Speeding up Convolutional Neural Networks with Low Rank Expansions

摘要: The focus of this paper is speeding up the application convolutional neural networks. While delivering impressive results across a range computer vision and machine learning tasks, these networks are computationally demanding, limiting their deployability. Convolutional layers generally consume bulk processing time, so in work we present two simple schemes for drastically layers. This achieved by exploiting cross-channel or filter redundancy to construct low rank basis filters that rank-1 spatial domain. Our methods architecture agnostic, can be easily applied existing CPU GPU frameworks tuneable speedup performance. We demonstrate with real world network designed scene text character recognition [15], showing possible 2.5× no loss accuracy, 4.5× less than 1% drop still achieving state-of-the-art on standard benchmarks.