mlsanityData to 14 Oct 2026

Quantization of Deep Neural Networks for Accurate Edge Computing

arXiv 2104.12046 ↗First posted 25 Apr 2021cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) have demonstrated their great potential in recent years, exceeding the per-formance of human experts in a wide range of applications. Due to their large sizes, however, compressiontechniques such as weight quantization and pruning are usually applied before they can be accommodated onthe edge. It is generally believed that quantization leads to performance degradation, and plenty of existingworks have explored quantization strategies aiming at minimum accuracy loss. In this paper, we argue thatquantization, which essentially imposes regularization on weight representations, can sometimes help toimprove accuracy. We conduct comprehensive experiments on three widely used applications: fully con-nected network (FCN) for biomedical image segmentation, convolutional neural network (CNN) for imageclassification on ImageNet, and recurrent neural network (RNN) for automatic speech recognition, and experi-mental results show that quantization can improve the accuracy by 1%, 1.95%, 4.23% on the three applicationsrespectively with 3.5x-6.4x memory reduction.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 20 of its 39 references that are in the map. First posted on arXiv 25 Apr 2021.

Builds on

20 of 39 references.

References · 20

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  4. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  5. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  6. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
  7. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 569
  8. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 426
  9. 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
  10. 2017Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weightscited by 217
  11. 2016Trained Ternary Quantizationcited by 208
  12. 2016Ternary Weight Networkscited by 204
8 more
  1. 2016Gland Segmentation in Colon Histology Images: The GlaS Challenge Contestcited by 203
  2. 2017Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentationcited by 146
  3. 2016DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentationcited by 84
  4. 2018Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentationcited by 19
  5. 2021ImageCHD: A 3D Computed Tomography Image Dataset for Classification of Congenital Heart Diseasecited by 16
  6. 2019Machine Vision Guided 3D Medical Image Compression for Efficient Transmission and Accurate Segmentation in the Cloudscited by 9
  7. 2020ICA-UNet: ICA Inspired Statistical UNet for Real-time 3D Cardiac Cine MRI Segmentationcited by 9
  8. 2018Deep Learning-Based Multiple Object Visual Tracking on Embedded System for IoT and Mobile Edge Computing Applicationscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 2; 2023: 1; 2024: 3; 2025: 3; 2026: 3.

13 papers.

Sort:

By area:

  1. 2024Asteroid: Resource-Efficient Hybrid Pipeline Parallelism for Collaborative DNN Training on Heterogeneous Edge Devicescited by 13
  2. 2022QReg: On Regularization Effects of Quantizationcited by 11
  3. 2024QGen: On the Ability to Generalize in Quantization Aware Trainingcited by 7
  4. 2023Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inferencecited by 6
  5. 2022SwiftPruner: Reinforced Evolutionary Pruning for Efficient Ad Relevancecited by 4
  6. 2021A Layer-wise Adversarial-aware Quantization Optimization for Improving Robustnesscited by 3
  7. 2025Efficient Mixed Precision Quantization in Graph Neural Networkscited by 3
  8. 2025MoENAS: Mixture-of-Expert based Neural Architecture Search for jointly Accurate, Fair, and Robust Edge Deep Neural Networkscited by 2
  9. 2024Smartphone-based Eye Tracking System using Edge Intelligence and Model Optimisationcited by 1
  10. 2025Pruning and Quantization Impact on Graph Neural Networkscited by 0
  11. 2026Toward Multi-Domain and Long-Tailed Quantization via Feature Alignment and Scalingcited by 0
  12. 2026Large Models for Small Devices: Recent Advances and Empirical Analysis of Edge AI Deploymentcited by 0
1 more
  1. 2026Beyond Reconstruction Loss in Post-Training Quantization: Balanced Fitting for Large Vision-Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Edge Inference with Fully Differentiable Quantized Mixed Precision Neural Networks
  2. 2022A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification
  3. 2026Quantization-Aware Regularizers for Deep Neural Networks Compression
  4. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Survey
  5. 2022A simple approach for quantizing neural networks
  6. 2025Low-bit Model Quantization for Deep Neural Networks: A Survey
  7. 2025Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization
  8. 2023Designing strong baselines for ternary neural network quantization through support and mass equalization