# PalQuant: Accelerating High-precision Networks on Low-precision Accelerators

arXiv: https://arxiv.org/abs/2208.01944 · HTML: https://mlsanity.com/paper/2208.01944/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 42 references that are in the map.
- First posted on arXiv 3 Aug 2022.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [BinaryConnect: Training Deep Neural Networks with binary weights during propagations](https://mlsanity.com/paper/1511.00363/) (2015)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [Deep Learning with Limited Numerical Precision](https://mlsanity.com/paper/1502.02551/) (2015)
- [LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks](https://mlsanity.com/paper/1807.10029/) (2018)
- [Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks](https://mlsanity.com/paper/1908.05033/) (2019)
- [Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights](https://mlsanity.com/paper/1702.03044/) (2017)
- [Trained Ternary Quantization](https://mlsanity.com/paper/1612.01064/) (2016)
- [Ternary Weight Networks](https://mlsanity.com/paper/1605.04711/) (2016)
- [Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Loss](https://mlsanity.com/paper/1808.05779/) (2018)
- [FINN: A Framework for Fast, Scalable Binarized Neural Network Inference](https://mlsanity.com/paper/1612.07119/) (2016)
- [Deep Learning with Low Precision by Half-wave Gaussian Quantization](https://mlsanity.com/paper/1702.00953/) (2017)
- [Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networks](https://mlsanity.com/paper/1712.01507/) (2017)
- [Network Quantization with Element-wise Gradient Scaling](https://mlsanity.com/paper/2104.00903/) (2021)
- [Rethinking Differentiable Search for Mixed-Precision Neural Networks](https://mlsanity.com/paper/2004.05795/) (2020)
- [Loss-aware Binarization of Deep Networks](https://mlsanity.com/paper/1611.01600/) (2016)
- [WRPN: Wide Reduced-Precision Networks](https://mlsanity.com/paper/1709.01134/) (2017)
- [Neural Networks with Few Multiplications](https://mlsanity.com/paper/1510.03009/) (2015)
- [Discovering Low-Precision Networks Close to Full-Precision Networks for Efficient Embedded Inference](https://mlsanity.com/paper/1809.04191/) (2018)
- [XNOR Neural Engine: a Hardware Accelerator IP for 21.6 fJ/op Binary Neural Network Inference](https://mlsanity.com/paper/1807.03010/) (2018)
- [Hardware-Software Codesign of Accurate, Multiplier-free Deep Neural Networks](https://mlsanity.com/paper/1705.04288/) (2017)
- [Bit-Parallel Vector Composability for Neural Acceleration](https://mlsanity.com/paper/2004.05333/) (2020)
- [Rethinking Floating Point Overheads for Mixed Precision DNN Accelerators](https://mlsanity.com/paper/2101.11748/) (2021)
- [A System-Level Solution for Low-Power Object Detection](https://mlsanity.com/paper/1909.10964/) (2019)

## Built on by (most cited first, 2 of 2)

- [MBQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization](https://mlsanity.com/paper/2305.08117/) (2023)
- [Exploiting the Partly Scratch-off Lottery Ticket for Quantization-Aware Training](https://mlsanity.com/paper/2211.08544/) (2022)

## Abstract (arXiv)

Recently low-precision deep learning accelerators (DLAs) have become popular due to their advantages in chip area and energy consumption, yet the low-precision quantized models on these DLAs bring in severe accuracy degradation. One way to achieve both high accuracy and efficient inference is to deploy high-precision neural networks on low-precision DLAs, which is rarely studied. In this paper, we propose the PArallel Low-precision Quantization (PalQuant) method that approximates high-precision computations via learning parallel low-precision representations from scratch. In addition, we present a novel cyclic shuffle module to boost the cross-group information communication between parallel low-precision groups. Extensive experiments demonstrate that PalQuant has superior performance to state-of-the-art quantization methods in both accuracy and inference speed, e.g., for ResNet-18 network quantization, PalQuant can obtain 0.52% higher accuracy and 1.78× speedup simultaneously over their 4-bit counter-part on a state-of-the-art 2-bit accelerator. Code is available at urlhttps://github.com/huqinghao/PalQuant.