提出新型量化方法，让视觉Transformer在早退出时更稳定高效
Amortized-Precision Quantization for Early-Exit Vision Transformers
- 按层动态考虑量化噪声影响，设计自适应精度分配策略
- 实现精度与效率的帕累托最优，最高降低95%计算量
- 适合需要低延迟部署的视觉任务，如检测与分割
视觉Transformer在各类视觉任务中表现优异，但其在低精度早退出场景下的部署仍不稳定。现有量化方法假设固定深度执行，当量化噪声扰动退出决策时，会沿动态推理路径放大误差。本文提出摊销精度量化（APQ），一种考虑逐层随机暴露于量化噪声的感知机制，揭示了深度与精度间的权衡关系。基于APQ，我们进一步提出互适应早退出量化（MAQEE），一个双层优化框架，在显式风险控制下联合优化退出阈值与位宽，提升推理稳定性。MAQEE在分类、检测和分割任务中均建立更优的精度-效率权衡前沿，计算量（BOPs）最高降低95%，同时保持精度，并优于强基线20%。
原文摘要 · Abstract (English)
Vision Transformers (ViTs) achieve strong performance across vision tasks, yet their deployment with low-precision early exiting remains fragile. Existing quantization methods assume static full-depth execution, making them unstable when exit decisions are perturbed by quantization noise, which can amplify errors along dynamic inference paths. In this paper, we introduce Amortized-Precision Quantization (APQ), a utilization-aware formulation that accounts for layer-wise stochastic exposure to quantization noise and reveals depth-precision trade-offs. Building on APQ, we propose Mutual Adaptive Quantization with Early Exiting (MAQEE), a bi-level framework that jointly optimizes exit thresholds and bit-widths under explicit risk control to improve inference stability. MAQEE establishes a superior Pareto frontier in the accuracy-efficiency trade-off, reducing BOPs by up to 95% while maintaining accuracy and outperforming strong baselines by up to 20\% across classification, detection, and segmentation tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。