PTQ-SL: Exploring the Sub-layerwise Post-training Quantization
Not on the map. Why?
Abstract (arXiv)
Network quantization is a powerful technique to compress convolutional neural networks. The quantization granularity determines how to share the scaling factors in weights, which affects the performance of network quantization. Most existing approaches share the scaling factors layerwisely or channelwisely for quantization of convolutional layers. Channelwise quantization and layerwise quantization have been widely used in various applications. However, other quantization granularities are rarely explored. In this paper, we will explore the sub-layerwise granularity that shares the scaling factor across multiple input and output channels. We propose an efficient post-training quantization method in sub-layerwise granularity (PTQ-SL). Then we systematically experiment on various granularities and observe that the prediction accuracy of the quantized neural network has a strong correlation with the granularity. Moreover, we find that adjusting the position of the channels can improve the performance of sub-layerwise quantization. Therefore, we propose a method to reorder the channels for sub-layerwise quantization. The experiments demonstrate that the sub-layerwise quantization with appropriate channel reordering can outperform the channelwise quantization.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 19 of its 25 references that are in the map. First posted on arXiv 15 Oct 2021.
Builds on
19 of 25 references.
References · 19
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
- 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
- 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
- 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 600
- 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
- 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 464
- 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 456
- 2019Q-BERT: Hessian Based Ultra Low Precision Quantization of BERTcited by 355
7 more
- 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 328
- 2018LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networkscited by 272
- 2019Low-bit Quantization of Neural Networks for Efficient Inferencecited by 185
- 2018Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Losscited by 157
- 2020Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programmingcited by 89
- 2019And the Bit Goes Down: Revisiting the Quantization of Neural Networkscited by 78
- 2020EasyQuant: Post-training Quantization via Scale Optimizationcited by 57
Built on by
Citing papers per year: 2023: 1.
1 paper.