LightweightNet: Toward fast and lightweight convolutional neural networks via architecture distillation.
Pattern Recognition(2019)
摘要
•We present a new framework of deep convolutional neural network architecture distillation, namely LightweightNet, for acceleration and compression.•We exploit the prior knowledge of pre-defined network architecture to guide the efficient design of acceleration/compression strategies, while not using pre-trained model.•The proposed framework consists of network parameter compression, network structure acceleration, and non-tensor layer improvement.•The proposed framework demonstrates a higher acceleration/compression rate than previous methods in experiments, including a large category handwritten Chinese character recognition task with state-of-the-art performance.
更多查看译文
关键词
Deep network acceleration and compression,Architecture distillation,Lightweight network
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络