Yulin Cao

An efficient region-of-interest-driven simplified neural dynamics for large-scale inverse problems

Simulation and real-world field experimental results demonstrate that the ROI-driven SND method effectively suppresses directional distortions and achieves improved reconstruction performance under both noise-free and noise-considered conditions.

An efficient region-of-interest-driven simplified neural dynamics for large-scale inverse problems

Weakly Supervised Remote Sensing Segmentation via Decoupled Cross-Modal Distillation and Semantic-Guided Refinement

A three-stage framework that integrates complementary priors from Contrastive Language–Image Pre-training, Self-Distillation with No Labels version 2 (DINOv2), and the Segment Anything Model (SAM) is proposed, demonstrating the effectiveness and generalizability of the proposed framework across diverse remote sensing s...