Beyond Quadratic: Linear-Time Change Detection with RWKV
This work addresses the problem of efficient and accurate change detection for remote sensing applications, offering a new paradigm that balances computational cost and performance.
The paper tackles the trade-off between efficiency and global context in remote sensing change detection by introducing ChangeRWKV, which achieves state-of-the-art performance on the LEVIR-CD benchmark with 85.46% IoU and 92.16% F1 score while reducing parameters and FLOPs.
Existing paradigms for remote sensing change detection are caught in a trade-off: CNNs excel at efficiency but lack global context, while Transformers capture long-range dependencies at a prohibitive computational cost. This paper introduces ChangeRWKV, a new architecture that reconciles this conflict. By building upon the Receptance Weighted Key Value (RWKV) framework, our ChangeRWKV uniquely combines the parallelizable training of Transformers with the linear-time inference of RNNs. Our approach core features two key innovations: a hierarchical RWKV encoder that builds multi-resolution feature representation, and a novel Spatial-Temporal Fusion Module (STFM) engineered to resolve spatial misalignments across scales while distilling fine-grained temporal discrepancies. ChangeRWKV not only achieves state-of-the-art performance on the LEVIR-CD benchmark, with an 85.46% IoU and 92.16% F1 score, but does so while drastically reducing parameters and FLOPs compared to previous leading methods. This work demonstrates a new, efficient, and powerful paradigm for operational-scale change detection. Our code and model are publicly available.