.png){kind=icon}
.png){kind=icon}
Return
CAIR-Net: Reliability-Aware Information Routing for Robust Multimodal Object Detection Under Modality Degradation
.png){kind=icon}
PRE
AI
DOI：10.1109/TCSVT.2026.3662605.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Multimodal remote sensing combines optical and synthetic aperture radar (SAR) imagery to improve perception, yet real deployments face spatially varying degradations (e.g., clouds, low light, sensor interference) that can corrupt fusion. To make robustness measurable, we introduce a controlled mixed-severity setting in which only the optical stream is synthetically cloud-degraded while SAR remains intact, providing a standardized testbed for evaluating multimodal detection under modality imbalance. We further present <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CAIR-Net</b>, a reliability–aware information routing network that follows a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">denoise-then-fuse</i> principle: a Local Reliability Modulation (LRM) module learns soft, spatial reliability maps to suppress degraded regions <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">before</i> cross-modal interaction, and a Global Information Selection Mechanism (GISM) performs confidence-aware expert routing across optical, fused, and SAR experts. On the mixed-severity benchmark, CAIR-Net consistently outperforms strong unimodal and fusion baselines and exhibits a substantially smaller performance drop under severe clouds. These results indicate that explicit reliability modeling and quality-guided routing provide a practical path toward robust multimodal detection when one modality is partially or nearly completely occluded.
Keywords:
Multimodal object detection
optical degradation
SAR-optical fusion
degradation-aware fusion
expert routing
Journal
IF:
11.1
Papers:
612
Citations:
3.1W