# DSConv: Efficient Convolution Operator

arXiv: https://arxiv.org/abs/1901.01928 · HTML: https://mlsanity.com/paper/1901.01928/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jan 2019.

## Built on by (most cited first, 4 of 4)

- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)
- [Neural Network Quantization with AI Model Efficiency Toolkit (AIMET)](https://mlsanity.com/paper/2201.08442/) (2022)
- [MoQE: Improve Quantization Model performance via Mixture of Quantization Experts](https://mlsanity.com/paper/2508.09204/) (2025)
- [Approximating Continuous Convolutions for Deep Network Compression](https://mlsanity.com/paper/2210.08951/) (2022)

## Abstract (arXiv)

Quantization is a popular way of increasing the speed and lowering the memory usage of Convolution Neural Networks (CNNs). When labelled training data is available, network weights and activations have successfully been quantized down to 1-bit. The same cannot be said about the scenario when labelled training data is not available, e.g. when quantizing a pre-trained model, where current approaches show, at best, no loss of accuracy at 8-bit quantizations. We introduce DSConv, a flexible quantized convolution operator that replaces single-precision operations with their far less expensive integer counterparts, while maintaining the probability distributions over both the kernel weights and the outputs. We test our model as a plug-and-play replacement for standard convolution on most popular neural network architectures, ResNet, DenseNet, GoogLeNet, AlexNet and VGG-Net and demonstrate state-of-the-art results, with less than 1% loss of accuracy, without retraining, using only 4-bit quantization. We also show how a distillation-based adaptation stage with unlabelled data can improve results even further.