mlsanityData to 7 Oct 2026

Faster Convolution Inference Through Using Pre-Calculated Lookup Tables

arXiv 2104.01681 ↗First posted 4 Apr 2021cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Low-cardinality activations permit an algorithm based on fetching the inference values from pre-calculated lookup tables instead of calculating them every time. This algorithm can have extensions, some of which offer abilities beyond those of the currently used algorithms. It also allows for a simpler and more effective CNN-specialized hardware.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 74 references that are in the map. First posted on arXiv 4 Apr 2021.

Builds on

17 of 74 references.

References · 17

  1. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  2. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  3. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  4. 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 427
  5. 2017Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weightscited by 211
  6. 2013Fast Training of Convolutional Networks through FFTscited by 89
  7. 2019Towards Unified INT8 Training for Convolutional Neural Networkcited by 77
  8. 2020EasyQuant: Post-training Quantization via Scale Optimizationcited by 57
  9. 2014Flattened Convolutional Neural Networks for Feedforward Accelerationcited by 20
  10. 2016Very Efficient Training of Convolutional Neural Networks using Fast Fourier Transform and Overlap-and-Addcited by 7
  11. 2015Origami: A 803 GOp/s/W Convolutional Network Acceleratorcited by 6
  12. 2020Acceleration of Convolutional Neural Network Using FFT-Based Split Convolutionscited by 6
5 more
  1. 2019Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networkscited by 5
  2. 2017Precision Scaling of Neural Networks for Efficient Audio Processingcited by 3
  3. 2019Derivation and Analysis of Fast Bilinear Algorithms for Convolutioncited by 2
  4. 2016Complexity Leads to Simplicity: A Consensus Layer V Pyramidal Neuron Can Sustain Interpulse-Interval Codingcited by 1
  5. 2017Towards a New Interpretation of Separable Convolutionscited by 1

Built on by

Not cited yet.