Compass: Degradation-Simulated Reciprocal Learning with Lightweight Needle RWKV for Multimodal Crack Segmentation under Missing Modalities

2026-08-04

AI Summary

This work addresses the challenges of performance degradation and high computational cost in multimodal crack segmentation for industrial facilities under arbitrary modality missingness. The authors propose Compass, a lightweight network featuring Degradation Simulation Distillation (DSD), a Modality-Agnostic Feature-Aware Prototype Transformer (FAPT), Evidential Theory-driven Topology-Preserving Fusion (ETPF), and an uncertainty-gated decoder to achieve robust segmentation regardless of missing modalities. Built upon an efficient Needle RWKV backbone, Compass contains only 2.58 million parameters. It achieves state-of-the-art performance across three datasets, with CrackDepth attaining an F1 score of 0.8216 and mIoU of 0.8434 even when 90% of depth modality data is missing.

Abstract

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.

Problem

• multimodal crack segmentation
• missing modalities
• semantic degradation
• lightweight network
• pixel-level performance

Innovation

• Degradation Simulation Distillation
• Needle RWKV
• Evidential Fusion
• Modality Missing Robustness
• Lightweight Crack Segmentation