面向多视图聚类的簇感知锚框学习
Cluster-aware Anchor Learning for Multi-View Clustering
把锚框数量从全局固定改为按簇自适应分配，并用 l2,1 列稀疏自动决定每簇保留多少锚框，这一思路可直接迁移到视觉中的大规模聚类、检索与表征压缩场景，例如对多视图/多模态视觉特征做可扩展聚类时替代固定锚框的 k-means 类方法。
原文依据 CAL imposes an l2,1-norm column-sparsity penalty on each group to suppress redundancy and preserve cluster-discriminative 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基于锚框的多视图聚类因其高效性而颇具吸引力，但大多数方法先验地固定锚框数量，隐含假设各簇的需求一致。实际上，各簇在信息丰富度、规模和内在结构上存在差异，这促使我们采用按簇自适应的锚框分配。我们提出簇感知锚框学习（CAL），它学习一个共识锚框矩阵，并将其列组织为簇特定的锚框组。CAL 对每个组施加 l2,1 范数列稀疏惩罚以抑制冗余并保留簇判别性特征，从而自动确定每个簇保留多少锚框。为进一步增强可分性，CAL 引入簇间正则化，约束各组之间的关系，促进相互差异性。这种数据驱动的设计学习到更高质量、簇感知的锚框，并在多个视图上产生更具判别性的表征矩阵。在多个基准上的大量实验表明，CAL 优于最优的多视图聚类方法，展现出更优的有效性、鲁棒性以及对异质簇结构的适应性。
英文原文摘要 1190 字符
Anchor-based multi-view clustering is attractive for its efficiency, yet most methods fix the number of anchors a priori, implicitly assuming uniform needs across clusters. In practice, clusters differ in information richness, scale, and intrinsic structure, motivating adaptive per-cluster anchor allocation. We propose Cluster-aware Anchor Learning (CAL), which learns a consensus anchor matrix and organizes its columns into cluster-specific anchor groups. CAL imposes an l2,1-norm column-sparsity penalty on each group to suppress redundancy and preserve cluster-discriminative features, thereby automatically determining how many anchors each cluster retains. To further enhance separability, CAL introduces an inter-cluster regularization that constrains relationships among groups, promoting mutual dissimilarity. This data-driven design learns higher-quality, cluster-aware anchors and yields a more discriminative representation matrix across multiple views. Extensive experiments on multiple benchmarks show that CAL outperforms state-of-the-art multi-view clustering methods, demonstrating superior effectiveness, robustness, and adaptability to heterogeneous cluster structures.