mlsanityData to 14 Oct 2026

LampQ: Towards Accurate Layer-wise Mixed Precision Quantization for Vision Transformers

arXiv 2511.10004 ↗First posted 13 Nov 2025cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

How can we accurately quantize a pre-trained Vision Transformer model? Quantization algorithms compress Vision Transformers (ViTs) into low-bit formats, reducing memory and computation demands with minimal accuracy degradation. However, existing methods rely on uniform precision, ignoring the diverse sensitivity of ViT components to quantization. Metric-based Mixed Precision Quantization (MPQ) is a promising alternative, but previous MPQ methods for ViTs suffer from three major limitations: 1) coarse granularity, 2) mismatch in metric scale across component types, and 3) quantization-unaware bit allocation. In this paper, we propose LampQ (Layer-wise Mixed Precision Quantization for Vision Transformers), an accurate metric-based MPQ method for ViTs to overcome these limitations. LampQ performs layer-wise quantization to achieve both fine-grained control and efficient acceleration, incorporating a type-aware Fisher-based metric to measure sensitivity. Then, LampQ assigns bit-widths optimally through integer linear programming and further updates them iteratively. Extensive experiments show that LampQ provides the state-of-the-art performance in quantizing ViTs pre-trained on various tasks such as image classification, object detection, and zero-shot quantization.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 29 of its 53 references that are in the map. First posted on arXiv 13 Nov 2025.

Builds on

29 of 53 references.

References · 29

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  6. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 724
  7. 2021Post-Training Quantization for Vision Transformercited by 278
  8. 2019HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networkscited by 261
  9. 2022EfficientFormer: Vision Transformers at MobileNet Speedcited by 241
  10. 2022SimVP: Simpler yet Better Video Predictioncited by 184
  11. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 180
  12. 2021PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantizationcited by 179
17 more
  1. 2023EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attentioncited by 172
  2. 2022RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformerscited by 137
  3. 2022Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformercited by 108
  4. 2022PD-Quant: Post-Training Quantization based on Prediction Difference Metriccited by 73
  5. 2023Towards Accurate Post-Training Quantization for Vision Transformercited by 71
  6. 2019AutoQ: Automated Kernel-Wise Neural Network Quantizationcited by 63
  7. 2022Patch Similarity Aware Data-Free Quantization for Vision Transformerscited by 56
  8. 2024Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMscited by 54
  9. 2022NIPQ: Noise proxy-based Integrated Pseudo-Quantizationcited by 35
  10. 2020Search What You Want: Barrier Panelty NAS for Mixed Precision Quantizationcited by 32
  11. 2024AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizercited by 29
  12. 2022SDQ: Stochastic Differentiable Quantization with Mixed Precisioncited by 28
  13. 2024Instance-Aware Group Quantization for Vision Transformerscited by 25
  14. 2023Boost Vision Transformer with GPU-Friendly Sparsity and Quantizationcited by 20
  15. 2023MetaMix: Meta-state Precision Searcher for Mixed-precision Activation Quantizationcited by 7
  16. 2025JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-Explorationcited by 3
  17. 2025Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Informationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compressioncited by 3
  2. 2026MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformerscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Patch-wise Mixed-Precision Quantization of Vision Transformer
  2. 2024MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer
  3. 2025IPTQ-ViT: Post-Training Quantization of Non-linear Functions for Integer-only Vision Transformers
  4. 2025GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers
  5. 2025AIQViT: Architecture-Informed Post-Training Quantization for Vision Transformers
  6. 2021FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer
  7. 2024DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers
  8. 2024P2-ViT: Power-of-Two Post-Training Quantization and Acceleration for Fully Quantized Vision Transformer