# Training Quantized Neural Networks with a Full-precision Auxiliary Module

arXiv: https://arxiv.org/abs/1903.11236 · HTML: https://mlsanity.com/paper/1903.11236/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Mar 2019.

## Built on by (most cited first, 30 of 35)

- [Network Quantization with Element-wise Gradient Scaling](https://mlsanity.com/paper/2104.00903/) (2021)
- [Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation](https://mlsanity.com/paper/2111.14826/) (2021)
- [IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization](https://mlsanity.com/paper/2111.09136/) (2021)
- [Learnable Companding Quantization for Accurate Low-bit Neural Networks](https://mlsanity.com/paper/2103.07156/) (2021)
- [Dynamic Network Quantization for Efficient Video Inference](https://mlsanity.com/paper/2108.10394/) (2021)
- [LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection](https://mlsanity.com/paper/2401.15865/) (2024)
- [Sharpness-aware Quantization for Deep Neural Networks](https://mlsanity.com/paper/2111.12273/) (2021)
- [Bit-Mixer: Mixed-precision networks with runtime bit-width selection](https://mlsanity.com/paper/2103.17267/) (2021)
- [Hard Sample Matters a Lot in Zero-Shot Quantization](https://mlsanity.com/paper/2303.13826/) (2023)
- [Patch-wise Mixed-Precision Quantization of Vision Transformer](https://mlsanity.com/paper/2305.06559/) (2023)
- [Quantized Feature Distillation for Network Quantization](https://mlsanity.com/paper/2307.10638/) (2023)
- [APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor Cores](https://mlsanity.com/paper/2106.12169/) (2021)
- [QuantV2X: A Fully Quantized Multi-Agent System for Cooperative Perception](https://mlsanity.com/paper/2509.03704/) (2025)
- [Reducing Computational Complexity of Neural Networks in Optical Channel Equalization: From Concepts to Implementation](https://mlsanity.com/paper/2208.12866/) (2022)
- [Single-path Bit Sharing for Automatic Loss-aware Model Compression](https://mlsanity.com/paper/2101.04935/) (2021)
- [Effective and Fast: A Novel Sequential Single Path Search for Mixed-Precision Quantization](https://mlsanity.com/paper/2103.02904/) (2021)
- [Reducing the Side-Effects of Oscillations in Training of Quantized YOLO Networks](https://mlsanity.com/paper/2311.05109/) (2023)
- [Improving Quantization-aware Training of Low-Precision Network via Block Replacement on Full-Precision Counterpart](https://mlsanity.com/paper/2412.15846/) (2024)
- [Improved Techniques for Quantizing Deep Networks with Adaptive Bit-Widths](https://mlsanity.com/paper/2103.01435/) (2021)
- [Rethinking Floating Point Overheads for Mixed Precision DNN Accelerators](https://mlsanity.com/paper/2101.11748/) (2021)
- [MWQ: Multiscale Wavelet Quantized Neural Networks](https://mlsanity.com/paper/2103.05363/) (2021)
- [Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking](https://mlsanity.com/paper/2205.11179/) (2022)
- [E2FIF: Push the limit of Binarized Deep Imagery Super-resolution using End-to-end Full-precision Information Flow](https://mlsanity.com/paper/2207.06893/) (2022)
- [Exploiting the Partly Scratch-off Lottery Ticket for Quantization-Aware Training](https://mlsanity.com/paper/2211.08544/) (2022)
- [Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection](https://mlsanity.com/paper/2306.07215/) (2023)
- [Memory-aware Scheduling for Complex Wired Networks with Iterative Graph Optimization](https://mlsanity.com/paper/2308.13898/) (2023)
- [Scheduling Weight Transitions for Quantization-Aware Training](https://mlsanity.com/paper/2404.19248/) (2024)
- [From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks](https://mlsanity.com/paper/2405.06038/) (2024)
- [Art and Science of Quantizing Large-Scale Models: A Comprehensive Overview](https://mlsanity.com/paper/2409.11650/) (2024)
- [Information-Bottleneck Driven Binary Neural Network for Change Detection](https://mlsanity.com/paper/2507.03504/) (2025)

## Abstract (arXiv)

In this paper, we seek to tackle a challenge in training low-precision networks: the notorious difficulty in propagating gradient through a low-precision network due to the non-differentiable quantization function. We propose a solution by training the low-precision network with a fullprecision auxiliary module. Specifically, during training, we construct a mix-precision network by augmenting the original low-precision network with the full precision auxiliary module. Then the augmented mix-precision network and the low-precision network are jointly optimized. This strategy creates additional full-precision routes to update the parameters of the low-precision model, thus making the gradient back-propagates more easily. At the inference time, we discard the auxiliary module without introducing any computational complexity to the low-precision network. We evaluate the proposed method on image classification and object detection over various quantization approaches and show consistent performance increase. In particular, we achieve near lossless performance to the full-precision model by using a 4-bit detector, which is of great practical value.