mlsanityData to 7 Oct 2026

RedBit: An End-to-End Flexible Framework for Evaluating the Accuracy of Quantized CNNs

arXiv 2301.06193 ↗First posted 15 Jan 2023cs.LG cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

In recent years, Convolutional Neural Networks (CNNs) have become the standard class of deep neural network for image processing, classification and segmentation tasks. However, the large strides in accuracy obtained by CNNs have been derived from increasing the complexity of network topologies, which incurs sizeable performance and energy penalties in the training and inference of CNNs. Many recent works have validated the effectiveness of parameter quantization, which consists in reducing the bit width of the network's parameters, to enable the attainment of considerable performance and energy efficiency gains without significantly compromising accuracy. However, it is difficult to compare the relative effectiveness of different quantization methods. To address this problem, we introduce RedBit, an open-source framework that provides a transparent, extensible and easy-to-use interface to evaluate the effectiveness of different algorithms and parameter configurations on network accuracy. We use RedBit to perform a comprehensive survey of five state-of-the-art quantization methods applied to the MNIST, CIFAR-10 and ImageNet datasets. We evaluate a total of 2300 individual bit width combinations, independently tuning the width of the network's weight and input activation parameters, from 32 bits down to 1 bit (e.g., 8/8, 2/2, 1/32, 1/1, for weights/activations). Upwards of 20000 hours of computing time in a pool of state-of-the-art GPUs were used to generate all the results in this paper. For 1-bit quantization, the accuracy losses for the MNIST, CIFAR-10 and ImageNet datasets range between [0.26%, 0.79%], [9.74%, 32.96%] and [10.86%, 47.36%] top-1, respectively. We actively encourage the reader to download the source code and experiment with RedBit, and to submit their own observed results to our public repository, available at https://github.com/IT-Coimbra/RedBit.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 82 of its 157 references that are in the map. First posted on arXiv 15 Jan 2023.

Builds on

82 of 157 references.

References · 82

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2016Densely Connected Convolutional Networkscited by 6,691
  7. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  9. 2014Going Deeper with Convolutionscited by 4,231
  10. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  11. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  12. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
38 more
  1. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  2. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  3. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  4. 2017Mixed Precision Trainingcited by 1,135
  5. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  6. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  7. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  8. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
  9. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 571
  10. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  11. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  12. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 456
  13. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 413
  14. 2015Deep Learning with Limited Numerical Precisioncited by 368
  15. 2014Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluationcited by 304
  16. 2018Model compression via distillation and quantizationcited by 287
  17. 2014Speeding up Convolutional Neural Networks with Low Rank Expansionscited by 283
  18. 2018LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networkscited by 272
  19. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 234
  20. 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 233
  21. 2019A Study of BFLOAT16 for Deep Learning Trainingcited by 227
  22. 2019Understanding Straight-Through Estimator in Training Activation Quantized Neural Netscited by 225
  23. 2015Quantized Convolutional Neural Networks for Mobile Devicescited by 212
  24. 2017Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weightscited by 211
  25. 2016Trained Ternary Quantizationcited by 203
  26. 2014Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decompositioncited by 199
  27. 2016Ternary Weight Networkscited by 195
  28. 2014Compressing Deep Convolutional Networks using Vector Quantizationcited by 189
  29. 2020Binary Neural Networks: A Surveycited by 184
  30. 2019Forward and Backward Information Retention for Accurate Binary Neural Networkscited by 169
  31. 2017Towards Accurate Binary Convolutional Neural Networkcited by 148
  32. 2016FINN: A Framework for Fast, Scalable Binarized Neural Network Inferencecited by 141
  33. 2017Deep Learning with Low Precision by Half-wave Gaussian Quantizationcited by 115
  34. 2015Data-free parameter pruning for Deep Neural Networkscited by 112
  35. 2020Training Binary Neural Networks with Real-to-Binary Convolutionscited by 111
  36. 2016Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1cited by 102
  37. 2017Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracycited by 100
  38. 2019Defensive Quantization: When Efficiency Meets Robustnesscited by 95

50 most cited of 82 All 82 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Convolutional Differentiable Logic Gate Networkscited by 37