cs.CVNov 19, 2026

Calibrate in Context: Efficient Data-Free Quantization from Small Synthetic Pools

Authors: Haowen Hua, Sen Lin, Yaokun Huang, Zeyi Shao, Hao Zhang, Wei Sui, John See, Zeyd Boukhers, 

Organizations: Soochow University · D-Robotics · Heriot-Watt University · Fraunhofer Institute for Applied Information Technology

Abstract

We enable accurate low-bit recovery from small synthetic pools by improving both image synthesis and student preparation. A grid with lower local response error can incur greater error in the student's block context. Functional Grid Calibration (FGC) selects activation scales and integer offsets against full-precision responses constructed from the student's current block input. With weights fixed during calibration, FGC evaluates candidates only at their consuming operators, bringing block context to calibration at nearly local-scoring cost. For DeiT and ViT, progressive inversion updates the same images through increasingly deep teacher prefixes. With 1,000 images, the complete pipeline exceeds MimiQ's reported accuracy in all 18 W4A4/W5A5 settings across nine backbones. With 256 images, DeiT-S and ViT-S reach 68.20% and 66.90% ImageNet top-1 accuracy at W4A4 in 26-27 minutes on one RTX 5090. The pipeline outperforms strengthened 1K-image MimiQ by 13.03 and 24.36 percentage points at lower preparation cost and the same recovery-update count. The same low-budget checkpoints retain their advantage on ImageNetV2.

Figures & tables

Explore similar work

CardsList
  1. Joint Post-Training Quantization of Vision Transformers with Learned Prompt-Guided Data Generation

    Feb 21, 2026Shile Li, Markus Karmann, Onay UrfaliogluPost-Training QuantizationNeural Network Quantization

  2. When Calibration Data Matter in Sub-4-Bit Language Model Quantization

    Nov 8, 2026Yehong Jiang, Yen-Kuang Chen, Xinmin TianLLM QuantizationPost-Training Quantization

  3. SoloQ: Calibration-Free Quantization for Diffusion Language Models

    Oct 5, 2026Donghyun Lee, Arkapravo Ghosh, Varun Manjunath +5Diffusion Model QuantizationKV-Cache Quantization