GuCNet: A Guided Clustering-based Network for Improved Classification

by   Ushasi Chaudhuri, et al.

We deal with the problem of semantic classification of challenging and highly-cluttered dataset. We present a novel, and yet a very simple classification technique by leveraging the ease of classifiability of any existing well separable dataset for guidance. Since the guide dataset which may or may not have any semantic relationship with the experimental dataset, forms well separable clusters in the feature set, the proposed network tries to embed class-wise features of the challenging dataset to those distinct clusters of the guide set, making them more separable. Depending on the availability, we propose two types of guide sets: one using texture (image) guides and another using prototype vectors representing cluster centers. Experimental results obtained on the challenging benchmark RSSCN, LSUN, and TU-Berlin datasets establish the efficacy of the proposed method as we outperform the existing state-of-the-art techniques by a considerable margin.



There are no comments yet.


page 3

page 4


Classification Recouvrante Basée sur les Méthodes à Noyau

Overlapping clustering problem is an important learning issue in which c...

Learning with partially separable data

There are partially separable data types that make classification tasks ...

DRBM-ClustNet: A Deep Restricted Boltzmann-Kohonen Architecture for Data Clustering

A Bayesian Deep Restricted Boltzmann-Kohonen architecture for data clust...

Progressive Cluster Purification for Transductive Few-shot Learning

Few-shot learning aims to learn to generalize a classifier to novel clas...

Class Specific Feature Selection for Interval Valued Data Through Interval K-Means Clustering

In this paper, a novel feature selection approach for supervised interva...

LSD-C: Linearly Separable Deep Clusters

We present LSD-C, a novel method to identify clusters in an unlabeled da...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.