AdaLoRA-QAT让医学影像模型更小更快，精度不降。
AdaLoRA-QAT: Adaptive Low-Rank and Quantization-Aware Segmentation
- 自适应低秩微调+全量化感知训练，兼顾效率与精度。
- 参数量减少16.6倍，模型压缩2.24倍，Dice达95.6%。
- 适合临床部署的轻量级医学图像分割模型，可信度高。
胸部X光（CXR）分割是辅助诊断的重要步骤，但大型基础模型在临床环境中部署受限于计算资源。本文提出AdaLoRA-QAT，一种两阶段微调框架，结合自适应低秩编码器适配与全量化感知训练。自适应秩分配提升参数效率，选择性混合精度INT8量化保留关键结构保真度，对临床可靠性至关重要。在大规模CXR数据集上评估显示，AdaLoRA-QAT实现95.6% Dice分数，与全精度SAM解码器微调相当，同时可训练参数减少16.6倍，模型压缩达2.24倍。威尔科克森符号秩检验表明，量化未显著降低分割精度。结果证明，AdaLoRA-QAT有效平衡了准确性、效率与结构可信性，使紧凑且可部署的基础模型成为可能。代码与预训练模型详见：https://prantik-pdeb.github.io/adaloraqat.github.io/
原文摘要 · Abstract (English)
Chest X-ray (CXR) segmentation is an important step in computer-aided diagnosis, yet deploying large foundation models in clinical settings remains challenging due to computational constraints. We propose AdaLoRA-QAT, a two-stage fine-tuning framework that combines adaptive low-rank encoder adaptation with full quantization-aware training. Adaptive rank allocation improves parameter efficiency, while selective mixed-precision INT8 quantization preserves structural fidelity crucial for clinical reliability. Evaluated across large-scale CXR datasets, AdaLoRA-QAT achieves 95.6% Dice, matching full-precision SAM decoder fine-tuning while reducing trainable parameters by 16.6\times and yielding 2.24\times model compression. A Wilcoxon signed-rank test confirms that quantization does not significantly degrade segmentation accuracy. These results demonstrate that AdaLoRA-QAT effectively balances accuracy, efficiency, and structural trust-worthiness, enabling compact and deployable foundation models for medical image segmentation. Code and pretrained models are available at: https://prantik-pdeb.github.io/adaloraqat.github.io/
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。