Mamba模型在语义分割中因信息衰减导致细节丢失，Reload-Mamba通过三重设计提升边界与类别敏感性。
Reload-Mamba: Hierarchical Anti-Dilution State-Space Modeling for Multi-Class Semantic Segmentation
- 引入边界监督的局部细节先验，定位需恢复响应的区域
- 设计基于类别不确定性的重载门，动态调节响应修复强度
- 分层多级重载机制融合高层语义，显著提升分割精度
基于Mamba的状态空间模型能以线性时间实现高分辨率密集预测的长程建模，但序列状态传播会导致边界和细节响应衰减，影响多类语义分割性能。本文提出Reload-Mamba框架，通过三项分割专用设计解决该问题：(i) 使用真实边界掩码训练的边界监督局部细节先验，识别需响应恢复的区域；(ii) 基于像素级类别熵的类别不确定性感知重载门，仅在多类密集预测场景下有效；(iii) 分层多级重载机制，在解码器三个层级应用反衰减优化，并自顶向下融合恢复特征。基于ConvNeXt-Tiny编码器、多尺度解码器及四方向Mamba扫描与像素级方向注意力，Reload-Mamba在ADE20K上取得47.9%（单尺度）/48.9%（多尺度）mIoU，Cityscapes达83.2%单尺度mIoU。在标准DeepLab协议下使用ResNet-101+COCO预训练，PASCAL VOC 2012 val集达到87.8% mIoU。消融实验表明，三项设计均超越直接移植的二值化抗衰减架构，累计提升2.2 mIoU。
原文摘要 · Abstract (English)
Mamba-based state space models offer linear-time long-range modeling for high-resolution dense prediction, but sequential state-space propagation can attenuate boundary-sensitive and detail-sensitive responses that are critical in multi-class semantic segmentation. We propose Reload-Mamba, a semantic segmentation framework that addresses this propagation-induced response dilution through three segmentation-specific designs: (i) a boundary-supervised local detail prior that is explicitly trained with ground-truth boundary masks to identify regions requiring response restoration; (ii) a class-uncertainty-aware Reload Gate that incorporates per-pixel class entropy from a pre-reload auxiliary head as an additional gating signal, a formulation that is informative only under multi-class dense prediction; and (iii) a hierarchical multi-level Reload mechanism that applies anti-dilution refinement at three decoder levels and fuses the restored representations top-down. Built upon a ConvNeXt-Tiny encoder with a multi-scale decoder and four-directional Mamba scanning with pixel-wise directional attention, Reload-Mamba achieves 47.9% single-scale (48.9% multi-scale) mIoU on ADE20K and 83.2% single-scale mIoU on Cityscapes. With ResNet-101 + COCO pre-training under the standard DeepLab-style protocol, Reload-Mamba reaches 87.8% mIoU on PASCAL VOC 2012 val. Controlled ablations show that each of the three segmentation-specific designs contributes beyond a direct port of the prior anti-dilution architecture proposed for binarization, cumulatively improving over the direct-port baseline by +2.2 mIoU on ADE20K.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。