Similarity-Based Clustering for Enhancing Image Classification Architectures

TL;DR

This paper proposes a similarity-based clustering approach that enhances image classification architectures by integrating content-based image similarity with deep learning, leading to reduced computational costs and faster model evaluation.

Contribution

It introduces a novel clustering method that combines content-based similarity with deep learning models to improve training efficiency and performance in image classification.

Findings

Clustering reduces computational costs.

Faster evaluation and tuning of models.

Improved classification performance.

Abstract

Convolutional networks are at the center of best-in-class computer vision applications for a wide assortment of undertakings. Since 2014, a profound amount of work began to make better convolutional architectures, yielding generous additions in different benchmarks. Albeit expanded model size and computational cost will, in general, mean prompt quality increases for most undertakings but, the architectures now need to have some additional information to increase the performance. I show evidence that with the amalgamation of content-based image similarity and deep learning models, we can provide the flow of information which can be used in making clustered learning possible. The paper shows how training of sub-dataset clusters not only reduces the cost of computation but also increases the speed of evaluating and tuning a model on the given dataset.