GuCNet: A Guided Clustering-based Network for Improved Classification

TL;DR

GuCNet introduces a simple yet effective clustering-guided classification approach that leverages well-separated guide datasets to improve semantic classification accuracy on challenging, cluttered datasets.

Contribution

The paper proposes a novel clustering-based network that uses guide datasets, either texture-based or prototype-based, to enhance class separability in difficult classification tasks.

Findings

Outperforms state-of-the-art methods on RSSCN, LSUN, TU-Berlin datasets.

Effectively improves class separability in cluttered datasets.

Demonstrates robustness across different types of guide sets.

Abstract

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.