mlsanityData to 7 Oct 2026

Q-HyViT: Post-Training Quantization of Hybrid Vision Transformers with Bridge Block Reconstruction for IoT Systems

arXiv 2303.12557 ↗First posted 22 Mar 2023cs.CV cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Recently, vision transformers (ViTs) have superseded convolutional neural networks in numerous applications, including classification, detection, and segmentation. However, the high computational requirements of ViTs hinder their widespread implementation. To address this issue, researchers have proposed efficient hybrid transformer architectures that combine convolutional and transformer layers with optimized attention computation of linear complexity. Additionally, post-training quantization has been proposed as a means of mitigating computational demands. For mobile devices, achieving optimal acceleration for ViTs necessitates the strategic integration of quantization techniques and efficient hybrid transformer structures. However, no prior investigation has applied quantization to efficient hybrid transformers. In this paper, we discover that applying existing post-training quantization (PTQ) methods for ViTs to efficient hybrid transformers leads to a drastic accuracy drop, attributed to the four following challenges: (i) highly dynamic ranges, (ii) zero-point overflow, (iii) diverse normalization, and (iv) limited model parameters (<5M). To overcome these challenges, we propose a new post-training quantization method, which is the first to quantize efficient hybrid ViTs (MobileViTv1, MobileViTv2, Mobile-Former, EfficientFormerV1, EfficientFormerV2). We achieve a significant improvement of 17.73% for 8-bit and 29.75% for 6-bit on average, respectively, compared with existing PTQ methods (EasyQuant, FQ-ViT, PTQ4ViT, and RepQ-ViT). We plan to release our code at https://gitlab.com/ones-ai/q-hyvit.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 40 of its 52 references that are in the map. First posted on arXiv 22 Mar 2023.

Builds on

40 of 52 references.

References · 40

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  3. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  5. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  6. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  7. 2019Searching for MobileNetV3cited by 1,984
  8. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  9. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  10. 2021Transformers in Vision: A Surveycited by 1,009
  11. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  12. 2020A Survey on Visual Transformercited by 653
28 more
  1. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 636
  2. 2019Learned Step Size Quantizationcited by 604
  3. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 600
  4. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  5. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  6. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 464
  7. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 456
  8. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 328
  9. 2021Post-Training Quantization for Vision Transformercited by 274
  10. 2018LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networkscited by 272
  11. 2022EfficientFormer: Vision Transformers at MobileNet Speedcited by 240
  12. 2021Mobile-Former: Bridging MobileNet and Transformercited by 234
  13. 2019Low-bit Quantization of Neural Networks for Efficient Inferencecited by 185
  14. 2020Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluationcited by 183
  15. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 175
  16. 2021PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantizationcited by 173
  17. 2022Separable Self-attention for Mobile Vision Transformerscited by 163
  18. 2018Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Losscited by 157
  19. 2019Improving Neural Network Quantization without Retraining using Outlier Channel Splittingcited by 150
  20. 2021FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformercited by 148
  21. 2022RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformerscited by 134
  22. 2022Rethinking Vision Transformers for MobileNet Size and Speedcited by 121
  23. 2022NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformerscited by 59
  24. 2020EasyQuant: Post-training Quantization via Scale Optimizationcited by 57
  25. 2019Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorizationcited by 45
  26. 2018Quantization for Rapid Deployment of Deep Neural Networkscited by 20
  27. 2018Fast Adjustable Threshold For Uniform Neural Network Quantization (Winning solution of LPIRC-II)cited by 6
  28. 2021Automated Backend-Aware Post-Training Quantizationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 3; 2026: 2.

6 papers.

  1. 2023LLM-FP4: 4-Bit Floating-Point Quantized Transformerscited by 65
  2. 2025EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devicescited by 1
  3. 2025TinyEcoWeedNet: Edge Efficient Real-Time Aerial Agricultural Weed Detectioncited by 0
  4. 2025Cat: Post-Training Quantization Error Reduction via Cluster-based Affine Transformationcited by 0
  5. 2026Evolving Layer-Specific Scalar Functions for Hardware-Aware Transformer Adaptationcited by 0
  6. 2026Same Predictions, Different Reasons: The Effect of Quantization on Model Explanationscited by 0