D
Damien Muselet
Researcher at University of Lyon
Publications - 69
Citations - 1112
Damien Muselet is an academic researcher from University of Lyon. The author has contributed to research in topics: Pixel & Color image. The author has an hindex of 15, co-authored 65 publications receiving 988 citations. Previous affiliations of Damien Muselet include Jean Monnet University & university of lille.
Papers
More filters
Proceedings ArticleDOI
Landmarks-based kernelized subspace alignment for unsupervised domain adaptation
TL;DR: A novel unsupervised DA approach based on both subspace alignment and selection of landmarks similarly distributed between the two domains is introduced, showing that this new method outperforms the most recent un supervised DA approaches.
Proceedings ArticleDOI
Discriminative Color Descriptors
Rahat Khan,Joost van de Weijer,Fahad Shahbaz Khan,Damien Muselet,Christophe Ducottet,Cécile Barat +5 more
TL;DR: This paper cluster color values together based on their discriminative power in a classification problem, and shows that the proposed descriptor outperforms existing photometric invariants and combined with shape description these color descriptors obtain excellent results on four challenging datasets.
Proceedings ArticleDOI
Residual Conv-Deconv Grid Network for Semantic Segmentation.
TL;DR: GridNet as mentioned in this paper follows a grid pattern allowing multiple interconnected streams to work at different resolutions for semantic image segmentation, which is trained from scratch and achieves competitive results on the Cityscapes dataset.
Proceedings ArticleDOI
Discriminative feature fusion for image classification
TL;DR: This paper presents a new logistic regression-based fusion method, called LRFF, which takes advantage of the different cues without being tied to any of them, and designs a new marginalized kernel by making use of the output of the regression model.
Posted Content
Residual Conv-Deconv Grid Network for Semantic Segmentation
TL;DR: The GridNet is a new Convolutional Neural Network architecture for semantic image segmentation that generalizes many well known networks such as conv-deconv, residual or U-Net networks and achieves competitive results on the Cityscapes dataset.