Abstract
The focus of this paper is speeding up the application of convolutional neural networks. While delivering impressive results across a range of computer vision and machine learning tasks, these networks are computationally demanding, limiting their deployability. Convolutional layers generally consume the bulk of the processing time, and so in this work we present two simple schemes for drastically speeding up these layers. This is achieved by exploiting cross-channel or filter redundancy to construct a low rank basis of filters that are rank-1 in the spatial domain. Our methods are architecture agnostic, and can be easily applied to existing CPU and GPU convolutional frameworks for tuneable speedup performance. We demonstrate this with a real world network designed for scene text character recognition [15], showing a possible 2.5× speedup with no loss in accuracy, and 4.5× speedup with less than 1% drop in accuracy, still achieving state-of-the-art on standard benchmarks.
Keywords
Convolutional neural networkComputer scienceRank (graph theory)Artificial intelligenceMathematicsCombinatorics
Affiliated Institutions
Related Publications
Speeding up Convolutional Neural Networks with Low Rank Expansions
The focus of this paper is speeding up the evaluation of convolutional neural networks. While delivering impressive results across a range of computer vision and machine learnin...
Quantized Convolutional Neural Networks for Mobile Devices
Recently, convolutional neural networks (CNN) have demonstrated impressive performance in various computer vision tasks. However, high performance hardware is typically indispen...
Efficient and accurate approximations of nonlinear convolutional networks
This paper aims to accelerate the test-time computation of deep convolutional neural networks (CNNs). Unlike existing methods that are designed for approximating linear filters ...
Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks
To design fast neural networks, many works have been focusing on reducing the number of floating-point operations (FLOPs). We observe that such reduction in FLOPs, however, does...
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
Designing accurate and efficient ConvNets for mobile devices is challenging because the design space is combinatorially large. Due to this, previous neural architecture search (...
Publication Info
- Year
- 2014
- Type
- article
- Pages
- 88.1-88.13
- Citations
- 1130
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
1130
OpenAlex
Cite This
Max Jaderberg,
Andrea Vedaldi,
Andrew Zisserman
(2014).
Speeding up Convolutional Neural Networks with Low Rank Expansions.
, 88.1-88.13.
https://doi.org/10.5244/c.28.88
Identifiers
- DOI
- 10.5244/c.28.88