通过干预稳定特征学习的多模态图像融合
Multi-Modal Image Fusion via Intervention-Stable Feature Learning
把因果干预（互补掩码、同区域随机掩码、模态 dropout）当作构造训练信号的手段，配合自适应不变性门控筛选「跨扰动模式仍重要」的特征，可直接迁移到多模态融合、跨模态对齐以及模态缺失下的鲁棒表征学习。
原文依据 we introduce a Causal Feature Integrator (CFI) that learns to identify and prioritize intervention-stable features
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论多模态图像融合将来自不同模态的互补信息整合为统一表示。现有方法主要优化模态间的统计相关性，往往学到由数据集诱发的虚假关联，在分布偏移下性能退化。本文提出一个受因果原理启发的基于干预的框架，用于识别鲁棒的跨模态依赖关系。借鉴 Pearl 因果层级的思想，我们设计三种有原则的干预策略，以探查模态关系的不同侧面：i) 空间不相交扰动下的互补掩码，检验模态是否能够真正补偿彼此缺失的信息；ii) 对相同区域施加随机掩码，识别在部分可观测条件下仍具信息量的特征子集；iii) 模态丢弃，评估每个模态不可替代的贡献。基于这些干预，我们引入因果特征整合器（CFI），它通过自适应不变性门控学习识别并优先选择在不同扰动模式下重要性保持稳定的干预稳定特征，从而捕获鲁棒的模态依赖而非虚假相关。大量实验表明，本方法在公开基准与下游高层视觉任务上均取得 SOTA 性能。代码将公开。
英文原文摘要 1426 字符
Multi-modal image fusion integrates complementary information from different modalities into a unified representation. Current methods predominantly optimize statistical correlations between modalities, often capturing dataset-induced spurious associations that degrade under distribution shifts. In this paper, we propose an intervention-based framework inspired by causal principles to identify robust cross-modal dependencies. Drawing insights from Pearl's causal hierarchy, we design three principled intervention strategies to probe different aspects of modal relationships: i) complementary masking with spatially disjoint perturbations tests whether modalities can genuinely compensate for each other's missing information, ii) random masking of identical regions identifies feature subsets that remain informative under partial observability, and iii) modality dropout evaluates the irreplaceable contribution of each modality. Based on these interventions, we introduce a Causal Feature Integrator (CFI) that learns to identify and prioritize intervention-stable features maintaining importance across different perturbation patterns through adaptive invariance gating, thereby capturing robust modal dependencies rather than spurious correlations. Extensive experiments demonstrate that our method achieves SOTA performance on both public benchmarks and downstream high-level vision tasks. The Code can be available.