Výsledky vyhledávání - "Gutierrez, Pierre"

Report

Improving generalization with synthetic training data for deep learning based quality inspection

Autor: Cordier, Antoine, Gutierrez, Pierre, Plessis, Victoire

Automating quality inspection with computer vision techniques is often a very data-demanding task. Specifically, supervised deep learning requires a large amount of annotated images for training. In practice, collecting and annotating such data is no

Externí odkaz: http://arxiv.org/abs/2202.12818

Zobrazit plný text záznamu

Report

Data refinement for fully unsupervised visual inspection using pre-trained networks

Autor: Cordier, Antoine, Missaoui, Benjamin, Gutierrez, Pierre

Anomaly detection has recently seen great progress in the field of visual inspection. More specifically, the use of classical outlier detection techniques on features extracted by deep pre-trained neural networks have been shown to deliver remarkable

Externí odkaz: http://arxiv.org/abs/2202.12759

Zobrazit plný text záznamu

Report

Data augmentation and pre-trained networks for extremely low data regimes unsupervised visual inspection

Autor: Gutierrez, Pierre, Cordier, Antoine, Caldeira, Thaïs, Sautory, Théophile

The use of deep features coming from pre-trained neural networks for unsupervised anomaly detection purposes has recently gathered momentum in the computer vision field. In particular, industrial inspection applications can take advantage of such fea

Externí odkaz: http://arxiv.org/abs/2106.01277

Zobrazit plný text záznamu

Report

Active learning using weakly supervised signals for quality inspection

Autor: Cordier, Antoine, Das, Deepan, Gutierrez, Pierre

Because manufacturing processes evolve fast, and since production visual aspect can vary significantly on a daily basis, the ability to rapidly update machine vision based inspection systems is paramount. Unfortunately, supervised learning of convolu

Externí odkaz: http://arxiv.org/abs/2104.02973

Zobrazit plný text záznamu

Report

Synthetic training data generation for deep learning based quality inspection

Autor: Gutierrez, Pierre, Luschkova, Maria, Cordier, Antoine, Shukor, Mustafa, Schappert, Mona, Dahmen, Tim

Deep learning is now the gold standard in computer vision-based quality inspection systems. In order to detect defects, supervised learning is often utilized, but necessitates a large amount of annotated images, which can be costly: collecting, clean

Externí odkaz: http://arxiv.org/abs/2104.02980

Zobrazit plný text záznamu

Report

Dataiku's Solution to SPHERE's Activity Recognition Challenge

Autor: Voisin, Maxime, Dreyfus-Schmidt, Leo, Gutierrez, Pierre, Ronsin, Samuel, Beillevaire, Marc

Our team won the second prize of the Safe Aging with SPHERE Challenge organized by SPHERE, in conjunction with ECML-PKDD and Driven Data. The goal of the competition was to recognize activities performed by humans, using sensor data. This paper prese

Externí odkaz: http://arxiv.org/abs/1610.02757

Zobrazit plný text záznamu

Report

Fast tree inference with weighted fusion penalties

Autor: Chiquet, Julien, Gutierrez, Pierre, Rigaill, Guillem

Given a data set with many features observed in a large number of conditions, it is desirable to fuse and aggregate conditions which are similar to ease the interpretation and extract the main characteristics of the data. This paper presents a multid

Externí odkaz: http://arxiv.org/abs/1407.5915

Zobrazit plný text záznamu

Akademický článek

Fast Tree Inference With Weighted Fusion Penalties

Autor: Chiquet, Julien, Gutierrez, Pierre, Rigaill, Guillem

Publikováno v: Journal of Computational and Graphical Statistics, 2017 Mar 01. 26(1), 205-216.

Externí odkaz: https://www.jstor.org/stable/44861944

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání