mlsanityData to 14 Oct 2026

QNNRepair: Quantized Neural Network Repair

arXiv 2306.13793 ↗First posted 23 Jun 2023cs.LG cs.NEcited by 0

Not on the map. Why?

Abstract (arXiv)

We present QNNRepair, the first method in the literature for repairing quantized neural networks (QNNs). QNNRepair aims to improve the accuracy of a neural network model after quantization. It accepts the full-precision and weight-quantized neural networks and a repair dataset of passing and failing tests. At first, QNNRepair applies a software fault localization method to identify the neurons that cause performance degradation during neural network quantization. Then, it formulates the repair problem into a linear programming problem of solving neuron weights parameters, which corrects the QNN's performance on failing tests while not compromising its performance on passing tests. We evaluate QNNRepair with widely used neural network architectures such as MobileNetV2, ResNet, and VGGNet on popular datasets, including high-resolution images. We also compare QNNRepair with the state-of-the-art data-free quantization method SQuant. According to the experiment results, we conclude that QNNRepair is effective in improving the quantized model's performance in most cases. Its repaired models have 24% higher accuracy than SQuant's in the independent validation set, especially for the ImageNet dataset.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 61 references that are in the map. First posted on arXiv 23 Jun 2023.

Builds on

31 of 61 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  4. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  5. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  6. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 479
  7. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 467
  8. 2017DeepXplore: Automated Whitebox Testing of Deep Learning Systemscited by 311
  9. 2016Safety Verification of Deep Neural Networkscited by 263
  10. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 242
  11. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 238
  12. 2021Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verificationcited by 228
19 more
  1. 2020TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systemscited by 165
  2. 2018A Survey on Methods and Theories of Quantized Neural Networkscited by 75
  3. 2021The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Resultscited by 71
  4. 2018TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzingcited by 68
  5. 2019An Abstraction-Based Framework for Neural Network Verificationcited by 68
  6. 2022SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximationcited by 55
  7. 2018Concolic Testing for Deep Neural Networkscited by 51
  8. 2020An SMT-Based Approach for Verifying Binarized Neural Networkscited by 47
  9. 2021Provable Repair of Deep Neural Networkscited by 42
  10. 2019DeepFault: Fault Localization for Deep Neural Networkscited by 30
  11. 2020Scalable Verification of Quantized Neural Networks (Technical Report)cited by 28
  12. 2021NNrepair: Constraint-based Repair of Neural Network Classifierscited by 26
  13. 2017DeepCorrect: Correcting DNN models against Image Distortionscited by 15
  14. 2019Testing and verification of neural-network-based safety-critical control software: A systematic literature reviewcited by 12
  15. 2022QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networkscited by 12
  16. 2020Improving Adversarial Robustness in Weight-quantized Neural Networkscited by 11
  17. 2021Verifying Quantized Neural Networks using SMT-Based Model Checkingcited by 6
  18. 2021QNNVerifier: A Tool for Verifying Neural Networks using SMT-Based Model Checkingcited by 4
  19. 2022AIREPAIR: A Repair Platform for Neural Networkscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023RepQ: Generalizing Quantization-Aware Training for Re-Parametrized Architectures
  2. 2021Pareto-Optimal Quantized ResNet Is Mostly 4-bit
  3. 2021Neural Network Quantization for Efficient Inference: A Survey
  4. 2024QGen: On the Ability to Generalize in Quantization Aware Training
  5. 2021A White Paper on Neural Network Quantization
  6. 2025Provable Repair of Deep Neural Network Defects by Preimage Synthesis and Property Refinement
  7. 2023Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting
  8. 2022FxP-QNet: A Post-Training Quantizer for the Design of Mixed Low-Precision DNNs with Dynamic Fixed-Point Representation