Show simple item record

dc.contributor.authorYu, L
dc.contributor.authorLi, Z
dc.contributor.authorXu, M
dc.contributor.authorGao, Y
dc.contributor.authorLuo, J
dc.contributor.authorZhang, J
dc.date.accessioned2021-11-17T05:15:20Z
dc.date.available2021-11-17T05:15:20Z
dc.date.issued2021
dc.identifier.issn0920-5691
dc.identifier.doi10.1007/s11263-021-01533-0
dc.identifier.urihttp://hdl.handle.net/10072/410180
dc.description.abstractThe Jaccard index, also known as Intersection-over-Union (IoU), is one of the most critical evaluation metrics in image semantic segmentation. However, direct optimization of IoU score is very difficult because the learning objective is neither differentiable nor decomposable. Although some algorithms have been proposed to optimize its surrogates, there is no guarantee provided for the generalization ability. In this paper, we propose a margin calibration method, which can be directly used as a learning objective, for an improved generalization of IoU over the data-distribution, underpinned by a rigid lower bound. This scheme theoretically ensures a better segmentation performance in terms of IoU score. We evaluated the effectiveness of the proposed margin calibration method on seven image datasets, showing substantial improvements in IoU score over other learning objectives using deep segmentation models.
dc.description.peerreviewedYes
dc.languageen
dc.publisherSpringer Science and Business Media LLC
dc.relation.ispartofjournalInternational Journal of Computer Vision
dc.subject.fieldofresearchArtificial intelligence
dc.subject.fieldofresearchImage processing
dc.subject.fieldofresearchcode4602
dc.subject.fieldofresearchcode460306
dc.titleDistribution-Aware Margin Calibration for Semantic Segmentation in Images
dc.typeJournal article
dc.type.descriptionC1 - Articles
dcterms.bibliographicCitationYu, L; Li, Z; Xu, M; Gao, Y; Luo, J; Zhang, J, Distribution-Aware Margin Calibration for Semantic Segmentation in Images, International Journal of Computer Vision, 2021
dc.date.updated2021-11-16T21:59:20Z
gro.description.notepublicThis publication has been entered in Griffith Research Online as an advanced online version.
gro.hasfulltextNo Full Text
gro.griffith.authorGao, Yongsheng
gro.griffith.authorYu, Litao


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record