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
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 : https://airccj.org/CSCP/vol8/csit88308.pdf