Improving Image Clustering With Multiple Pretrained CNN Feature Extractors

07/20/2018
by   Joris Guérin, et al.
0

For many image clustering problems, replacing raw image data with features extracted by a pretrained convolutional neural network (CNN), leads to better clustering performance. However, the specific features extracted, and, by extension, the selected CNN architecture, can have a major impact on the clustering results. In practice, this crucial design choice is often decided arbitrarily due to the impossibility of using cross-validation with unsupervised learning problems. However, information contained in the different pretrained CNN architectures may be complementary, even when pretrained on the same data. To improve clustering performance, we rephrase the image clustering problem as a multi-view clustering (MVC) problem that considers multiple different pretrained feature extractors as different "views" of the same data. We then propose a multi-input neural network architecture that is trained end-to-end to solve the MVC problem effectively. Our experimental results, conducted on three different natural image datasets, show that: 1. using multiple pretrained CNNs jointly as feature extractors improves image clustering; 2. using an end-to-end approach improves MVC; and 3. combining both produces state-of-the-art results for the problem of image clustering.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/07/2021

Combining pretrained CNN feature extractors to enhance clustering of complex natural images

Recently, a common starting point for solving complex unsupervised image...
research
07/06/2017

CNN features are also great at unsupervised classification

This paper aims at providing insight on the transferability of deep CNN ...
research
08/19/2018

Deep Multi-View Clustering via Multiple Embedding

Exploring the information among multiple views usually leads to more pro...
research
10/21/2019

Improving Vehicle Re-Identification using CNN Latent Spaces: Metrics Comparison and Track-to-track Extension

This paper addresses the problem of vehicle re-identification using dist...
research
06/04/2019

Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition

View based strategies for 3D object recognition have proven to be very s...
research
05/19/2017

CNN-Based Joint Clustering and Representation Learning with Feature Drift Compensation for Large-Scale Image Data

Given a large unlabeled set of images, how to efficiently and effectivel...
research
03/24/2023

Image Deblurring by Exploring In-depth Properties of Transformer

Image deblurring continues to achieve impressive performance with the de...

Please sign up or login with your details

Forgot password? Click here to reset