2 papers
cs.CV2025
Attack for Defense: Adversarial Agents for Point Prompt Optimization Empowering Segment Anything Model
Xueyu Liu, Xiaoyi Zhang, Guangze Shi +4
Prompt quality plays a critical role in the performance of the Segment Anything Model (SAM), yet existing approaches often rely on heuristic or manually crafted prompts, limiting s…
cs.CV2025
FMaMIL: Frequency-Driven Mamba Multi-Instance Learning for Weakly Supervised Lesion Segmentation in Medical Images
Hangbei Cheng, Xiaorong Dong, Xueyu Liu +6
Accurate lesion segmentation in histopathology images is essential for diagnostic interpretation and quantitative analysis, yet it remains challenging due to the limited availabili…