Cited time in webofscience Cited time in scopus

Full metadata record

DC Field Value Language
dc.contributor.author Hong, Seunghoon -
dc.contributor.author Kwak, Su Ha -
dc.contributor.author Han, Bohyung -
dc.date.available 2018-01-11T10:06:00Z -
dc.date.created 2018-01-01 -
dc.date.issued 2017-11 -
dc.identifier.issn 1053-5888 -
dc.identifier.uri http://hdl.handle.net/20.500.11750/4841 -
dc.description.abstract Semantic segmentation is a popular visual recognition task whose goal is to estimate pixel-level object class labels in images. This problem has been recently handled by deep convolutional neural networks (DCNNs), and the state-of-theart techniques achieve impressive records on public benchmark data sets. However, learning DCNNs demand a large number of annotated training data while segmentation annotations in existing data sets are significantly limited in terms of both quantity and diversity due to the heavy annotation cost. Weakly supervised approaches tackle this issue by leveraging weak annotations such as image-level labels and bounding boxes, which are either readily available in existing large-scale data sets for image classification and object detection or easily obtained thanks to their low annotation costs. The main challenge in weakly supervised semantic segmentation then is the incomplete annotations that miss accurate object boundary information required to learn segmentation. This article provides a comprehensive overview of weakly supervised approaches for semantic segmentation. Specifically, we describe how the approaches overcome the limitations and discuss research directions worthy of investigation to improve performance. © 1991-2012 IEEE. -
dc.language English -
dc.publisher Institute of Electrical and Electronics Engineers Inc. -
dc.title Weakly Supervised Learning with Deep Convolutional Neural Networks for Semantic Segmentation Understanding semantic layout of images with minimum human supervision -
dc.type Article -
dc.identifier.doi 10.1109/MSP.2017.2742558 -
dc.identifier.scopusid 2-s2.0-85035079382 -
dc.identifier.bibliographicCitation IEEE Signal Processing Magazine, v.34, no.6, pp.39 - 49 -
dc.description.isOpenAccess FALSE -
dc.citation.endPage 49 -
dc.citation.number 6 -
dc.citation.startPage 39 -
dc.citation.title IEEE Signal Processing Magazine -
dc.citation.volume 34 -
Files in This Item:

There are no files associated with this item.

Appears in Collections:
ETC 1. Journal Articles

qrcode

  • twitter
  • facebook
  • mendeley

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE