Monday, August 31, 2020


 Author :  Joris Guérin

Affiliation :  Laboratoire des Sciences de l'Information et des Systèmes (CNRS UMR 7296) Arts et Métiers ParisTech

Country :  France

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  8, 3, February, 2018

Abstract :

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.

Keyword :  Transfer learning, Image clustering, Robotics application

For More Details

No comments:

Post a Comment