53 citations · 126 across the 13 of their papers we have counts for
3 papers · 1 filter
Combining pretrained CNN feature extractors to enhance clustering of complex natural images
Joris Guerin, Stephane Thiery, Eric Nyiri +2
Recently, a common starting point for solving complex unsupervised image classification tasks is to use generic features, extracted with deep Convolutional Neural Networks (CNN) pr…
Automatic Construction of Real-World Datasets for 3D Object Localization using Two Cameras
Joris Guérin, Olivier Gibaru, Eric Nyiri +1
Unlike classification, position labels cannot be assigned manually by humans. For this reason, generating supervision for precise object localization is a hard task. This paper det…
CNN features are also great at unsupervised classification
Joris Guérin, Olivier Gibaru, Stéphane Thiery +1
This paper aims at providing insight on the transferability of deep CNN features to unsupervised problems. We study the impact of different pretrained CNN feature extractors on the…