2 papers
cs.CV2025
SAM2-UNeXT: An Improved High-Resolution Baseline for Adapting Foundation Models to Downstream Segmentation Tasks
Xinyu Xiong, Zihuang Wu, Lei Zhang +3
Recent studies have highlighted the potential of adapting the Segment Anything Model (SAM) for various downstream tasks. However, constructing a more powerful and generalizable enc…
cs.CV2025
PDC-Net: Pattern Divide-and-Conquer Network for Pelvic Radiation Injury Segmentation
Xinyu Xiong, Wuteng Cao, Zihuang Wu +4
Accurate segmentation of Pelvic Radiation Injury (PRI) from Magnetic Resonance Images (MRI) is crucial for more precise prognosis assessment and the development of personalized tre…