mlsanityData to 7 Oct 2026

AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer

arXiv 2407.12951 ↗First posted 17 Jul 2024cs.CVcited by 28

Not on the map. Why?

Abstract (arXiv)

Vision Transformer (ViT) has become one of the most prevailing fundamental backbone networks in the computer vision community. Despite the high accuracy, deploying it in real applications raises critical challenges including the high computational cost and inference latency. Recently, the post-training quantization (PTQ) technique has emerged as a promising way to enhance ViT's efficiency. Nevertheless, existing PTQ approaches for ViT suffer from the inflexible quantization on the post-Softmax and post-GELU activations that obey the power-law-like distributions. To address these issues, we propose a novel non-uniform quantizer, dubbed the Adaptive Logarithm AdaLog (AdaLog) quantizer. It optimizes the logarithmic base to accommodate the power-law-like distribution of activations, while simultaneously allowing for hardware-friendly quantization and de-quantization. By employing the bias reparameterization, the AdaLog quantizer is applicable to both the post-Softmax and post-GELU activations. Moreover, we develop an efficient Fast Progressive Combining Search (FPCS) strategy to determine the optimal logarithm base for AdaLog, as well as the scaling factors and zero points for the uniform quantizers. Extensive experimental results on public benchmarks demonstrate the effectiveness of our approach for various ViT-based architectures and vision tasks including classification, object detection, and instance segmentation. Code is available at https://github.com/GoatWu/AdaLog.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 32 of its 42 references that are in the map. First posted on arXiv 17 Jul 2024.

Builds on

32 of 42 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  8. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  9. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  10. 2022Token Merging: Your ViT But Fastercited by 995
  11. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  12. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
20 more
  1. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  2. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 636
  3. 2019Learned Step Size Quantizationcited by 604
  4. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 600
  5. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  6. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  7. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 464
  8. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 456
  9. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 426
  10. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 175
  11. 2021PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantizationcited by 173
  12. 2021FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformercited by 148
  13. 2019Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networkscited by 143
  14. 2022RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformerscited by 134
  15. 2022Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformercited by 106
  16. 2023Towards Accurate Post-Training Quantization for Vision Transformercited by 70
  17. 2023X-Pruner: eXplainable Pruning for Vision Transformerscited by 66
  18. 2020EasyQuant: Post-training Quantization via Scale Optimizationcited by 57
  19. 2023OcTr: Octree-based Transformer for 3D Object Detectioncited by 32
  20. 2023Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformerscited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 15; 2026: 11.

28 papers.

Sort:

By area:

  1. 2024Quantization without Tearscited by 24
  2. 2025Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategiescited by 24
  3. 2025APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformerscited by 17
  4. 2025PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancementcited by 17
  5. 2025FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximationcited by 16
  6. 2025Low-bit Model Quantization for Deep Neural Networks: A Surveycited by 11
  7. 2025LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generationcited by 10
  8. 2025Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivitycited by 9
  9. 2024TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Modelscited by 6
  10. 2025Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Modelcited by 4
  11. 2025LampQ: Towards Accurate Layer-wise Mixed Precision Quantization for Vision Transformerscited by 2
  12. 2026Zero-Shot Quantization via Weight-Space Arithmeticcited by 2
16 more
  1. 2025Pack-PTQ: Advancing Post-training Quantization of Neural Networks by Pack-wise Reconstructioncited by 1
  2. 2025EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devicescited by 1
  3. 2025PTQAT: A Hybrid Parameter-Efficient Quantization Algorithm for 3D Perception Taskscited by 1
  4. 2025I-Segmenter: Integer-Only Vision Transformer for Efficient Semantic Segmentationcited by 1
  5. 2026Nonlinear Bipolar Compensation: Handling Outliers in Post-Training Quantizationcited by 1
  6. 2026Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformerscited by 1
  7. 2025SegQuant: A Semantics-Aware and Generalizable Quantization Framework for Diffusion Modelscited by 0
  8. 2025Assessing the Potential for Catastrophic Failure in Dynamic Post-Training Quantizationcited by 0
  9. 2026Benford's Law as a Distributional Prior for Post-Training Quantization of Large Language Modelscited by 0
  10. 2026Joint Post-Training Quantization of Vision Transformers with Learned Prompt-Guided Data Generationcited by 0
  11. 2026MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantizationcited by 0
  12. 2026ScalePredictor: Instance-aware Scale Learning for Accurate Quantization of Vision Transformerscited by 0
  13. 2026MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformerscited by 0
  14. 2026Channel-Wise and Token-Aware Post-Training Quantization for Visual State Space Dualitycited by 0
  15. 2026The Undetected Damage of Quantization on Retrieval and How to Fix Itcited by 0
  16. 2026GLF-Q: Global-Local Feature-based Quantization for Vision Transformerscited by 0