# And the Bit Goes Down: Revisiting the Quantization of Neural Networks

arXiv: https://arxiv.org/abs/1907.05686 · HTML: https://mlsanity.com/paper/1907.05686/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jul 2019.

## Built on by (most cited first, 30 of 78)

- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference](https://mlsanity.com/paper/2104.01136/) (2021)
- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)
- [Pre-Trained Models: Past, Present and Future](https://mlsanity.com/paper/2106.07139/) (2021)
- [GPTVQ: The Blessing of Dimensionality for LLM Quantization](https://mlsanity.com/paper/2402.15319/) (2024)
- [A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification](https://mlsanity.com/paper/2205.07877/) (2022)
- [VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference](https://mlsanity.com/paper/2102.04503/) (2021)
- [ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training](https://mlsanity.com/paper/2104.14129/) (2021)
- [VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2409.17066/) (2024)
- [Implicit Neural Video Compression](https://mlsanity.com/paper/2112.11312/) (2021)
- [NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise Modeling](https://mlsanity.com/paper/2212.14593/) (2022)
- [Differentiable Model Compression via Pseudo Quantization Noise](https://mlsanity.com/paper/2104.09987/) (2021)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [DKM: Differentiable K-Means Clustering Layer for Neural Network Compression](https://mlsanity.com/paper/2108.12659/) (2021)
- [Knowledge Distillation as Semiparametric Inference](https://mlsanity.com/paper/2104.09732/) (2021)
- [Neural Network Quantization with AI Model Efficiency Toolkit (AIMET)](https://mlsanity.com/paper/2201.08442/) (2022)
- [FineQuant: Unlocking Efficiency with Fine-Grained Weight-Only Quantization for LLMs](https://mlsanity.com/paper/2308.09723/) (2023)
- [LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision](https://mlsanity.com/paper/2112.09852/) (2021)
- [LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup](https://mlsanity.com/paper/2302.03213/) (2023)
- [RED : Looking for Redundancies for Data-Free Structured Compression of Deep Neural Networks](https://mlsanity.com/paper/2105.14797/) (2021)
- [RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging](https://mlsanity.com/paper/2110.01397/) (2021)
- [LVAC: Learned Volumetric Attribute Compression for Point Clouds using Coordinate Based Networks](https://mlsanity.com/paper/2111.08988/) (2021)
- [AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments](https://mlsanity.com/paper/2303.07129/) (2023)
- [KDLSQ-BERT: A Quantized Bert Combining Knowledge Distillation with Learned Step Size Quantization](https://mlsanity.com/paper/2101.05938/) (2021)
- [Knowledge Distillation Methods for Efficient Unsupervised Adaptation Across Multiple Domains](https://mlsanity.com/paper/2101.07308/) (2021)
- [Optimal Quantization for Matrix Multiplication](https://mlsanity.com/paper/2410.13780/) (2024)
- [VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers](https://mlsanity.com/paper/2408.17131/) (2024)
- [LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms](https://mlsanity.com/paper/2311.11420/) (2023)
- [MKQ-BERT: Quantized BERT with 4-bits Weights and Activations](https://mlsanity.com/paper/2203.13483/) (2022)
- [Fixed-point Quantization of Convolutional Neural Networks for Quantized Inference on Embedded Platforms](https://mlsanity.com/paper/2102.02147/) (2021)

## Abstract (arXiv)

In this paper, we address the problem of reducing the memory footprint of convolutional network architectures. We introduce a vector quantization method that aims at preserving the quality of the reconstruction of the network outputs rather than its weights. The principle of our approach is that it minimizes the loss reconstruction error for in-domain inputs. Our method only requires a set of unlabelled data at quantization time and allows for efficient inference on CPU by using byte-aligned codebooks to store the compressed weights. We validate our approach by quantizing a high performing ResNet-50 model to a memory size of 5MB (20x compression factor) while preserving a top-1 accuracy of 76.1% on ImageNet object classification and by compressing a Mask R-CNN with a 26x factor.