglomerative clustering algorithm merges the most similar pair of clusters at every iteration. The function that evaluates similarity is traditionally hand- designed, but there has been recent interest in supervised or semisupervised settings in which ground-truth clustered data is available for training. Here we show how to train a similarity function by regarding it as the action-value function of a reinforcement learning problem. We apply this general method to segment images by clustering superpixels, an application that we call Learning to Agglomerate Superpixel Hierarchies (LASH). When applied to a challenging dataset of brain images from serial electron microscopy, LASH dramatically improved segmentation accuracy when clustering supervoxels generated by state of the boundary detection algorithms. The naive strategy of directly training only supervoxel similarities and applying single linkage clustering produced less improvement.
Author Information
Viren Jain (Howard Hughes Medical Institute)
Srinivas C Turaga (HHMI Janelia Research Campus)
K Briggman (MPI)
Moritz N Helmstaedter (Max Planck Institute for Medical Research)
Winfried Denk (Max Planck Institute for Medical Research)
H. Sebastian Seung (Massachusetts Institute of Technology)
More from the Same Authors
-
2016 : Srini Turaga : Independence testing & Amortized inference, with neural networks, for neuroscience »
Srinivas C Turaga -
2013 Workshop: Acquiring and Analyzing the Activity of Large Neural Ensembles »
Srinivas C Turaga · Lars Buesing · Maneesh Sahani · Jakob H Macke -
2013 Poster: Inferring neural population dynamics from multiple partial recordings of the same neural circuit »
Srinivas C Turaga · Lars Buesing · Adam M Packer · Henry Dalgleish · Noah Pettit · Michael Hausser · Jakob H Macke -
2013 Spotlight: Inferring neural population dynamics from multiple partial recordings of the same neural circuit »
Srinivas C Turaga · Lars Buesing · Adam M Packer · Henry Dalgleish · Noah Pettit · Michael Hausser · Jakob H Macke -
2012 Workshop: Connectomics: Opportunities and Challenges for Machine Learning »
Viren Jain · Moritz Helmstaedter -
2009 Poster: Maximin affinity learning of image segmentation »
Srinivas C Turaga · K Briggman · Moritz N Helmstaedter · Winfried Denk · H. Sebastian Seung -
2008 Invited Talk: Connectome: the quest to deconstruct the brain »
H. Sebastian Seung -
2008 Poster: Natural Image Denoising with Convolutional Networks »
Viren Jain · H. Sebastian Seung