no code implementations • Nature Methods 2017 • Michał Januszewski, Jörgen Kornfeld, Peter H. Li, Art Pope, Tim Blakely, Larry Lindsey, Jeremy Maitin-Shepard, Mike Tyka, Winfried Denk, Viren Jain
Reconstruction of neural circuits from volume electron microscopy data requires the tracing of complete cells including all their neurites.
Electron Microscopy Image Segmentation Image Reconstruction +1
no code implementations • 30 Jun 2017 • Viren Jain
Finally, we show how these two capabilities can be combined in order to produce artificial isotropic volumes from anisotropic image volumes using a super-resolution adversarial alignment and interpolation approach.
4 code implementations • 31 May 2017 • Kisuk Lee, Jonathan Zung, Peter Li, Viren Jain, H. Sebastian Seung
For the past decade, convolutional networks have been used for 3D reconstruction of neurons from electron microscopic (EM) brain images.
no code implementations • 30 May 2017 • David Rolnick, Yaron Meirovitch, Toufiq Parag, Hanspeter Pfister, Viren Jain, Jeff W. Lichtman, Edward S. Boyden, Nir Shavit
Deep learning algorithms for connectomics rely upon localized classification, rather than overall morphology.
3 code implementations • 1 Nov 2016 • Michał Januszewski, Jeremy Maitin-Shepard, Peter Li, Jörgen Kornfeld, Winfried Denk, Viren Jain
State-of-the-art image segmentation algorithms generally consist of at least two successive and distinct computations: a boundary detection process that uses local image information to classify image locations as boundaries between objects, followed by a pixel grouping step such as watershed or connected components that clusters pixels into segments.
no code implementations • NeurIPS 2016 • Jeremy Maitin-Shepard, Viren Jain, Michal Januszewski, Peter Li, Pieter Abbeel
We introduce a new machine learning approach for image segmentation that uses a neural network to model the conditional energy of a segmentation given an image.
no code implementations • 20 Dec 2013 • John A. Bogovic, Gary B. Huang, Viren Jain
For image recognition and labeling tasks, recent results suggest that machine learning methods that rely on manually specified feature representations may be outperformed by methods that automatically derive feature representations based on the data.
no code implementations • 1 Oct 2013 • Gary B. Huang, Viren Jain
Feedforward multilayer networks trained by supervised learning have recently demonstrated state of the art performance on image labeling problems such as boundary prediction and scene parsing.
no code implementations • NeurIPS 2011 • Viren Jain, Srinivas C. Turaga, K Briggman, Moritz N. Helmstaedter, Winfried Denk, H. S. Seung
An agglomerative clustering algorithm merges the most similar pair of clusters at every iteration.
no code implementations • NeurIPS 2008 • Viren Jain, Sebastian Seung
We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedure that synthesizes training samples from specific noise models.