DF^2-VB：面向多视图多标签分类的双层模糊融合与视图特定提升
DF^2-VB: Dual-level Fuzzy Fusion with View-specific Boosting for Multi-view Multi-label Classification
论文提出的特征级与决策级双层融合框架（模糊动态融合 + 视图特定提升）可直接迁移到多模态/多视图视觉任务中，例如多视角图像分类、多传感器融合识别，为如何联合利用互补特征与各视图预测提供可复用的融合范式。
原文依据 we propose DF^2-VB, a dual-level fusion framework that jointly exploits complementary strengths to mitigate their respective weaknesses by integrating feature- and decision-level fusion
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视图多标签分类（MVMLC）旨在同时利用共识信息与互补信息来预测样本可能相关的标签。现有的 MVMLC 方法通常聚焦于特征级融合或决策级融合中的一种：前者整合互补特征以获得更具表达力的表示，后者聚合各视图特定的预测以更有效地利用标签监督。事实上，仅依赖特征级融合往往未能充分利用标签信息，并限制了所学表示的可判别性；而纯粹的决策级融合对视图表示的表达能力关注不足，从而制约了分类性能。为解决这些局限，我们提出 DF^2-VB，一个双层融合框架，通过整合特征级与决策级融合，联合发挥二者的互补优势以缓解各自的不足。在特征级，模糊动态融合（FDF）模块将共识特征映射到更兼容的模糊特征空间，在其中识别关键特征并抑制冗余特征，从而进一步融合出具有表达力的共识表示，并提升用于决策级融合的视图特定预测。在决策级，视图特定提升（VB）策略自适应地度量样本与视图特定预测的重要性，以加强对监督的利用，进而促进特征级融合中的可判别性。作为补充，FDF 与 VB 共同增强模型的表达力与可判别性，从而获得可靠的预测。在多个公开数据集上的大量实验验证了我们的策略优于先进的 MVMLC 模型。
英文原文摘要 1738 字符
Multi-view multi-label classification (MVMLC) aims to utilize both consensus and complementarity information to predict potentially relevant labels for samples. Existing MVMLC approaches typically focus on either feature-level fusion, which integrates complementary features for more expressive representations, or decision-level fusion, which aggregates view-specific predictions to exploit label supervision more effectively. In fact, relying solely on feature-level fusion often underutilizes label information and limits discriminability of learned representations, whereas pure decision-level fusion pays insufficient attention to view representation expressiveness and thus constrains classification performance. To address these limitations, we propose DF^2-VB, a dual-level fusion framework that jointly exploits complementary strengths to mitigate their respective weaknesses by integrating feature- and decision-level fusion. At the feature level, a Fuzzy Dynamic Fusion (FDF) module maps consensus features into a more compatible fuzzy feature space, where essential features are identified and redundant features are suppressed to further fuse an expressive consensus representation and boost view-specific predictions for decision-level fusion. At the decision level, a View-specific Boosting (VB) strategy adaptively measures the importance of samples and view-specific predictions to strengthen the utilization of supervision for facilitating the discriminability in feature-level fusion. Complementarily, FDF and VB jointly reinforce the model expressiveness and discriminability for reliable predictions. Extensive experiments on multiple public datasets verify the superiority of our strategy over advanced MVMLC models.