CNN Features are also Great at Unsupervised Classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

CNN Features are also Great at Unsupervised Classification

Résumé

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 problem of image set clustering for object classification as well as fine-grained classification. We propose a rather straightforward pipeline combining deep-feature extraction using a CNN pretrained on ImageNet and a classic clustering algorithm to classify sets of images. This approach is compared to state-of-the-art algorithms in image-clustering and provides better results. These results strengthen the belief that supervised training of deep CNN on large datasets, with a large variability of classes, extracts better features than most carefully designed engineering approaches, even for unsupervised tasks. We also validate our approach on a robotic application, consisting in sorting and storing objects smartly based on clustering.

Dates et versions

hal-03153610 , version 1 (26-02-2021)

Identifiants

Citer

Joris Guérin, Olivier Gibaru, Stéphane Thiery, Eric Nyiri. CNN Features are also Great at Unsupervised Classification. 8th International Conference on Computer Science, Engineering and Applications, Feb 2018, Melbourne, Australia. pp.83-95, ⟨10.5121/csit.2018.80308⟩. ⟨hal-03153610⟩
59 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More