MIT Libraries homeMIT Libraries logoDSpace@MIT

MIT
View Item 
  • DSpace@MIT Home
  • Center for Brains, Minds & Machines
  • Publications
  • CBMM Memo Series
  • View Item
  • DSpace@MIT Home
  • Center for Brains, Minds & Machines
  • Publications
  • CBMM Memo Series
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Do Neural Networks for Segmentation Understand Insideness?

Author(s)
Villalobos, Kimberly; Štih, Vilim; Ahmadinejad, Amineh; Sundaram, Shobhita; Dozier, Jamell; Francl, Andrew; Azevedo, Frederico; Sasaki, Tomotake; Boix, Xavier; ... Show more Show less
Thumbnail
DownloadCBMM-Memo-105.pdf (4.625Mb)
Additional downloads
CBMM-Memo-105v2.pdf (3.195Mb)
CBMM-Memo-105 v3.pdf (8.328Mb)
Metadata
Show full item record
Abstract
The insideness problem is an image segmentation modality that consists of determining which pixels are inside and outside a region. Deep Neural Networks (DNNs) excel in segmentation benchmarks, but it is unclear that they have the ability to solve the insideness problem as it requires evaluating long-range spatial dependencies. In this paper, the insideness problem is analyzed in isolation, without texture or semantic cues, such that other aspects of segmentation do not interfere in the analysis. We demonstrate that DNNs for segmentation with few units have sufficient complexity to solve insideness for any curve. Yet, such DNNs have severe problems to learn general solutions. Only recurrent networks trained with small images learn solutions that generalize well to almost any curve. Recurrent networks can decompose the evaluation of long-range dependencies into a sequence of local operations, and learning with small images alleviates the common difficulties of training recurrent networks with a large number of unrolling steps.
Date issued
2020-04-04
URI
https://hdl.handle.net/1721.1/124491
Publisher
Center for Brains, Minds and Machines (CBMM)
Series/Report no.
CBMM Memo;105

Collections
  • CBMM Memo Series

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries homeMIT Libraries logo

Find us on

Twitter Facebook Instagram YouTube RSS

MIT Libraries navigation

SearchHours & locationsBorrow & requestResearch supportAbout us
PrivacyPermissionsAccessibility
MIT
Massachusetts Institute of Technology
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.