Compass：面向缺失模态场景下多模态裂缝分割的退化模拟互学习与轻量型Needle RWKV
Compass: Degradation-Simulated Reciprocal Learning with Lightweight Needle RWKV for Multimodal Crack Segmentation under Missing Modalities
浏览论文内容
中文总结 AI 辅助
Compass是面向缺失模态场景的多模态裂缝分割轻量型网络，通过DSD、Needle Block与ETPF实现鲁棒分割，在90%深度模态缺失时仍达SOTA性能，仅需258万参数。
中文摘要 AI 辅助
在工业设施的多模态裂缝分割任务中，核心挑战是在缺失模态导致性能下降时，防止像素级性能受损，同时保持较低的计算成本。现有方法难以解决缺失模态引发的语义退化问题。本文提出Compass，一种可在任意模态缺失场景下实现鲁棒裂缝分割的轻量型网络。Compass包含退化模拟蒸馏（DSD）、Needle Block和证据拓扑保持融合（ETPF）三个核心模块。DSD构建一条退化模拟流，模拟更严重的缺失模态场景，并与原始流执行互蒸馏，将完整感知与退化适应解耦；DSD内的特征感知原型传输器（FAPT）执行与模态无关的原型引导特征补全，以在模态不完整时保持语义完整性。作为轻量型骨干网络，Needle将裂缝方向线索注入WKV调制，并结合感知连通性的门控机制与各向异性上下文探测，实现面向结构的建模。ETPF通过Dempster-Shafer证据组合与不确定性门控解码融合多模态特征，在保留裂缝拓扑结构的同时抑制不可靠特征。在三个数据集上的实验表明，Compass在各类模态缺失场景下达到了当前最优（SOTA）性能；即使在CrackDepth数据集上90%的深度模态缺失时，Compass仍以仅258万参数取得了0.8216的F1值和0.8434的mIoU值，代码可在指定URL获取。
英文摘要
In multimodal crack segmentation for industrial facilities, the key challenge is preventing missing modalities from degrading pixel-level performance while maintaining low computational cost. Existing methods struggle to address semantic degradation caused by missing modalities. We propose Compass, a lightweight network for robust crack segmentation under arbitrary missing modalities. Compass comprises Degradation Simulation Distillation (DSD), Needle Block, and Evidential Topology-Preserving Fusion (ETPF). DSD constructs a degradation simulation stream that mimics more severe missing conditions and performs reciprocal distillation with the original stream, decoupling complete perception from degradation adaptation. Within DSD, Feature-Aware Prototype Transmitter (FAPT) performs modality agnostic prototype-guided feature completion to maintain semantic integrity under incomplete modality conditions. As a lightweight backbone, Needle injects crack-direction cues into WKV modulation and combines connectivity-aware gating with anisotropic context probing for structure-aware modeling. ETPF fuses multimodal features via Dempster-Shafer evidential combination with uncertainty-gated decoding, preserving crack topology while suppressing unreliable features. Experiments on three datasets demonstrate state-of-the-art (SOTA) performance under diverse missing modality scenarios. Even with 90\% depth modality missing on CrackDepth, Compass achieves F1 of 0.8216 and mIoU of 0.8434 with only 2.58M parameters. The code is available at https://github.com/Karl1109/Compass.
