GuCNet: A Guided Clustering-based Network for Improved Classification
This addresses classification challenges in cluttered datasets, offering a novel guidance approach that is incremental in leveraging existing separable data.
The paper tackles the problem of semantic classification on challenging, cluttered datasets by using a guide dataset to improve feature separability, achieving state-of-the-art results on RSSCN, LSUN, and TU-Berlin benchmarks with a considerable performance margin.
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.