# Instance-Aware Group Quantization for Vision Transformers

arXiv: https://arxiv.org/abs/2404.00928 · HTML: https://mlsanity.com/paper/2404.00928/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 44 references that are in the map.
- First posted on arXiv 1 Apr 2024.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT](https://mlsanity.com/paper/1909.05840/) (2019)
- [Post-Training Quantization for Vision Transformer](https://mlsanity.com/paper/2106.14156/) (2021)
- [Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights](https://mlsanity.com/paper/1702.03044/) (2017)
- [QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization](https://mlsanity.com/paper/2203.05740/) (2022)
- [Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Loss](https://mlsanity.com/paper/1808.05779/) (2018)
- [Understanding and Overcoming the Challenges of Efficient Transformer Quantization](https://mlsanity.com/paper/2109.12948/) (2021)
- [RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers](https://mlsanity.com/paper/2212.08254/) (2022)
- [Loss Aware Post-training Quantization](https://mlsanity.com/paper/1911.07190/) (2019)
- [Network Quantization with Element-wise Gradient Scaling](https://mlsanity.com/paper/2104.00903/) (2021)
- [Rethinking Differentiable Search for Mixed-Precision Neural Networks](https://mlsanity.com/paper/2004.05795/) (2020)
- [Post-Training Piecewise Linear Quantization for Deep Neural Networks](https://mlsanity.com/paper/2002.00104/) (2020)
- [Towards Effective Low-bitwidth Convolutional Neural Networks](https://mlsanity.com/paper/1711.00205/) (2017)

## Built on by (most cited first, 25 of 25)

- [Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers](https://mlsanity.com/paper/2406.17343/) (2024)
- [Quantization without Tears](https://mlsanity.com/paper/2411.13918/) (2024)
- [Towards Accurate Post-Training Quantization of Vision Transformers via Error Reduction](https://mlsanity.com/paper/2407.06794/) (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)
- [PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement](https://mlsanity.com/paper/2505.12266/) (2025)
- [Accelerating Vision Transformers with Adaptive Patch Sizes](https://mlsanity.com/paper/2510.18091/) (2025)
- [Low-bit Model Quantization for Deep Neural Networks: A Survey](https://mlsanity.com/paper/2505.05530/) (2025)
- [Diffusion Model Quantization: A Review](https://mlsanity.com/paper/2505.05215/) (2025)
- [SL-ACC: A Communication-Efficient Split Learning Framework with Adaptive Channel-wise Compression](https://mlsanity.com/paper/2508.12984/) (2025)
- [AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization](https://mlsanity.com/paper/2503.03088/) (2025)
- [Less Precise Can Be More Reliable: A Systematic Evaluation of Quantization's Impact on VLMs Beyond Accuracy](https://mlsanity.com/paper/2509.21173/) (2025)
- [AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models](https://mlsanity.com/paper/2510.20348/) (2025)
- [LampQ: Towards Accurate Layer-wise Mixed Precision Quantization for Vision Transformers](https://mlsanity.com/paper/2511.10004/) (2025)
- [Nonlinear Bipolar Compensation: Handling Outliers in Post-Training Quantization](https://mlsanity.com/paper/2605.16423/) (2026)
- [Shift-and-Sum Quantization for Visual Autoregressive Models](https://mlsanity.com/paper/2606.16131/) (2026)
- [Assessing the Potential for Catastrophic Failure in Dynamic Post-Training Quantization](https://mlsanity.com/paper/2510.02457/) (2025)
- [When W4A4 Breaks Camouflaged Object Detection: Token-Group Dual-Constraint Activation Quantization](https://mlsanity.com/paper/2604.16855/) (2026)
- [Toward Multi-Domain and Long-Tailed Quantization via Feature Alignment and Scaling](https://mlsanity.com/paper/2606.04920/) (2026)
- [ScalePredictor: Instance-aware Scale Learning for Accurate Quantization of Vision Transformers](https://mlsanity.com/paper/2606.21947/) (2026)
- [QuaSAR: Quantization Compensation via Stable Activation-Aware Rank Truncation](https://mlsanity.com/paper/2608.14149/) (2026)
- [Channel-Wise and Token-Aware Post-Training Quantization for Visual State Space Duality](https://mlsanity.com/paper/2609.16656/) (2026)
- [GLF-Q: Global-Local Feature-based Quantization for Vision Transformers](https://mlsanity.com/paper/2609.34564/) (2026)
- [VisionMX: Unlocking Microscaling Post-Training Quantization for Vision Models](https://mlsanity.com/paper/2610.03218/) (2026)
- [RPFQ-ViT: Rotated Phase-Frame Quantization for Extremely Low-Bit Weights in Vision Transformers](https://mlsanity.com/paper/2610.04457/) (2026)

## Abstract (arXiv)

Post-training quantization (PTQ) is an efficient model compression technique that quantizes a pretrained full-precision model using only a small calibration set of unlabeled samples without retraining. PTQ methods for convolutional neural networks (CNNs) provide quantization results comparable to full-precision counterparts. Directly applying them to vision transformers (ViTs), however, incurs severe performance degradation, mainly due to the differences in architectures between CNNs and ViTs. In particular, the distribution of activations for each channel vary drastically according to input instances, making PTQ methods for CNNs inappropriate for ViTs. To address this, we introduce instance-aware group quantization for ViTs (IGQ-ViT). To this end, we propose to split the channels of activation maps into multiple groups dynamically for each input instance, such that activations within each group share similar statistical properties. We also extend our scheme to quantize softmax attentions across tokens. In addition, the number of groups for each layer is adjusted to minimize the discrepancies between predictions from quantized and full-precision models, under a bit-operation (BOP) constraint. We show extensive experimental results on image classification, object detection, and instance segmentation, with various transformer architectures, demonstrating the effectiveness of our approach.