4 papers
Masks Can Talk: Extracting Structured Text Information from Single-Modal Images for Remote Sensing Change Detection
Kai Zheng, Hang-Cheng Dong, Jiatong Pan +3
Remote sensing change detection is pivotal for urban monitoring, disaster assessment, and environmental resource management. Yet, unimodal deep learning methods frequently confuse…
Tri-path DINO: Feature Complementary Learning for Remote Sensing Multi-Class Change Detection
Kai Zheng, Hang-Cheng Dong, Shoulei Liu +5
In remote sensing imagery, multi-class change detection (MCD) is crucial for fine-grained monitoring, yet it has long been plagued by feature ambiguity in change regions, which obs…
Changes in Gaza: DINOv3-Powered Multi-Class Change Detection for Damage Assessment in Conflict Zones
Kai Zheng, Zhenkai Wu, Fupeng Wei +6
Accurately and swiftly assessing damage from conflicts is crucial for humanitarian aid and regional stability. In conflict zones, damaged zones often share similar architectural st…
Sample-Centric Multi-Task Learning for Detection and Segmentation of Industrial Surface Defects
Hang-Cheng Dong, Yibo Jiao, Fupeng Wei +3
Industrial surface defect inspection for sample-wise quality control (QC) must simultaneously decide whether a given sample contains defects and localize those defects spatially. I…