TY - GEN
T1 - Stability based filter pruning for accelerating deep CNNs
AU - Singh, Pravendra
AU - Kadi, Vinay Sameer Raja
AU - Verma, Nikhil
AU - Namboodiri, Vinay P.
PY - 2019/3/7
Y1 - 2019/3/7
N2 - Convolutional neural networks (CNN) have achieved impressive performance on the wide variety of tasks (classification, detection, etc.) across multiple domains at the cost of high computational and memory requirements. Thus, leveraging CNNs for real-time applications necessitates model compression approaches that not only reduce the total number of parameters but reduce the overall computation as well. In this work, we present a stability-based approach for filter-level pruning of CNNs. We evaluate our proposed approach on different architectures (LeNet, VGG-16, ResNet, and Faster RCNN) and datasets and demonstrate its generalizability through extensive experiments. Moreover, our compressed models can be used at run-time without requiring any special libraries or hardware. Our model compression method reduces the number of FLOPS by an impressive factor of 6.03X and GPU memory footprint by more than 17X, significantly outperforming other state-of-the-art filter pruning methods.
AB - Convolutional neural networks (CNN) have achieved impressive performance on the wide variety of tasks (classification, detection, etc.) across multiple domains at the cost of high computational and memory requirements. Thus, leveraging CNNs for real-time applications necessitates model compression approaches that not only reduce the total number of parameters but reduce the overall computation as well. In this work, we present a stability-based approach for filter-level pruning of CNNs. We evaluate our proposed approach on different architectures (LeNet, VGG-16, ResNet, and Faster RCNN) and datasets and demonstrate its generalizability through extensive experiments. Moreover, our compressed models can be used at run-time without requiring any special libraries or hardware. Our model compression method reduces the number of FLOPS by an impressive factor of 6.03X and GPU memory footprint by more than 17X, significantly outperforming other state-of-the-art filter pruning methods.
UR - http://www.scopus.com/inward/record.url?scp=85063585909&partnerID=8YFLogxK
U2 - 10.1109/WACV.2019.00129
DO - 10.1109/WACV.2019.00129
M3 - Chapter in a published conference proceeding
AN - SCOPUS:85063585909
T3 - Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019
SP - 1166
EP - 1174
BT - Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019
PB - IEEE
T2 - 19th IEEE Winter Conference on Applications of Computer Vision, WACV 2019
Y2 - 7 January 2019 through 11 January 2019
ER -