Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AdaLoRA-QAT: Adaptive Low-Rank and Quantization-Aware Segmentation

Prantik Deb, Srimanth Dhondy, N. Ramakrishna, Anu Kapoor, Raju S. Bapi, Tapabrata Chakraborti

Abstract

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/

AdaLoRA-QAT: Adaptive Low-Rank and Quantization-Aware Segmentation

Abstract

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/

Paper Structure

This paper contains 15 sections, 4 equations, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Method
  3. Datasets
  4. Model Overview
  5. Stage 1: Full-Precision AdaLoRA Training
  6. Stage 2: Quantization-Aware Fine-Tuning
  7. Training Strategy
  8. Results and Discussion
  9. Quantitative and Qualitative Evaluation
  10. Quantization Error and Statistical Validation
  11. Ablation Study
  12. Conclusion
  13. Acknowledgement
  14. COMPLIANCE WITH ETHICAL STANDARDS
  15. Conflicts of Interest

Figures (3)

  • Figure 1: Two-stage training pipeline of the proposed AdaLoRA-QAT framework.
  • Figure 2: Structural Similarity Index (SSIM) heatmap comparison of lung segmentation. From left: input CXR, ground truth, baseline SAM SSIM map, proposed AdaLoRA+ Full QAT SSIM map, and $\Delta$SSIM (QAT -- Baseline). Bright regions indicate higher structural agreement. Green in the difference map denotes localized improvements, while red marks degradations.
  • Figure 3: Quantization error analysis of AdaLoRA-QAT: (a) zero-mean Gaussian noise distribution, (b) FP32-–INT8 correlation, (c) stable error across weight amplitudes, and (d) Q–Q validation of normality.