LCNN: Lookup-Based Convolutional Neural Network

@article{Bagherinezhad2016LCNNLC,
  title={LCNN: Lookup-Based Convolutional Neural Network},
  author={Hessam Bagherinezhad and Mohammad Rastegari and Ali Farhadi},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={860-869}
}
Porting state of the art deep learning algorithms to resource constrained compute platforms (e.g. VR, AR, wearables) is extremely challenging. We propose a fast, compact, and accurate model for convolutional neural networks that enables efficient learning and inference. We introduce LCNN, a lookup-based convolutional neural network that encodes convolutions by few lookups to a dictionary that is trained to cover the space of weights in CNNs. Training LCNN involves jointly learning a dictionary… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 40 CITATIONS

3DICT: A Reliable and QoS Capable Mobile Process-In-Memory Architecture for Lookup-based CNNs in 3D XPoint ReRAMs

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

SECS: Efficient Deep Stream Processing via Class Skew Dichotomy

VIEW 2 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

ServeNet: A Deep Neural Network for Web Service Classification

VIEW 5 EXCERPTS
HIGHLY INFLUENCED

Adaptive Deep Reuse: Accelerating CNN Training on the Fly

VIEW 2 EXCERPTS
CITES BACKGROUND

Comparison of Face Recognition and Detection Models: Using Different Convolution Neural Networks

  • Kai Kang
  • Computer Science
  • Optical Memory and Neural Networks
  • 2019
VIEW 1 EXCERPT
CITES METHODS

EdgeL^3: Compressing L^3-Net for Mote Scale Urban Noise Monitoring

VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 47 REFERENCES

Deep Residual Learning for Image Recognition

VIEW 14 EXCERPTS
HIGHLY INFLUENTIAL

Learning Structured Sparsity in Deep Neural Networks

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Low-shot visual object recognition

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

ImageNet: A large-scale hierarchical image database

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Bitwise Neural Networks

VIEW 1 EXCERPT