Sökning: onr:"swepub:oai:DiVA.org:his-23236" >
Towards Sim-to-Real...
-
Zhu, XiaomengKTH,Robotik, perception och lärande, RPL,Scania CV AB, Sweden ; KTH Royal Institute of Technology, Sweden
(författare)
Towards Sim-to-Real Industrial Parts Classification with Synthetic Dataset
- Artikel/kapitelEngelska2023
Förlag, utgivningsår, omfång ...
-
IEEE,2023
-
printrdacarrier
Nummerbeteckningar
-
LIBRIS-ID:oai:DiVA.org:his-23236
-
https://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-23236URI
-
https://doi.org/10.1109/CVPRW59228.2023.00468DOI
-
https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-337847URI
Kompletterande språkuppgifter
-
Språk:engelska
-
Sammanfattning på:engelska
Ingår i deldatabas
Klassifikation
-
Ämneskategori:ref swepub-contenttype
-
Ämneskategori:kon swepub-publicationtype
Anmärkningar
-
© 2023 IEEE.This work is partially supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation. The computations were enabled by resources provided by the Swedish National Infrastructure for Computing (SNIC), partially funded by the Swedish Research Council through grant agreement no. 2018-05973, as well as by the Berzelius resource provided by the Knut and Alice Wallenberg Foundation at the National Supercomputer Centre.
-
Part of ISBN 9798350302493QC 20231010
-
This paper is about effectively utilizing synthetic data for training deep neural networks for industrial parts classification, in particular, by taking into account the domain gap against real-world images. To this end, we introduce a synthetic dataset that may serve as a preliminary testbed for the Sim-to-Real challenge; it contains 17 objects of six industrial use cases, including isolated and assembled parts. A few subsets of objects exhibit large similarities in shape and albedo for reflecting challenging cases of industrial parts. All the sample images come with and without random backgrounds and post-processing for evaluating the importance of domain randomization. We call it Synthetic Industrial Parts dataset (SIP-17). We study the usefulness of SIP-17 through benchmarking the performance of five state-of-the-art deep network models, supervised and self-supervised, trained only on the synthetic data while testing them on real data. By analyzing the results, we deduce some insights on the feasibility and challenges of using synthetic data for industrial parts classification and for further developing larger-scale synthetic datasets. Our dataset † and code ‡ are publicly available.
Ämnesord och genrebeteckningar
Biuppslag (personer, institutioner, konferenser, titlar ...)
-
Bilal, TalhaScania CV AB, Sweden,Scania CV AB, Scania Cv Ab
(författare)
-
Mårtensson, PärScania CV AB, Sweden,Scania CV AB, Scania Cv Ab
(författare)
-
Hanson, LarsHögskolan i Skövde,Institutionen för ingenjörsvetenskap,Forskningsmiljön Virtuell produkt- och produktionsutveckling,User Centred Product Design,University of Skövde, University of Skövde(Swepub:his)hano
(författare)
-
Björkman, Mårten,1970-KTH,Robotik, perception och lärande, RPL,KTH Royal Institute of Technology, Sweden(Swepub:kth)u1cs4x4i
(författare)
-
Maki, AtsutoKTH,Robotik, perception och lärande, RPL,KTH Royal Institute of Technology, Sweden(Swepub:kth)u1elx760
(författare)
-
KTHRobotik, perception och lärande, RPL
(creator_code:org_t)
Sammanhörande titlar
-
Ingår i:Proceedings, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops: IEEE, s. 4454-4463, s. 4454-446397983503024939798350302509
-
Ingår i:Proceedings: IEEE, s. 4454-4463, s. 4454-4463
Internetlänk
Hitta via bibliotek
Till lärosätets databas