# Towards Accurate Post-Training Quantization for Vision Transformer

arXiv: https://arxiv.org/abs/2303.14341 · HTML: https://mlsanity.com/paper/2303.14341/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 51 references that are in the map.
- First posted on arXiv 25 Mar 2023.

## Builds on (most cited first, 30 of 42)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference](https://mlsanity.com/paper/2104.01136/) (2021)
- [Post-Training Quantization for Vision Transformer](https://mlsanity.com/paper/2106.14156/) (2021)
- [Libra R-CNN: Towards Balanced Learning for Object Detection](https://mlsanity.com/paper/1904.02701/) (2019)
- [I-BERT: Integer-only BERT Quantization](https://mlsanity.com/paper/2101.01321/) (2021)
- [Sparse Communication for Distributed Gradient Descent](https://mlsanity.com/paper/1704.05021/) (2017)
- [Low-bit Quantization of Neural Networks for Efficient Inference](https://mlsanity.com/paper/1902.06822/) (2019)
- [PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantization](https://mlsanity.com/paper/2111.12293/) (2021)
- [QuadTree Attention for Vision Transformers](https://mlsanity.com/paper/2201.02767/) (2022)
- [Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World](https://mlsanity.com/paper/2103.01050/) (2021)
- [Dynamic Curriculum Learning for Imbalanced Data Classification](https://mlsanity.com/paper/1901.06783/) (2019)
- [Colorization Transformer](https://mlsanity.com/paper/2102.04432/) (2021)
- [Post-Training Piecewise Linear Quantization for Deep Neural Networks](https://mlsanity.com/paper/2002.00104/) (2020)

## Built on by (most cited first, 30 of 71)

- [Efficient Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2405.10739/) (2024)
- [LLM-FP4: 4-Bit Floating-Point Quantized Transformers](https://mlsanity.com/paper/2310.16836/) (2023)
- [GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration](https://mlsanity.com/paper/2504.02692/) (2025)
- [A Survey on Transformer Compression](https://mlsanity.com/paper/2402.05964/) (2024)
- [A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking](https://mlsanity.com/paper/2309.02031/) (2023)
- [PTQ4SAM: Post-Training Quantization for Segment Anything](https://mlsanity.com/paper/2405.03144/) (2024)
- [LGViT: Dynamic Early Exiting for Accelerating Vision Transformer](https://mlsanity.com/paper/2308.00255/) (2023)
- [AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer](https://mlsanity.com/paper/2407.12951/) (2024)
- [Instance-Aware Group Quantization for Vision Transformers](https://mlsanity.com/paper/2404.00928/) (2024)
- [Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies](https://mlsanity.com/paper/2503.02891/) (2025)
- [Towards Accurate Post-Training Quantization of Vision Transformers via Error Reduction](https://mlsanity.com/paper/2407.06794/) (2024)
- [I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization](https://mlsanity.com/paper/2311.10126/) (2023)
- [DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers](https://mlsanity.com/paper/2408.03291/) (2024)
- [APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers](https://mlsanity.com/paper/2504.02508/) (2025)
- [FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation](https://mlsanity.com/paper/2506.11543/) (2025)
- [FrameQuant: Flexible Low-Bit Quantization for Transformers](https://mlsanity.com/paper/2403.06082/) (2024)
- [Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision](https://mlsanity.com/paper/2307.00331/) (2023)
- [2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution](https://mlsanity.com/paper/2406.06649/) (2024)
- [Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey](https://mlsanity.com/paper/2405.00314/) (2024)
- [COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization](https://mlsanity.com/paper/2403.07134/) (2024)
- [MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer](https://mlsanity.com/paper/2401.14895/) (2024)
- [RepQuant: Towards Accurate Post-Training Quantization of Large Transformer Models via Scale Reparameterization](https://mlsanity.com/paper/2402.05628/) (2024)
- [PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution](https://mlsanity.com/paper/2411.17106/) (2024)
- [Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity](https://mlsanity.com/paper/2501.06357/) (2025)
- [TeleSparse: Practical Privacy-Preserving Verification of Deep Neural Networks](https://mlsanity.com/paper/2504.19274/) (2025)
- [LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation](https://mlsanity.com/paper/2401.11243/) (2024)
- [Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion](https://mlsanity.com/paper/2409.09808/) (2024)
- [A Survey on Mamba Architecture for Vision Applications](https://mlsanity.com/paper/2502.07161/) (2025)
- [QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge](https://mlsanity.com/paper/2503.16709/) (2025)
- [TransAxx: Efficient Transformers with Approximate Computing](https://mlsanity.com/paper/2402.07545/) (2024)

## Abstract (arXiv)

Vision transformer emerges as a potential architecture for vision tasks. However, the intense computation and non-negligible delay hinder its application in the real world. As a widespread model compression technique, existing post-training quantization methods still cause severe performance drops. We find the main reasons lie in (1) the existing calibration metric is inaccurate in measuring the quantization influence for extremely low-bit representation, and (2) the existing quantization paradigm is unfriendly to the power-law distribution of Softmax. Based on these observations, we propose a novel Accurate Post-training Quantization framework for Vision Transformer, namely APQ-ViT. We first present a unified Bottom-elimination Blockwise Calibration scheme to optimize the calibration metric to perceive the overall quantization disturbance in a blockwise manner and prioritize the crucial quantization errors that influence more on the final output. Then, we design a Matthew-effect Preserving Quantization for Softmax to maintain the power-law character and keep the function of the attention mechanism. Comprehensive experiments on large-scale classification and detection datasets demonstrate that our APQ-ViT surpasses the existing post-training quantization methods by convincing margins, especially in lower bit-width settings (e.g., averagely up to 5.17% improvement for classification and 24.43% for detection on W4A4). We also highlight that APQ-ViT enjoys versatility and works well on diverse transformer variants.