stuliu / regda

The official implementation for "Learn from Segment Anything Model: Local Region Homogenizing for Cross-domain Remote Sensing Image Segmentation".

Hi there 👋

• 🔭 I’m currently pursuing PhD at Hunan University.
• 🌱 I’m interested in Unsupervised Domain Adaptation, Semantic Segmentation, and Image Fusion.
• 📫 Please feel free to attach me if you have any questions: [email protected]

Publications

• Wang Liu, et, al. Uncertain Example Mining Network for Domain Adaptive Segmentation of Remote Sensing Images, TGRS, 2024 (code)
• Wang Liu, et, al. Learn from Segment Anything Model: Local Region Homogenizing for Cross-domain Remote Sensing Image Segmentation, IGARSS, 2024 (code)
• Wang Liu, et, al. Agriculture-Vision Challenge 2024--The Runner-Up Solution for Agricultural Pattern Recognition via Class Balancing and Model Ensemble, Arxiv, 2024 (paper)
• Wang Liu, et, al. SOSNet: Real-Time Small Object Segmentation via Hierarchical Decoding and Example Mining, TNNLS, 2023. (paper, code)
• Zhuojun Xie, Puhong Duan, Wang Liu, et, al, Feature consistency-based prototype network for open-set hyperspectral image classification. TNNLS, 2023. (paper)

Awards

• 2nd place in the 5th CVPR Agriculture Vision Challenge, 2024.
• 1st place in the CVPR SyntaGen Challenge, 2024.
• 1st place in the ISPRS Contest on Intelligent Interpretation for Multi-modal Remote Sensing Application, 2024.
• Best paper award in Pattern Recognition, Machine Vision, and Intelligent Algorithms (PRMVIA), 2024.

Github stats