Metraipolis › archive › dc_0deb6baba072

Compass: Degradation-Simulated Reciprocal Learning with Lightweight Needle RWKV for Multimodal Crack Segmentation under Missing Modalities — arXiv:2608.03559

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03559
License (as archived)
CC0-1.0
Archived
2026-10-31T12:59:40.223Z
SHA-256 of the archived text
a256a437e33c8da63414c492a411b98a44fb8f5831727809d19e6eb2b5738c6d
Stable URL of this page
https://metraipolis.com/documento/dc_0deb6baba072

How to cite

Compass: Degradation-Simulated Reciprocal Learning with Lightweight Needle RWKV for Multimodal Crack Segmentation under Missing Modalities — arXiv:2608.03559 — arXiv (en), https://arxiv.org/abs/2608.03559 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0deb6baba072 (Metraipolis archive dc_0deb6baba072, sha256 a256a437e33c8da63414c492a411b98a44fb8f5831727809d19e6eb2b5738c6d)
BibTeX
@misc{dc0deb6baba072,
  title = {Compass: Degradation-Simulated Reciprocal Learning with Lightweight Needle RWKV for Multimodal Crack Segmentation under Missing Modalities — arXiv:2608.03559},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03559},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0deb6baba072; sha256 a256a437e33c8da63414c492a411b98a44fb8f5831727809d19e6eb2b5738c6d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03559. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.03559 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T12:45:33.260Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).