Show simple item record

dc.contributor.authorSharma, Angira
dc.contributor.authorKhan, Naeemullah
dc.contributor.authorSundaramoorthi, Ganesh
dc.contributor.authorTorr, Philip
dc.date.accessioned2020-11-03T12:59:53Z
dc.date.available2020-11-03T12:59:53Z
dc.date.issued2020-10-28
dc.identifier.urihttp://hdl.handle.net/10754/665792
dc.description.abstractIn this paper we present a novel loss function, called class-agnostic segmentation (CAS) loss. With CAS loss the class descriptors are learned during training of the network. We don't require to define the label of a class a-priori, rather the CAS loss clusters regions with similar appearance together in a weakly-supervised manner. Furthermore, we show that the CAS loss function is sparse, bounded, and robust to class-imbalance. We apply our CAS loss function with fully-convolutional ResNet101 and DeepLab-v3 architectures to the binary segmentation problem of salient object detection. We investigate the performance against the state-of-the-art methods in two settings of low and high-fidelity training data on seven salient object detection datasets. For low-fidelity training data (incorrect class label) class-agnostic segmentation loss outperforms the state-of-the-art methods on salient object detection datasets by staggering margins of around 50%. For high-fidelity training data (correct class labels) class-agnostic segmentation models perform as good as the state-of-the-art approaches while beating the state-of-the-art methods on most datasets. In order to show the utility of the loss function across different domains we also test on general segmentation dataset, where class-agnostic segmentation loss outperforms cross-entropy based loss by huge margins on both region and edge metrics.
dc.publisherarXiv
dc.relation.urlhttps://arxiv.org/pdf/2010.14793
dc.rightsArchived with thanks to arXiv
dc.titleClass-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation
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.departmentVisual Computing Center (VCC)
dc.eprint.versionPre-print
dc.contributor.institutionUniversity of Oxford.
dc.identifier.arxivid2010.14793
kaust.personSundaramoorthi, Ganesh
refterms.dateFOA2020-11-03T13:00:49Z


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
10.77Mb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record