面向未对齐 RGB-T 显著性目标检测的不确定性感知模态融合
Uncertainty-Aware Modality Fusion for Unaligned RGB-T Salient Object Detection
把像素特征建模为高斯潜变量分布来估计局部不确定性，从而在特征空间内实现免配准的隐式跨模态对齐，并用置信度图调制融合权重；这套「不确定性驱动对齐+融合」思路可直接迁移到其他未配准多模态密集预测任务（如 RGB-D 分割、多光谱检测）。
原文依据 models pixel-wise features as Gaussian latent distributions to estimate local uncertainty and identify cross-modal consistency regions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论由于严重的跨模态空间差异与不可靠的特征融合，未对齐 RGB-T 显著性目标检测（SOD）仍具挑战性。现有方法往往假设完美对齐，或依赖几何配准，而后者计算代价高且对跨模态不一致敏感。为解决这些局限，我们提出不确定性感知模态融合网络（UMFNet），将 RGB-T SOD 重新表述为不确定性感知的表征学习问题。具体而言，所提出的不确定性对齐模块（UAM）将像素级特征建模为高斯潜变量分布，以估计局部不确定性并在特征空间内识别跨模态一致区域，从而在无显式配准的情况下实现隐式对齐。此外，置信度引导全局调制（CGM）机制利用由不确定性估计得到的置信度图，自适应地调控 RGB 与热红外特征的融合，在可靠区域增强显著线索，同时抑制噪声或不一致信息。在五个未对齐与三个已对齐 RGB-T SOD 基准上的大量实验表明，UMFNet 在多种对齐条件下均达到最优性能。
英文原文摘要 1248 字符
Unaligned RGB-T salient object detection (SOD) remains challenging due to severe cross-modal spatial discrepancies and unreliable feature fusion. Existing methods often assume perfect alignment or rely on geometric registration, which is computationally demanding and sensitive to cross-modal inconsistencies. To address these limitations, we propose an uncertainty-aware modality fusion network (UMFNet) that reformulates RGB-T SOD as an uncertainty-aware representation learning problem. Specifically, the proposed uncertainty alignment module (UAM) models pixel-wise features as Gaussian latent distributions to estimate local uncertainty and identify cross-modal consistency regions within the feature space, thereby achieving implicit alignment without explicit registration. Furthermore, the confidence-guided global modulation (CGM) mechanism leverages confidence maps derived from uncertainty estimation to adaptively regulate the fusion of RGB and thermal features, enhancing salient cues in reliable regions while suppressing noisy or inconsistent information. Extensive experiments on five unaligned and three aligned RGB-T SOD benchmarks demonstrate that UMFNet achieves state-of-the-art performance across diverse alignment conditions.