GeoCueFormer：几何引导的小波表示与预测提示双阶段解码器用于水下语义分割
GeoCueFormer: Geometry-Guided Wavelet Representation and Prediction-Cued Dual-Stage Decoder for Underwater Semantic Segmentation
浏览论文内容
中文总结 AI 辅助
GeoCueFormer提出几何约束频率增强与预测提示双阶段解码器，区分结构细节与退化干扰，在SUIM和DUT上达到SOTA性能，实现精度-复杂度平衡。
中文摘要 AI 辅助
水下语义分割对于海洋生态系统监测至关重要，但由于严重的视觉退化仍然具有挑战性。光的吸收和散射常导致颜色偏移、低对比度和模糊边界，使得浅层细节特征不可靠。现有的水下分割方法改善了RGB特征聚合或边界预测，但仍缺乏明确的机制来区分结构相关细节与退化引起的响应。为解决这一局限，我们提出了GeoCueFormer，一个轻量级框架，结合了几何约束的频率增强与预测提示的细化。GeoCueFormer在分层编码器特征上执行特定阶段的小波增强，以补充浅层边界细节，同时保留深层结构语义。一个深度导出的空间门将浅层频率增强约束到几何一致的区域，而预测提示的双阶段解码器进一步细化模糊的高分辨率特征。GeoCueFormer在SUIM和DUT上分别获得82.23%和73.04%的mIoU。在SUIM和DUT上，在相当的模型复杂度和标准基准设置下，它实现了SOTA性能，同时保持了良好的精度-复杂度权衡。这些结果表明，区分结构细节与退化引起的干扰对于水下分割更为有效。
英文摘要
Underwater semantic segmentation is essential for marine ecosystem monitoring, yet remains challenging due to severe visual degradation. Light absorption and scattering often lead to color shifts, low contrast, and blurred boundaries, making shallow detail features unreliable. Existing underwater segmentation methods improve RGB feature aggregation or boundary prediction, but still lack an explicit mechanism to distinguish structure-related details from degradation-induced responses. To address this limitation, we propose GeoCueFormer, a lightweight framework that combines geometry-constrained frequency enhancement with prediction-cued refinement. GeoCueFormer performs stage-specific wavelet enhancement on hierarchical encoder features to complement shallow boundary details while preserving deep structural semantics. A depth-derived spatial gate constrains shallow frequency enhancement toward geometry-consistent regions, and a prediction-cued dual-stage decoder further refines ambiguous high-resolution features. GeoCueFormer obtains 82.23% and 73.04% mIoU on SUIM and DUT, respectively. Under comparable model complexity and standard benchmark settings on SUIM and DUT, it achieves SOTA performance while maintaining a favorable accuracy-complexity trade-off. These results show that distinguishing structural details from degradation-induced interference is more effective for underwater segmentation.
发表机构
- Southwest University of Science and Technology（西南科技大学）
- Columbia University（哥伦比亚大学）
- Carnegie Mellon University（卡内基梅隆大学）
- University of California, Berkeley（加州大学伯克利分校）
机构由 AI 辅助整理，请以论文原文为准。
