Multi-layer pruning framework for compressing Single Shot MultiBox detector

Pravendra Singh, R. Manikandan, Neeraj Matiyali, Vinay P. Namboodiri

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)
1 Downloads (Pure)

Abstract

We propose a framework for compressing state-of-the-art Single Shot MultiBox Detector (SSD). The framework addresses compression in the following stages: Sparsity Induction, Filter Selection, and Filter Pruning. In the Sparsity Induction stage, the object detector model is sparsified via an improved global threshold. In Filter Selection & Pruning stage, we select and remove filters using sparsity statistics of filter weights in two consecutive convolutional layers. This results in the model with the size smaller than most existing compact architectures. We evaluate the performance of our framework with multiple datasets and compare over multiple methods. Experimental results show that our method achieves state-of-the-art compression of 6.7X and 4.9X on PASCAL VOC dataset on models SSD300 and SSD512 respectively. We further show that the method produces maximum compression of 26X with SSD512 on German Traffic Sign Detection Benchmark (GTSDB). Additionally, we also empirically show our method’s adaptability for classification based architecture VGG16 on datasets CIFAR and German Traffic Sign Recognition Benchmark (GTSRB) achieving a compression rate of 125X and 200X with the reduction in flops by 90.50% and 96.6% respectively with no loss of accuracy. In addition to this, our method does not require any special libraries or hardware support for the resulting compressed models.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019
PublisherIEEE
Pages1318-1327
Number of pages10
ISBN (Electronic)9781728119755
DOIs
Publication statusPublished - 7 Mar 2019
Event19th IEEE Winter Conference on Applications of Computer Vision, WACV 2019 - Waikoloa Village, USA United States
Duration: 7 Jan 201911 Jan 2019

Publication series

NameProceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019

Conference

Conference19th IEEE Winter Conference on Applications of Computer Vision, WACV 2019
CountryUSA United States
CityWaikoloa Village
Period7/01/1911/01/19

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Multi-layer pruning framework for compressing Single Shot MultiBox detector'. Together they form a unique fingerprint.

Cite this