EP 3698286 A4 20201223 - METHOD AND SYSTEM FOR SEMANTIC SEGMENTATION INVOLVING MULTI-TASK CONVOLUTIONAL NEURAL NETWORK
Title (en)
METHOD AND SYSTEM FOR SEMANTIC SEGMENTATION INVOLVING MULTI-TASK CONVOLUTIONAL NEURAL NETWORK
Title (de)
VERFAHREN UND SYSTEM ZUR SEMANTISCHEN SEGMENTIERUNG MIT EINBEZIEHUNG EINES NEURONALEN FALTUNGSNETZES MIT MEHREREN TASKS
Title (fr)
PROCÉDÉ ET SYSTÈME DE SEGMENTATION SÉMANTIQUE CONCERNANT UN RÉSEAU NEURONAL CONVOLUTIF
Publication
Application
Priority
US 2018068172 W 20181231
Abstract (en)
[origin: WO2020142077A1] Methods and systems involving convolutional neural networks as applicable for semantic segmentation, including multi-task convolutional networks employing curriculum based transfer learning, are disclosed herein. In one example embodiment, a method of semantic segmentation involving a convolutional neural network includes training and applying the convolutional neural network. The training of the convolutional neural network includes each of training a semantic segmentation decoder network of the convolutional neural network, generating first feature maps by way of an encoder network of the convolutional neural network, based at least in part upon a dataset received at the encoder network, and training an instance segmentation decoder network of the convolutional neural network based at least in part upon the first feature maps. The applying includes receiving an image, and generating each of a semantic segmentation map and an instance segmentation map in response to the receiving of the image, in a single feedforward pass.
IPC 8 full level
G06N 3/04 (2006.01); G06N 3/08 (2006.01); G06T 1/20 (2006.01); G06T 3/00 (2006.01); G06T 7/11 (2017.01); G06T 7/246 (2017.01)
CPC (source: EP)
G06N 3/045 (2023.01); G06N 3/084 (2013.01); G06T 7/11 (2016.12); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30261 (2013.01)
Citation (search report)
- [I] DUY-KIEN NGUYEN ET AL: "Multi-task Learning of Hierarchical Vision-Language Representation", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 3 December 2018 (2018-12-03), XP080988112
- [A] CIPOLLA ROBERTO ET AL: "Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics", 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, IEEE, 18 June 2018 (2018-06-18), pages 7482 - 7491, XP033473668, DOI: 10.1109/CVPR.2018.00781
- [A] NEVEN DAVY ET AL: "Towards End-to-End Lane Detection: an Instance Segmentation Approach", 2018 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV), IEEE, 26 June 2018 (2018-06-26), pages 286 - 291, XP033423446, DOI: 10.1109/IVS.2018.8500547
- [A] XUE DI-XIU ET AL: "Fully convolutional networks with double-label for esophageal cancer image segmentation by self-transfer learning", PROCEEDINGS OF SPIE; [PROCEEDINGS OF SPIE ISSN 0277-786X VOLUME 10524], SPIE, US, vol. 10420, 21 July 2017 (2017-07-21), pages 104202D - 104202D, XP060092290, ISBN: 978-1-5106-1533-5, DOI: 10.1117/12.2282000
- See references of WO 2020142077A1
Designated contracting state (EPC)
AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
Designated extension state (EPC)
BA ME
DOCDB simple family (publication)
WO 2020142077 A1 20200709; EP 3698286 A1 20200826; EP 3698286 A4 20201223
DOCDB simple family (application)
US 2018068172 W 20181231; EP 18913207 A 20181231