Show simple item record

dc.contributor.authorKhan, Naeemullah
dc.contributor.authorSharma, Angira
dc.contributor.authorSundaramoorthi, Ganesh
dc.contributor.authorTorr, Philip H. S.
dc.date.accessioned2021-02-24T12:27:30Z
dc.date.available2021-02-24T12:27:30Z
dc.date.issued2021-02-16
dc.identifier.urihttp://hdl.handle.net/10754/667663
dc.description.abstractWe present Shape-Tailored Deep Neural Networks (ST-DNN). ST-DNN extend convolutional networks (CNN), which aggregate data from fixed shape (square) neighborhoods, to compute descriptors defined on arbitrarily shaped regions. This is natural for segmentation, where descriptors should describe regions (e.g., of objects) that have diverse shape. We formulate these descriptors through the Poisson partial differential equation (PDE), which can be used to generalize convolution to arbitrary regions. We stack multiple PDE layers to generalize a deep CNN to arbitrary regions, and apply it to segmentation. We show that ST-DNN are covariant to translations and rotations and robust to domain deformations, natural for segmentation, which existing CNN based methods lack. ST-DNN are 3-4 orders of magnitude smaller then CNNs used for segmentation. We show that they exceed segmentation performance compared to state-of-the-art CNN-based descriptors using 2-3 orders smaller training sets on the texture segmentation problem.
dc.publisherarXiv
dc.relation.urlhttps://arxiv.org/pdf/2102.08497.pdf
dc.rightsArchived with thanks to arXiv
dc.titleShape-Tailored Deep Neural Networks
dc.typePreprint
dc.contributor.departmentComputational Vision Lab
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentElectrical Engineering Program
dc.contributor.departmentPhysical Science and Engineering (PSE) Division
dc.contributor.departmentVisual Computing Center (VCC)
dc.eprint.versionPre-print
dc.identifier.arxivid2102.08497
kaust.personSundaramoorthi, Ganesh
refterms.dateFOA2021-02-24T12:29:34Z


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
30.96Mb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record