Reproduce “Shared-Pattern Collaborative Network for Multi-Source Remote Sensing Data Classification” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Chenfang Yang, Chuanzheng Gong, Feng Gao, Junyu Dong, Qian Du

SPCNet maps land cover from co-registered hyperspectral imagery and LiDAR or polarimetric SAR by sharing spatial convolution across sensor branches while retaining adaptive local filters and modality-specific features. Its regional fusion module assigns location-dependent source weights. It achieves the highest overall accuracy and Kappa on three benchmarks; Houston2013 accuracy is 93.53%, versus 90.98% for the strongest competitor, within dataset-specific splits.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.