Consensus Subspace Clustering

One significant challenge in the field of supervised deep learning is the lack of large-scale labeled datasets for many problems. In this paper, we propose Consensus Spectral Clustering (CSC), which leverages the strengths of convolutional autoencoders and spectral clustering to provide pseudo label...

Full description

Saved in:
Bibliographic Details
Main Authors: Thom, Nathan, Nguyen, Hung, Hand, Emily M.
Format: Conference Proceeding
Language:English
Subjects:
Area measurement
Autoencoder
Cluster
Clustering methods
Conferences
Data visualization
Deep learning
Noise reduction
Pseudo label
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:One significant challenge in the field of supervised deep learning is the lack of large-scale labeled datasets for many problems. In this paper, we propose Consensus Spectral Clustering (CSC), which leverages the strengths of convolutional autoencoders and spectral clustering to provide pseudo labels for image data. This data can be used as weakly-labeled data for training and evaluating classifiers which require supervision. The primary weaknesses of previous works lies in their inability to isolate the object of interest in an image and cluster similar images together. We address these issues by denoising input images to remove pixels which do not contain data pertinent to the target. Additionally, we introduce a voting method for label selection to improve the clustering results. Our extensive experimentation on several benchmark datasets demonstrates that the proposed CSC method achieves competitive performance with state-of-the-art methods.
ISSN:2375-0197
DOI:10.1109/ICTAI52525.2021.00064