# A New Clustering-Based Technique for the Acceleration of Deep Convolutional Networks

Source: [A New Clustering-Based Technique for the Acceleration of Deep Convolutional Networks](<https://www.sota2.com/research/paper/68fa6a5d1e209131cea27b94>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:23:37.152Z

Authors: Erion-Vasilis Pikoulis, Christos Mavrokefalidis, Aris S. Lalos

Published: 2021-07-19T18:22:07.000Z

## Abstract

Deep learning and especially the use of Deep Neural Networks (DNNs) provides impressive results in various regression and classification tasks. However, to achieve these results, there is a high demand for computing and storing resources. This becomes problematic when, for instance, real-time, mobile applications are considered, in which the involved (embedded) devices have limited resources. A common way of addressing this problem is to transform the original large pre-trained networks into new smaller models, by utilizing Model Compression and Acceleration (MCA) techniques. Within the MCA framework, we propose a clustering-based approach that is able to increase the number of employed centroids/representatives, while at the same time, have an acceleration gain compared to conventional, $k$-means based approaches. This is achieved by imposing a special structure to the employed representatives, which is enabled by the particularities of the problem at hand. Moreover, the theoretical acceleration gains are presented and the key system hyper-parameters that affect that gain, are identified. Extensive evaluation studies carried out using various state-of-the-art DNN models trained in image classification, validate the superiority of the proposed method as compared for its use in MCA tasks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2107.09095>)

[PDF](<https://arxiv.org/pdf/2107.09095.pdf>)
