# Bit Efficient Quantization for Deep Neural Networks

arXiv: https://arxiv.org/abs/1910.04877 · HTML: https://mlsanity.com/paper/1910.04877/

## Key facts

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

## Built on by (most cited first, 14 of 14)

- [A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification](https://mlsanity.com/paper/2205.07877/) (2022)
- [Quantization-Guided Training for Compact TinyML Models](https://mlsanity.com/paper/2103.06231/) (2021)
- [Reducing Computational Complexity of Neural Networks in Optical Channel Equalization: From Concepts to Implementation](https://mlsanity.com/paper/2208.12866/) (2022)
- [Data-free mixed-precision quantization using novel sensitivity metric](https://mlsanity.com/paper/2103.10051/) (2021)
- [TinyMLOps: Operational Challenges for Widespread Edge AI Adoption](https://mlsanity.com/paper/2203.10923/) (2022)
- [Advances in Classifying the Stages of Diabetic Retinopathy Using Convolutional Neural Networks in Low Memory Edge Devices](https://mlsanity.com/paper/2106.01739/) (2021)
- [Compressed Object Detection](https://mlsanity.com/paper/2102.02896/) (2021)
- [RCT: Resource Constrained Training for Edge AI](https://mlsanity.com/paper/2103.14493/) (2021)
- [Going Further With Winograd Convolutions: Tap-Wise Quantization for Efficient Inference on 4x4 Tile](https://mlsanity.com/paper/2209.12982/) (2022)
- [Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders](https://mlsanity.com/paper/2405.03651/) (2024)
- [LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM](https://mlsanity.com/paper/2604.04523/) (2026)
- [Machine Learning Advances aiding Recognition and Classification of Indian Monuments and Landmarks](https://mlsanity.com/paper/2107.14070/) (2021)
- [DNA-TEQ: An Adaptive Exponential Quantization of Tensors for DNN Inference](https://mlsanity.com/paper/2306.16430/) (2023)
- [Toward Efficient Convolutional Neural Networks With Structured Ternary Patterns](https://mlsanity.com/paper/2407.14831/) (2024)

## Abstract (arXiv)

Quantization for deep neural networks have afforded models for edge devices that use less on-board memory and enable efficient low-power inference. In this paper, we present a comparison of model-parameter driven quantization approaches that can achieve as low as 3-bit precision without affecting accuracy. The post-training quantization approaches are data-free, and the resulting weight values are closely tied to the dataset distribution on which the model has converged to optimality. We show quantization results for a number of state-of-art deep neural networks (DNN) using large dataset like ImageNet. To better analyze quantization results, we describe the overall range and local sparsity of values afforded through various quantization schemes. We show the methods to lower bit-precision beyond quantization limits with object class clustering.