Where to Prune: Using LSTM to Guide Data-Dependent Soft Pruning

Guiguang Ding, Shuo Zhang, Zizhou Jia, Jing Zhong, Jungong Han

Research output: Contribution to journalArticlepeer-review

25 Citations (SciVal)
184 Downloads (Pure)


While convolutional neural network (CNN) has achieved overwhelming success in various vision tasks, its heavy computational cost and storage overhead limit the practical use on mobile or embedded devices. Recently, compressing CNN models has attracted considerable attention, where pruning CNN filters, also known as the channel pruning, has generated great research popularity due to its high compression rate. In this paper, a new channel pruning framework is proposed, which can significantly reduce the computational complexity while maintaining sufficient model accuracy. Unlike most existing approaches that seek to-be-pruned filters layer by layer, we argue that choosing appropriate layers for pruning is more crucial, which can result in more complexity reduction but less performance drop. To this end, we utilize a long short-term memory (LSTM) to learn the hierarchical characteristics of a network and generate a global network pruning scheme. On top of it, we propose a data-dependent soft pruning method, dubbed Squeeze-Excitation-Pruning (SEP), which does not physically prune any filters but selectively excludes some kernels involved in calculating forward and backward propagations depending on the pruning scheme. Compared with the hard pruning, our soft pruning can better retain the capacity and knowledge of the baseline model. Experimental results demonstrate that our approach still achieves comparable accuracy even when reducing 70.1% Floating-point operation per second (FLOPs) for VGG and 47.5% for Resnet-56.
Original languageEnglish
Article number9258919
Pages (from-to)293 - 304
Number of pages12
JournalIEEE Transactions on Image Processing
Early online date13 Nov 2020
Publication statusPublished - 20 Nov 2020


  • Deep learning
  • computer vision
  • image classification
  • model compression


Dive into the research topics of 'Where to Prune: Using LSTM to Guide Data-Dependent Soft Pruning'. Together they form a unique fingerprint.

Cite this