Reference : Comparison of deep transfer learning strategies for digital pathology
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/222511
Comparison of deep transfer learning strategies for digital pathology
English
[fr] Comparaison de stratégies de transfert profond pour la pathologie digitale
Mormont, Romain mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique >]
Geurts, Pierre mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique >]
Marée, Raphaël mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
2018
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
IEEE
Yes
International
3rd Computer Vision for Microscopy Image Analysis (CVMI) workshop at the 2018 IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR)
du 18 juin 2018 au 22 juin 2018
IEEE Computer Society, Computer Vision Foundation
Salt Lake City
USA
[en] deep learning ; transfer learning ; digital pathology ; object recognition
[en] In this paper, we study deep transfer learning as a way of overcoming object recognition challenges encountered in the field of digital pathology. Through several experiments, we investigate various uses of pre-trained neural network architectures and different combination schemes with random forests for feature selection. Our experiments on eight classification datasets show that densely connected and residual networks consistently yield best performances across strategies. It also appears that network fine-tuning and using inner layers features are the best performing strategies, with the former yielding slightly superior results.
Montefiore Institute of Electrical Engineering and Computer Science - Montefiore Institute
http://hdl.handle.net/2268/222511

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
mormont2018-comparison.pdfPublisher postprint2.14 MBView/Open

Additional material(s):

File Commentary Size Access
Open access
mormont2018comparison-supp.pdfSupplementary materials1.98 MBView/Open
Open access
mormont2018comparison-poster.pdfPoster CVMI 20186.13 MBView/Open
Open access
code.zipCode107.58 kBView/Open
Open access
mormont2018comparison-slides.pdfSlides CVMI 20189.89 MBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.