CRISP: Calibration-Aware Visual State Space Duality for Remote Sensing Semantic Segmentation

2026-08-24

AI Summary

为解决VSSD在遥感语义分割中边界过度平滑问题，提出CRISP框架，通过双校准算子恢复局部对比度和边界响应，并使用正交多原型头保留细节。

Abstract

State space models, especially Visual State Space Duality (VSSD), have emerged as efficient linear-time alternatives to Transformers for dense visual tasks. However, we observe that VSSD compresses spatial context into a global aggregation that suppresses high-frequency responses, causing excessive boundary smoothing in remote sensing semantic segmentation. To address this, we propose CRISP, a calibration framework with two components. Its core, the Duality Calibration Operator (DCO), restores local contrast and boundary responses through residual injection and frequency calibration within the VSSD backbone, without altering its linear complexity. To retain the recovered detail, an Orthogonal Multi-Prototype (OMP) head assigns multiple orthogonally constrained prototypes per class to model large intra-class variance. Extensive experiments on Potsdam, Vaihingen, and LoveDA show that, with approximately 30M parameters, CRISP achieves consistent gains in mean F1 (mF) and mIoU while remaining competitive with state-of-the-art methods. Code is available at https://github.com/crazylifeha/CRISP.

Problem

• Visual State Space Duality
• remote sensing semantic segmentation
• boundary smoothing
• spatial context

Innovation

• Duality Calibration Operator
• Orthogonal Multi-Prototype
• Visual State Space Duality