mlsanityData to 14 Oct 2026

ScalePredictor: Instance-aware Scale Learning for Accurate Quantization of Vision Transformers

arXiv 2606.21947 ↗First posted 20 Jun 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Vision Transformers have achieved remarkable success in many fields, yet their deployment on edge devices remains challenging due to their substantial computational demands. Post-Training Quantization (PTQ) offers an attractive solution by compressing models using a small calibration set with minimal training overhead. However, most existing PTQ works adopt a static quantization paradigm that is uniformly applied to all instances. Given the substantial diversity of natural images, the activation distributions vary significantly across samples, making these methods inherently suboptimal. In this paper, we propose ScalePredictor, a dynamic quantization framework for accurate and efficient quantization scale learning of ViTs. We first reveal a hidden correlation between the distribution range of shallow-layer activations and the optimal scales of deeper layers. Based on this, we develop a scale learning mechanism that integrates an efficient range extraction approach to capture robust range statistics at the shallow stage, which are then fed into a Taylor-motivated polynomial scale projection module to generate all quantization scales simultaneously. With the efficiency of polynomial approximation, ScalePredictor introduces insignificant computational overhead while avoiding costly just-in-time calibration. Extensive experiments on ImageNet demonstrate that ScalePredictor consistently outperforms prior PTQ methods, achieving a more favorable accuracy-efficiency trade-off. Code and additional results are shown in the supplementary materials.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 37 references that are in the map. First posted on arXiv 20 Jun 2026.

Builds on

30 of 37 references.

References · 30

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  4. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  5. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
  6. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,101
  7. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  8. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 724
  9. 2019Importance Estimation for Neural Network Pruningcited by 541
  10. 2022ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformerscited by 526
  11. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 479
  12. 2021A White Paper on Neural Network Quantizationcited by 472
18 more
  1. 2019HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networkscited by 261
  2. 2022EfficientFormer: Vision Transformers at MobileNet Speedcited by 241
  3. 2021Mobile-Former: Bridging MobileNet and Transformercited by 235
  4. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 180
  5. 2021PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantizationcited by 179
  6. 2021You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detectioncited by 170
  7. 2021FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformercited by 151
  8. 2022RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformerscited by 137
  9. 2023Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scalingcited by 61
  10. 2024AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizercited by 29
  11. 2024Instance-Aware Group Quantization for Vision Transformerscited by 25
  12. 2023I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantizationcited by 19
  13. 2025FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximationcited by 19
  14. 2023Bi-ViT: Pushing the Limit of Vision Transformer Quantizationcited by 13
  15. 2018Diverse feature visualizations reveal invariances in early layers of deep neural networkscited by 8
  16. 2025AIQViT: Architecture-Informed Post-Training Quantization for Vision Transformerscited by 5
  17. 2025Pack-PTQ: Advancing Post-training Quantization of Neural Networks by Pack-wise Reconstructioncited by 1
  18. 2025ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitivecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023TSPTQ-ViT: Two-scaled post-training quantization for vision transformer
  2. 2024DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers
  3. 2024ADFQ-ViT: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformers
  4. 2024P2-ViT: Power-of-Two Post-Training Quantization and Acceleration for Fully Quantized Vision Transformer
  5. 2024MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer
  6. 2026Amortized-Precision Quantization for Early-Exit Vision Transformers
  7. 2022CPT-V: A Contrastive Approach to Post-Training Quantization of Vision Transformers
  8. 2022Patch Similarity Aware Data-Free Quantization for Vision Transformers