RA-SOD：模态退化下可靠性感知的RGB-T显著目标检测
RA-SOD: Reliability-Aware RGB-T Salient Object Detection under Modality Degradation
- State Key Laboratory of Robotics and Systems, Harbin Institute of Technology（哈尔滨工业大学机器人技术与系统国家重点实验室）
- School of Computer Science, University of Sydney（悉尼大学计算机科学学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对RGB-T显著目标检测中模态退化导致融合不可靠的问题，提出可靠性感知框架RA-SOD，通过可靠性条件化表示、不确定性引导细化及像素级模态竞争机制，在四个基准上取得最优性能。
AI中文摘要：
RGB-热红外（RGB-T）显著目标检测利用可见光与热红外模态的互补线索，以提升在挑战性环境中的鲁棒性。然而，在真实场景中，各模态的可靠性本质上是不稳定的：RGB图像在低光照、运动模糊和噪声条件下会退化，而热红外图像则常遭受对比度压缩和传感器伪影的影响。这种退化会引入不可靠的感知证据，从而误导跨模态融合，并显著降低检测性能。为应对这一挑战，我们提出RA-SOD，一个可靠性感知的RGB-T显著目标检测框架，该框架显式建模模态可靠性并将其整合进特征学习与跨模态融合中。首先，我们引入一种可靠性条件化表示，自适应地补偿退化模态的特征，同时保留结构线索。其次，一种不确定性引导的双流细化策略逐步修正跨模态表示，同时抑制不可靠证据。最后，我们提出一种像素级模态竞争机制，根据空间可靠性动态选择模态线索以实现细粒度融合。在四个基准（VT821、VT1000、VT5000和VT-IMAG）上的大量实验表明，RA-SOD取得了最先进的性能，并在严重模态退化下展现出强鲁棒性。代码和模型可在该https URL获取。
英文摘要：
RGB-Thermal (RGB-T) salient object detection leverages complementary cues from visible and thermal modalities to improve robustness in challenging environments. However, in real-world scenarios, the reliability of each modality is inherently unstable: RGB images degrade under low illumination, motion blur, and noise, while thermal imagery often suffers from contrast compression and sensor artifacts. Such degradation introduces unreliable perceptual evidence that can mislead cross-modal fusion and significantly deteriorate detection performance. To address this challenge, we propose RA-SOD, a reliability-aware RGB-T salient object detection framework that explicitly models modality reliability and integrates it into feature learning and cross-modal fusion. First, we introduce a reliability-conditioned representation that adaptively compensates degraded modality features while preserving structural cues. Second, an uncertainty-guided dual-stream refinement strategy progressively corrects cross-modal representations while suppressing unreliable evidence. Finally, we propose a pixel-wise modality competition mechanism that dynamically selects modality cues according to spatial reliability for fine-grained fusion. Extensive experiments on four benchmarks (VT821, VT1000, VT5000, and VT-IMAG) demonstrate that RA-SOD achieves state-of-the-art performance and exhibits strong robustness under severe modality degradation. Code and models are available at https://github.com/zaoxienian/RA-SOD.
