Published February 23, 2021 | Version v1
Conference paper Open

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

  • 1. Industrial Systems Institute, Computer Engineering and Informatics Dept., University of Patras
  • 2. Industrial Systems Institute


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


2020 - A New Clustering-Based Technique for the Acceleration of Deep Convolutional Networks - International Conference on Machine Learni.pdf

Additional details


CPSoSaware – Cross-layer cognitive optimization tools & methods for the lifecycle support of dependable CPSoS 871738
European Commission