Yayın:
Image Colorization by Capsule Networks

Basit öğe sayfası
dc.contributor.authorOzbulak, Gokhan
dc.date.accessioned2026-01-26T04:47:05Z
dc.date.issued2019-06-01
dc.description.abstractIn this paper, a simple topology of Capsule Network (CapsNet) is investigated for the problem of image colorization. The generative and segmentation capabilities of the original CapsNet topology, which is proposed for image classification problem, is leveraged for the colorization of the images by modifying the network as follows:1) The original CapsNet model is adapted to map the grayscale input to the output in the CIE Lab colorspace, 2) The feature detector part of the model is updated by using deeper feature layers inherited from VGG-19 pre-trained model with weights in order to transfer low-level image representation capability to this model, 3) The margin loss function is modified as Mean Squared Error (MSE) loss to minimize the image-to-imagemapping. The resulting CapsNet model is named as Colorizer Capsule Network (ColorCapsNet).The performance of the ColorCapsNet is evaluated on the DIV2K dataset and promising results are obtained to investigate Capsule Networks further for image colorization problem.
dc.description.abstractAccepted to New Trends in Image Restoration and Enhancement(NTIRE) Workshop at CVPR 2019
dc.description.urihttps://doi.org/10.1109/cvprw.2019.00268
dc.description.urihttp://arxiv.org/pdf/1908.08307
dc.description.urihttps://dx.doi.org/10.48550/arxiv.1908.08307
dc.description.urihttp://arxiv.org/abs/1908.08307
dc.description.urihttps://doi.org/10.1109/CVPRW.2019.00268
dc.description.urihttps://dx.doi.org/10.1109/cvprw.2019.00268
dc.description.urihttps://aperta.ulakbim.gov.tr/record/99787
dc.identifier.doi10.1109/cvprw.2019.00268
dc.identifier.endpage2158
dc.identifier.openairedoi_dedup___::e402511d72ff6f3ba4199b5da19421ff
dc.identifier.startpage2150
dc.identifier.urihttps://hdl.handle.net/11527/61265
dc.publisherIEEE
dc.relation.ispartof2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
dc.rightsOPEN
dc.subjectFOS: Computer and information sciences
dc.subjectComputer Vision and Pattern Recognition (cs.CV)
dc.subjectImage and Video Processing (eess.IV)
dc.subjectComputer Science - Computer Vision and Pattern Recognition
dc.subjectFOS: Electrical engineering, electronic engineering, information engineering
dc.subjectElectrical Engineering and Systems Science - Image and Video Processing
dc.titleImage Colorization by Capsule Networks
dc.typeArticle
dspace.entity.typePublication

Dosyalar

Koleksiyonlar

Yayınlar