Timezone: »
In this paper, we propose a deep reinforcement learning (DRL) based framework to efficiently perform runtime channel pruning on convolutional neural networks (CNNs). Our DRL-based framework aims to learn a pruning strategy to determine how many and which channels to be pruned in each convolutional layer, depending on each individual input instance at runtime. Unlike existing runtime pruning methods which require to store all channels parameters for inference, our framework can reduce parameters storage consumption by introducing a static pruning component. Comparison experimental results with existing runtime and static pruning methods on state-of-the-art CNNs demonstrate that our proposed framework is able to provide a tradeoff between dynamic flexibility and storage efficiency in runtime channel pruning.
Author Information
Jianda Chen (Nanyang Technological University, Singapore)
Shangyu Chen (Nanyang Technological University, Singapore)
Sinno Jialin Pan (Nanyang Technological University, Singapore)
More from the Same Authors
-
2022 Poster: Learning Representations via a Robust Behavioral Metric for Deep Reinforcement Learning »
Jianda Chen · Sinno Pan -
2019 Poster: MetaQuant: Learning to Quantize by Learning to Penetrate Non-differentiable Quantization »
Shangyu Chen · Wenya Wang · Sinno Jialin Pan -
2017 Poster: Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon »
Xin Dong · Shangyu Chen · Sinno Pan -
2015 Workshop: Transfer and Multi-Task Learning: Trends and New Perspectives »
Anastasia Pentina · Christoph Lampert · Sinno Jialin Pan · Mingsheng Long · Judy Hoffman · Baochen Sun · Kate Saenko -
2013 Workshop: New Directions in Transfer and Multi-Task: Learning Across Domains and Tasks »
Urun Dogan · Marius Kloft · Tatiana Tommasi · Francesco Orabona · Massimiliano Pontil · Sinno Jialin Pan · Shai Ben-David · Arthur Gretton · Fei Sha · Marco Signoretto · Rajhans Samdani · Yun-Qian Miao · Mohammad Gheshlaghi azar · Ruth Urner · Christoph Lampert · Jonathan How -
2009 Workshop: Transfer Learning for Structured Data »
Sinno Jialin Pan · Ivor W Tsang · Le Song · Karsten Borgwardt · Qiang Yang