Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Bucher, Maxime"'
Publikováno v:
Proceedings of the 2021 International Conference on 3D Vision (3DV 2021), pp. 992-1002
While there has been a number of studies on Zero-Shot Learning (ZSL) for 2D images, its application to 3D data is still recent and scarce, with just a few methods limited to classification. We present the first generative approach for both ZSL and Ge
Externí odkaz:
http://arxiv.org/abs/2108.06230
In this work, we define and address a novel domain adaptation (DA) problem in semantic scene segmentation, where the target domain not only exhibits a data distribution shift w.r.t. the source domain, but also includes novel classes that do not exist
Externí odkaz:
http://arxiv.org/abs/2004.01130
Autor:
Bucher, Maxime
Dans cette thèse nous étudions différentes questions relatives à la mise en pratique de modèles d'apprentissage profond. En effet malgré les avancées prometteuses de ces algorithmes en vision par ordinateur, leur emploi dans certains cas d'usa
Externí odkaz:
http://www.theses.fr/2018NORMC250/document
Semantic segmentation models are limited in their ability to scale to large numbers of object classes. In this paper, we introduce the new task of zero-shot semantic segmentation: learning pixel-wise classifiers for never-seen object categories with
Externí odkaz:
http://arxiv.org/abs/1906.00817
Unsupervised domain adaptation (UDA) is important for applications where large scale annotation of representative data is challenging. For semantic segmentation in particular, it helps deploy on real "target domain" data models that are trained on an
Externí odkaz:
http://arxiv.org/abs/1904.01886
Semantic segmentation is a key problem for many computer vision tasks. While approaches based on convolutional neural networks constantly break new records on different benchmarks, generalizing well to diverse testing environments remains a major cha
Externí odkaz:
http://arxiv.org/abs/1811.12833
Publikováno v:
Asian Conference on Computer Vision (ACCV), Dec 2018, Perth, Australia
This paper introduces a novel method for the representation of images that is semantic by nature, addressing the question of computation intelligibility in computer vision tasks. More specifically, our proposition is to introduce what we call a seman
Externí odkaz:
http://arxiv.org/abs/1811.02234
Publikováno v:
International Conference on Computer Vision (ICCV) Workshops : TASK-CV: Transferring and Adapting Source Knowledge in Computer Vision, Oct 2017, venise, Italy. International Conference on Computer Vision (ICCV) Workshops, 2017
This paper addresses the task of learning an image clas-sifier when some categories are defined by semantic descriptions only (e.g. visual attributes) while the others are defined by exemplar images as well. This task is often referred to as the Zero
Externí odkaz:
http://arxiv.org/abs/1708.06975
Publikováno v:
In Computer Vision and Image Understanding November 2021 212
Publikováno v:
ECCV 16 WS TASK-CV: Transferring and Adapting Source Knowledge in Computer Vision, Oct 2016, Amsterdam, Netherlands. ECCV 16 WS TASK-CV: Transferring and Adapting Source Knowledge in Computer Vision
Zero-Shot learning has been shown to be an efficient strategy for domain adaptation. In this context, this paper builds on the recent work of Bucher et al. [1], which proposed an approach to solve Zero-Shot classification problems (ZSC) by introducin
Externí odkaz:
http://arxiv.org/abs/1608.07441