Boosting the Dual-Stream Architecture in Ultra-High Resolution Segmentation with Resolution-Biased Uncertainty Estimation

framework, where an estimator is used to assess resolutionbiased uncertainties through the entropy map and highfrequency feature residual. The framework also includes a selector, an ensembler, and a complementer to boost the model with obtained estimations. They share the uncertainty estimations as the weights to choose difficult regions as the inputs for UHR stream, perform weighted fusion between distinct streams, and enhance the learning for important pixels, respectively. Experiment results demonstrate that our method achieves a satisfactory balance between accuracy and inference consumption against other stateof-the-art (SOTA) methods. The code is available in the https://github.com/Qinrong-NKU/RUE .