Data-Free Quantization Through Weight Equalization and Bias Correction
@article{Nagel2019DataFreeQT, title={Data-Free Quantization Through Weight Equalization and Bias Correction}, author={M. Nagel and Mart van Baalen and Tijmen Blankevoort and M. Welling}, journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)}, year={2019}, pages={1325-1334} }
We introduce a data-free quantization method for deep neural networks that does not require fine-tuning or hyperparameter selection. [...] Key Method Our approach relies on equalizing the weight ranges in the network by making use of a scale-equivariance property of activation functions. In addition the method corrects biases in the error that are introduced during quantization. This improves quantization accuracy performance, and can be applied to many common computer vision architectures with a straight…Expand Abstract
Supplemental Code
Github Repo
Via Papers with Code
PyTorch implementation of Data Free Quantization Through Weight Equalization and Bias Correction.
Figures, Tables, and Topics from this paper
75 Citations
Post-training Piecewise Linear Quantization for Deep Neural Networks
- Computer Science
- ECCV
- 2020
- 5
- Highly Influenced
- PDF
Near-Lossless Post-Training Quantization of Deep Neural Networks via a Piecewise Linear Approximation
- Computer Science
- ArXiv
- 2020
- 3
- Highly Influenced
Up or Down? Adaptive Rounding for Post-Training Quantization
- Computer Science, Mathematics
- ICML
- 2020
- 9
- PDF
DAQ: Distribution-Aware Quantization for Deep Image Super-Resolution Networks
- Computer Science, Engineering
- ArXiv
- 2020
- Highly Influenced
- PDF
Gradient $\ell_1$ Regularization for Quantization Robustness
- Computer Science, Mathematics
- ICLR
- 2020
- PDF
Weight Equalizing Shift Scaler-Coupled Post-training Quantization
- Computer Science, Mathematics
- ArXiv
- 2020
- Highly Influenced
- PDF
Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming
- Computer Science, Mathematics
- ArXiv
- 2020
- 3
- PDF
Filter Pre-Pruning for Improved Fine-tuning of Quantized Deep Neural Networks
- Computer Science
- ArXiv
- 2020
- Highly Influenced
- PDF
References
SHOWING 1-10 OF 38 REFERENCES
SYQ: Learning Symmetric Quantization for Efficient Deep Neural Networks
- Computer Science
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- 2018
- 73
- PDF
Quantizing deep convolutional networks for efficient inference: A whitepaper
- Computer Science, Mathematics
- ArXiv
- 2018
- 227
- Highly Influential
- PDF
PACT: Parameterized Clipping Activation for Quantized Neural Networks
- Computer Science
- ArXiv
- 2018
- 225
- PDF
Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights
- Computer Science
- ICLR
- 2017
- 547
- PDF
Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorization
- Computer Science, Mathematics
- ICML
- 2019
- 19
- PDF
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
- Computer Science, Mathematics
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- 2018
- 625
- Highly Influential
- PDF
Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
- Computer Science
- J. Mach. Learn. Res.
- 2017
- 933
- PDF