How to explore the interaction between the RGB and thermal modalities is the key success of the RGB-T saliency object detection (SOD). Most of the existing methods integrate multi-modality information by designing various fusion strategies. However, the modality gap between the RGB and thermal features will lead to unsatisfactory performances by simple feature concatenation. To solve this problem, we innovatively propose a cross-guided modality difference reduction network (CGMDRNet) to achieve intrinsic consistency feature fusion via reducing the modality differences. Specifically, we design a modality difference reduction (MDR) module, which is embedded in each layer of the backbone network. The module uses a cross-guided strategy to reduce the modality difference between the RGB and thermal features. Then, a cross-attention fusion (CAF) module is designed to fuse cross-modality features with small modality differences. In addition, we use a transformer-based feature enhancement (TFE) module to enhance the high-level feature representation that contributes more to performance. Finally, the high-level features guide the fusion of low-level features to obtain a saliency map with clear boundaries. Extensive experiments on three public RGB-T datasets show that the proposed CGMDRNet achieves competitive performance compared with state-of-the-art (SOTA) RGB-T SOD models.

中文翻译：

---

CGMDRNet：用于 RGB-T 显着目标检测的交叉引导模态差异减少网络


如何探索 RGB 和热模态之间的相互作用是 RGB-T 显着性目标检测 (SOD) 成功的关键。现有方法大多数通过设计各种融合策略来集成多模态信息。然而，RGB 和热特征之间的模态差距将导致简单特征串联的性能不令人满意。为了解决这个问题，我们创新性地提出了一种交叉引导模态差异缩减网络（CGMDRNet），通过减少模态差异来实现内在一致性特征融合。具体来说，我们设计了一个模态差异缩减（MDR）模块，该模块嵌入在骨干网络的每一层中。该模块采用交叉引导策略来减少 RGB 和热特征之间的模态差异。然后，设计了交叉注意融合（CAF）模块来融合具有较小模态差异的跨模态特征。此外，我们使用基于变压器的特征增强（TFE）模块来增强高级特征表示，从而对性能做出更大贡献。最后，高层特征引导低层特征融合，得到边界清晰的显着图。对三个公共 RGB-T 数据集的大量实验表明，与最先进的 (SOTA) RGB-T SOD 模型相比，所提出的 CGMDRNet 实现了有竞争力的性能。