Andrew Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Andrew Zhang has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Danrong Zhang
School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA
1 shared publication - Huili Huang
School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA
1 shared publication - James David Frost
Georgia Institute of Technology
1 shared publication - Max Mahdi Roozbahani
School of Computing Instruction, Georgia Institute of Technology, Atlanta, GA 30332, USA
1 shared publication
Latest Publications
- Open Access
- 14 August 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (16) , 2812
DASeg: A Domain-Adaptive Segmentation Pipeline Using Vision Foundation Models—Earthquake Damage Detection Use Case
Limited labeled imagery and tight response windows hinder the accurate damage quantification for post-disaster assessment. The objective of this study is to develop and evaluate a deep learning-based Domain-Adaptive Segmentation (DASeg) workflow to detect post-disaster damage using limited information available shortly after an event. DASeg unifies three Vision Foundation Models in an automatic workflow: fine-tuned DINOv2 supplies attention-based point prompts, fine-tuned Grounding DINO yields open-set box prompts, and a frozen Segment Anything Model (SAM) generates the final masks. In the earthquake-focused case study DASeg-Quake, the pipeline boosts mean Intersection over Union (mIoU) by 9.52% over prior work and 2.10% over state-of-the-art supervised baselines. In a zero-shot setting scenario, DASeg-Quake achieves the mIoU of 75.03% for geo-damage analysis, closely matching expert-level annotations. These results show that DASeg achieves superior workflow enhancement in infrastructure damage segmentation without needing pixel-level annotation, providing a practical solution for early-stage disaster response.
- 14 August 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (16) , 2812
Open AccessDASeg: A Domain-Adaptive Segmentation Pipeline Using Vision Foundation Models—Earthquake Damage Detection Use Case
Limited labeled imagery and tight response windows hinder the accurate damage quantification for post-disaster assessment. The objective of this study is to develop and evaluate a deep learning-based Domain-Adaptive Segmentation (DASeg) workflow to detect post-disaster damage using limited information available shortly after an event. DASeg unifies three Vision Foundation Models in an automatic workflow: fine-tuned DINOv2 supplies attention-based point prompts, fine-tuned Grounding DINO yields open-set box prompts, and a frozen Segment Anything Model (SAM) generates the final masks. In the earthquake-focused case study DASeg-Quake, the pipeline boosts mean Intersection over Union (mIoU) by 9.52% over prior work and 2.10% over state-of-the-art supervised baselines. In a zero-shot setting scenario, DASeg-Quake achieves the mIoU of 75.03% for geo-damage analysis, closely matching expert-level annotations. These results show that DASeg achieves superior workflow enhancement in infrastructure damage segmentation without needing pixel-level annotation, providing a practical solution for early-stage disaster response.