Deep co-training for semi-supervised image segmentation

/in , , /by
Deep co-training for semi-supervised image segmentation

Peng, J and Estrada, G and Pedersoli, M and Desrosiers, C

Pattern Recognition 2020

Abstract : In this paper, we aim to improve the performance of semantic image segmentation in a semi-supervised setting where training is performed with a reduced set of annotated images and additional non-annotated images. We present a method based on an ensemble of deep łdots

You might also like
Pump assembly with electric drive and with mechanical drive comprising transmission means
Real-time correction of closed-captions
Foreground and background information in an HMM-based method for recognition of isolated characters and numeral strings
Pairwise fusion matrix for combining classifiers
Weakly supervised object detection with convex clustering
Une Nouvelle Strat\é\gie pour l’Am\é\lioration des Jeux de Primitives d’un Syst\è\me de Reconnaissance de l’Ecriture
A hybrid multi-objective evolutionary algorithm for the uncapacitated exam proximity problem
Towards robust speech-to-text adversarial attack