Journal
NEUROCOMPUTING
Volume 423, Issue -, Pages 551-571Publisher
ELSEVIER
DOI: 10.1016/j.neucom.2020.10.068
Keywords
Image clustering; Transfer clustering; Multi-View clustering
Categories
Funding
- Fulbright Haut-de-France Scholarship
- Fondation Arts et Metiers [8130-01]
- European Union [688807]
Ask authors/readers for more resources
This paper investigates the use of pretrained CNN features for image clustering and finds that the choice of CNN architecture for feature extraction significantly impacts the final clustering results. It proposes a method to reframe the IC problem as an MVC problem and presents a multi-input neural network architecture to effectively solve this problem, achieving state-of-the-art results for IC on nine natural image datasets.
Recently, a common starting point for solving complex unsupervised image classification tasks is to use generic features, extracted with deep Convolutional Neural Networks (CNN) pretrained on a large and versatile dataset (ImageNet). However, in most research, the CNN architecture for feature extraction is chosen arbitrarily, without justification. This paper aims at providing insight on the use of pretrained CNN features for image clustering (IC). First, extensive experiments are conducted and show that, for a given dataset, the choice of the CNN architecture for feature extraction has a huge impact on the final clustering. These experiments also demonstrate that proper extractor selection for a given IC task is difficult. To solve this issue, we propose to rephrase the IC problem as a multi-view clustering (MVC) problem that considers features extracted from different architectures as different views of the same data. This approach is based on the assumption that information contained in the different CNN may be complementary, even when pretrained on the same data. We then propose a multi-input neural network architecture that is trained end-to-end to solve the MVC problem effectively. This approach is tested on nine natural image datasets, and produces state-of-the-art results for IC. (c) 2020 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available