TY - JOUR
T1 - An error detection and correction framework for connectomics
AU - Zung, Jonathan
AU - Tartavull, Ignacio
AU - Lee, Kisuk
AU - Seung, Hyunjune Sebastian
N1 - Funding Information:
We acknowledge NVIDIA Corporation for providing us with early access to Titan X Pascal GPU used in this research, and Amazon for assistance through an AWS Research Grant. This research was supported by the Mathers Foundation, the Samsung Scholarship and the Intelligence Advanced Research Projects Activity (IARPA) via Department of Interior/ Interior Business Center (DoI/IBC) contract number D16PC0005. The U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon. Disclaimer: The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of IARPA, DoI/IBC, or the U.S. Government.
PY - 2017
Y1 - 2017
N2 - We define and study error detection and correction tasks that are useful for 3D reconstruction of neurons from electron microscopic imagery, and for image segmentation more generally. Both tasks take as input the raw image and a binary mask representing a candidate object. For the error detection task, the desired output is a map of split and merge errors in the object. For the error correction task, the desired output is the true object. We call this object mask pruning, because the candidate object mask is assumed to be a superset of the true object. We train multiscale 3D convolutional networks to perform both tasks. We find that the error-detecting net can achieve high accuracy. The accuracy of the error-correcting net is enhanced if its input object mask is "advice" (union of erroneous objects) from the error-detecting net.
AB - We define and study error detection and correction tasks that are useful for 3D reconstruction of neurons from electron microscopic imagery, and for image segmentation more generally. Both tasks take as input the raw image and a binary mask representing a candidate object. For the error detection task, the desired output is a map of split and merge errors in the object. For the error correction task, the desired output is the true object. We call this object mask pruning, because the candidate object mask is assumed to be a superset of the true object. We train multiscale 3D convolutional networks to perform both tasks. We find that the error-detecting net can achieve high accuracy. The accuracy of the error-correcting net is enhanced if its input object mask is "advice" (union of erroneous objects) from the error-detecting net.
UR - http://www.scopus.com/inward/record.url?scp=85047002534&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85047002534&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85047002534
VL - 2017-December
SP - 6819
EP - 6830
JO - Advances in Neural Information Processing Systems
JF - Advances in Neural Information Processing Systems
SN - 1049-5258
T2 - 31st Annual Conference on Neural Information Processing Systems, NIPS 2017
Y2 - 4 December 2017 through 9 December 2017
ER -