mlsanityData to 14 Oct 2026

Fixed Point Quantization of Deep Convolutional Networks

arXiv 1511.06393 ↗First posted 19 Nov 2015cs.LGcited by 143

Not on the map. Why?

Abstract (arXiv)

In recent years increasingly complex architectures for deep convolution networks (DCNs) have been proposed to boost the performance on image recognition tasks. However, the gains in performance have come at a cost of substantial increase in computation and model storage resources. Fixed point implementation of DCNs has the potential to alleviate some of these complexities and facilitate potential deployment on embedded hardware. In this paper, we propose a quantizer design for fixed point implementation of DCNs. We formulate and solve an optimization problem to identify optimal fixed point bit-width allocation across DCN layers. Our experiments show that in comparison to equal bit-width settings, the fixed point DCNs with optimized bit width allocation offer >20% reduction in the model size without any loss in accuracy on CIFAR-10 benchmark. We also demonstrate that fine-tuning can further enhance the accuracy of fixed point DCNs beyond that of the original floating point model. In doing so, we report a new state-of-the-art fixed point performance of 6.78% error-rate on CIFAR-10 benchmark.

Key facts. Cited by 143 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Nov 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 42; 2022: 35; 2023: 28; 2024: 18; 2025: 12; 2026: 8.

143 papers.

Sort:

By area:

  1. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  2. 2021Knowledge distillation: A good teacher is patient and consistentcited by 259
  3. 2021Understanding and Overcoming the Challenges of Efficient Transformer Quantizationcited by 141
  4. 2024A Survey on Large Language Model Acceleration based on KV Cache Managementcited by 131
  5. 2022LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Modelscited by 105
  6. 2022FP8 Quantization: The Power of the Exponentcited by 88
  7. 2022Federated Learning Enables Big Data for Rare Cancer Boundary Detectioncited by 84
  8. 2023Pruning vs Quantization: Which is Better?cited by 46
  9. 2021Applications and Techniques for Fast Machine Learning in Sciencecited by 32
  10. 2022F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantizationcited by 28
  11. 2021Efficient Video Compression via Content-Adaptive Super-Resolutioncited by 26
  12. 2023Adaptive Data-Free Quantizationcited by 26
38 more
  1. 2021Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Schemecited by 23
  2. 2022Hardly Perceptible Trojan Attack against Neural Networks with Bit Flipscited by 22
  3. 2022It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teachercited by 20
  4. 2023Integer or Floating Point? New Outlooks for Low-Bit Quantization on Large Language Modelscited by 19
  5. 2022DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videoscited by 18
  6. 2021Secure Quantized Training for Deep Learningcited by 15
  7. 2023Patch-wise Mixed-Precision Quantization of Vision Transformercited by 15
  8. 2021Neural Network Quantization for Efficient Inference: A Surveycited by 14
  9. 2022DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardwarecited by 14
  10. 2023One-bit Flip is All You Need: When Bit-flip Attack Meets Model Trainingcited by 14
  11. 2023Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challengescited by 14
  12. 2023Rethinking Data-Free Quantization as a Zero-Sum Gamecited by 13
  13. 2021Dynamic Precision Analog Computing for Neural Networkscited by 12
  14. 2022Low-Precision Stochastic Gradient Langevin Dynamicscited by 12
  15. 2021Sound Event Detection with Binary Neural Networks on Tightly Power-Constrained IoT Devicescited by 10
  16. 2021How RL Agents Behave When Their Actions Are Modifiedcited by 10
  17. 2021GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsitycited by 10
  18. 2022Multi-task Learning Approach for Modulation and Wireless Signal Classification for 5G and Beyond: Edge Deployment via Model Compressioncited by 10
  19. 2022FlexBlock: A Flexible DNN Training Accelerator with Multi-Mode Block Floating Point Supportcited by 10
  20. 2021Confounding Tradeoffs for Neural Network Quantizationcited by 9
  21. 2021Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networkscited by 9
  22. 2022QEBVerif: Quantization Error Bound Verification of Neural Networkscited by 9
  23. 2023Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Reviewcited by 9
  24. 2024MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similaritycited by 9
  25. 2021Measuring what Really Matters: Optimizing Neural Networks for TinyMLcited by 8
  26. 2021Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networkscited by 8
  27. 2022Accelerating DNN Training with Structured Data Gradient Pruningcited by 8
  28. 2023Entity-Agnostic Representation Learning for Parameter-Efficient Knowledge Graph Embeddingcited by 8
  29. 2024DaCapo: Accelerating Continuous Learning in Autonomous Systems for Video Analyticscited by 8
  30. 2021Fixed-point Quantization of Convolutional Neural Networks for Quantized Inference on Embedded Platformscited by 7
  31. 2022Energy-efficient Deployment of Deep Learning Applications on Cortex-M based Microcontrollers using Deep Compressioncited by 7
  32. 2022Mixed-Precision Neural Networks: A Surveycited by 7
  33. 2025Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applicationscited by 7
  34. 2021Toward Compact Deep Neural Networks via Energy-Aware Pruningcited by 6
  35. 2021Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Acceleratorscited by 6
  36. 2021Training Quantized Neural Networks to Global Optimality via Semidefinite Programmingcited by 6
  37. 2021Verifying Quantized Neural Networks using SMT-Based Model Checkingcited by 6
  38. 2022Quantune: Post-training Quantization of Convolutional Neural Networks using Extreme Gradient Boosting for Fast Deploymentcited by 6

50 most cited of 143 All 143 (JSON)