CoRiM：面向动态多模态融合的冲突驱动风险最小化
CoRiM: Conflict-driven Risk Minimization for Dynamic Multimodal Fusion
提出一种基于模态冲突风险最小化的动态融合范式，其可微风险函数与 Frank-Wolfe 优化框架可被视觉多模态任务（如多模态检测、分割）直接复用，以提升在模态冲突或噪声环境下的鲁棒性。
原文依据 we propose a Conflict-driven Risk Minimization (CoRiM) dynamic fusion paradigm
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论动态多模态融合方法缺乏处理模态冲突和数据质量不一致的鲁棒理论指导。尽管近期的理论工作将模态权重与损失或置信度等标量关联，但这种范式难以全面应对跨模态预测分布不一致所带来的风险。本文提出了一种冲突驱动风险最小化（CoRiM）动态融合范式。具体而言，我们将动态融合重新定义为一个有原则的、逐样本的直接风险最小化任务。为此，我们首先设计了一种新颖的可微模态冲突风险（MCR）函数 \mathcal{R}(w)，通过直接建模融合不确定性和模态间一致性来量化风险。其次，我们指出最小化 \mathcal{R}(w) 本质上是在概率单纯形上的非凸约束优化问题。为了高效解决这一特定挑战，我们创新性地引入了无投影 Frank-Wolfe（FW）算法，因为它非常适合单纯形上的优化。我们证明了所设计的 \mathcal{R}(w) 具有 L-平滑性，这为 FW 算法在我们的非凸目标上的收敛性提供了理论保证。在多个基准数据集上的大量实验表明，CoRiM 在高冲突和噪声环境下优于当前最优方法，验证了该方法的鲁棒性。
英文原文摘要 1474 字符
Dynamic multimodal fusion methods lack robust theoretical guidance for handling modal conflicts and inconsistent data quality. While recent theoretical work has associated modal weights with scalar quantities such as loss or confidence, this paradigm struggles to comprehensively address the risks caused by inconsistent predictive distributions across modalities. In this paper, we propose a **Co**nflict-driven **Ri**sk **M**inimization (**CoRiM**) dynamic fusion paradigm. Specifically, we redefine dynamic fusion as a principled, per-sample, direct risk minimization task. To this end, we first design a novel, differentiable Modality Conflict Risk (MCR) function, \mathcal R (w), which quantifies risk by directly modeling fused uncertainty and inter-modal consistency. Second, we identify that minimizing \mathcal R (w) is fundamentally a non-convex constrained optimization problem over the probabilistic simplex. To efficiently solve this specific challenge, we innovatively introduce the projection free Frank-Wolfe (FW) algorithm, as it is perfectly suited for optimization on the simplex.We prove that our designed \mathcal R (w) possesses L-smoothness, which provides theoretical guarantees for the convergence of the FW algorithm on our non-convex objective. Extensive experiments on multiple benchmark datasets demonstrate that CoRiM outperforms current state-of-the-art methods in high-conflict and noisy environments, validating the robustness of our method.