Výsledky vyhledávání - "Nicolas Hueber"

Self-supervised learning for autonomous vehicles perception: A conciliation between analytical and learning methods

Autor: Nicolas Hueber, Mohamed-Cherif Rahal, Florent Chiaroni, Frederic Dufaux

Publikováno v: IEEE Signal Processing Magazine
IEEE Signal Processing Magazine, Institute of Electrical and Electronics Engineers, 2021, 38 (1), pp.31-41. ⟨10.1109/MSP.2020.2977269⟩

Nowadays, supervised deep learning techniques yield the best state-of-the-art prediction performances for a wide variety of computer vision tasks. However, such supervised techniques generally require a large amount of manually labeled training data.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a01f7b1f52025bdc57181dff9b99fe81
https://hal.archives-ouvertes.fr/hal-02302705

Zobrazit plný text záznamu

Novelty Detection in Images Using Vector Quantization with Topological Learning

Autor: Nicolas Hueber, Bernard Girau, Yann Bernard

Publikováno v: ICECS
ICECS 2020, 27th IEEE International Conference on Electronics Circuits and Systems
ICECS 2020, 27th IEEE International Conference on Electronics Circuits and Systems, Nov 2020, Glasgow/Virtual, United Kingdom

International audience; Novelty detection is a key component of biological vision systems, where its role is to extract critical elements for the agents survival from the massive amount of information present in his visual environment. Current vision

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a47a4936a3fd283aedba58207a0f7b70
https://doi.org/10.1109/icecs49266.2020.9294957

Zobrazit plný text záznamu

A fast algorithm to find Best Matching Units in Self-Organizing Maps

Autor: Nicolas Hueber, Yann Bernard, Bernard Girau

Publikováno v: ICANN 2020, 29th International Conference on Artificial Neural Networks
ICANN 2020, 29th International Conference on Artificial Neural Networks, Sep 2020, Bratislava, Slovakia
Artificial Neural Networks and Machine Learning – ICANN 2020 ISBN: 9783030616151
ICANN (2)

International audience; Self-Organizing Maps (SOM) are well-known unsupervised neural networks able to perform vector quantization while mapping an underlying regular neighbourhood structure onto the codebook. They are used in a wide range of applica

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e71d16f86ee6f9de69d4fcbfc4aa5aa8
https://hal.univ-lorraine.fr/hal-02984424/document

Zobrazit plný text záznamu

Generating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image Classification

Autor: Florent Chiaroni, Frederic Dufaux, Ghazaleh Khodabandelou, Mohamed-Cherif Rahal, Nicolas Hueber

Publikováno v: Web of Science
Pattern Recognition
Pattern Recognition, Elsevier, 2020, 107, pp.107527. ⟨10.1016/j.patcog.2020.107527⟩
Pattern Recognition, Elsevier, 2020, (in press), ⟨10.1016/j.patcog.2020.107527⟩

With surge of available but unlabeled data, Positive Unlabeled (PU) learning is becoming a thriving challenge. This work deals with this demanding task for which recent GAN-based PU approaches have demonstrated promising results. Generative adversari

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::24761fc6031a62bfa73e672a744f1aff
http://arxiv.org/abs/1910.01968

Zobrazit plný text záznamu

Hallucinating A Cleanly Labeled Augmented Dataset from A Noisy Labeled Dataset Using GAN

Autor: Nicolas Hueber, Frederic Dufaux, Florent Chiaroni, M-C. Rahal

Publikováno v: ICIP

Noisy labeled learning methods deal with training datasets containing corrupted labels. However, prediction performances of existing methods on small datasets still leave room for improvements. With this objective, in this paper we present a GAN-base

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::5cc356ca371b747e66cc9b9199d9e68c
https://doi.org/10.1109/icip.2019.8803632

Zobrazit plný text záznamu

Novelty Detection with Self-Organizing Maps for Autonomous Extraction of Salient Tracking Features

Autor: Nicolas Hueber, Bernard Girau, Yann Bernard

Publikováno v: Advances in Intelligent Systems and Computing ISBN: 9783030196417
WSOM
13th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization
13th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization, Jun 2019, Barcelona, Spain. ⟨10.1007/978-3-030-19642-4_10⟩

International audience; In the image processing field, many tracking algorithms rely on prior knowledge like color, shape or even need a database of the objects to be tracked. This may be a problem for some real world applications that cannot fill th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ee1531ba0ad3c0076cb206b190de0b80
https://doi.org/10.1007/978-3-030-19642-4_10

Zobrazit plný text záznamu

Bio-Inspired Perception Sensor (BIPS) Concept Analysis for Embedded Applications

Autor: Nicolas Hueber, Antoine Manzanera, Louise Sarrabezolles

Publikováno v: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications ISBN: 9783030134686
CIARP
The 23rd Iberoamerican Congress on Pattern Recognition (CIARP 2018)
The 23rd Iberoamerican Congress on Pattern Recognition (CIARP 2018), Nov 2018, Madrid, Spain

International audience; The Bio-inspired Perception Sensor (BIPS) component is a small and low power bio-inspired on-chip device which has been used in different computer vision applications (traffic analysis, driving assistance , object tracking). I

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a744be2e0e7d4b27a3e7ff801bf7e26c
https://doi.org/10.1007/978-3-030-13469-3_50

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání