Zhu Wenhui, Chen Xiwen, Qiu Peijie, Sotiras Aristeidis, Razi Abolfazl, Wang Yalin
Arizona State University, AZ, USA.
Clemson University, SC, USA.
Comput Vis ECCV. 2025;15096:333-351. doi: 10.1007/978-3-031-72920-1_19. Epub 2024 Oct 1.
Multiple instance learning (MIL) stands as a powerful approach in weakly supervised learning, regularly employed in histological whole slide image (WSI) classification for detecting tumorous lesions. However, existing mainstream MIL methods focus on modeling correlation between instances while overlooking the inherent diversity among instances. However, few MIL methods have aimed at diversity modeling, which empirically show inferior performance but with a high computational cost. To bridge this gap, we propose a novel MIL aggregation method based on diverse global representation (DGR-MIL), by modeling diversity among instances through a set of global vectors that serve as a summary of all instances. First, we turn the instance correlation into the similarity between instance embeddings and the predefined global vectors through a cross-attention mechanism. This stems from the fact that similar instance embeddings typically would result in a higher correlation with a certain global vector. Second, we propose two mechanisms to enforce the diversity among the global vectors to be more descriptive of the entire bag: (i) positive instance alignment and (ii) a novel, efficient, and theoretically guaranteed diversification learning paradigm. Specifically, the positive instance alignment module encourages the global vectors to align with the center of positive instances (e.g., instances containing tumors in WSI). To further diversify the global representations, we propose a novel diversification learning paradigm leveraging the determinantal point process. The proposed model outperforms the state-of-the-art MIL aggregation models by a substantial margin on the CAMELYON-16 and the TCGA-lung cancer datasets. The code is available at https://github.com/ChongQingNoSubway/DGR-MIL .
多实例学习（MIL）是弱监督学习中的一种强大方法，常用于组织学全切片图像（WSI）分类以检测肿瘤病变。然而，现有的主流MIL方法侧重于对实例之间的相关性进行建模，而忽略了实例之间固有的多样性。然而，很少有MIL方法致力于多样性建模，经验表明这些方法性能较差且计算成本高。为了弥补这一差距，我们提出了一种基于多样全局表示的新型MIL聚合方法（DGR-MIL），通过一组作为所有实例摘要的全局向量对实例之间的多样性进行建模。首先，我们通过交叉注意力机制将实例相关性转化为实例嵌入与预定义全局向量之间的相似性。这是因为相似的实例嵌入通常会与某个全局向量产生更高的相关性。其次，我们提出了两种机制来加强全局向量之间的多样性，使其更能描述整个包：（i）正实例对齐和（ii）一种新颖、高效且理论上有保证的多样化学习范式。具体来说，正实例对齐模块鼓励全局向量与正实例的中心对齐（例如，WSI中包含肿瘤的实例）。为了进一步使全局表示多样化，我们提出了一种利用行列式点过程的新型多样化学习范式。在CAMELYON-16和TCGA肺癌数据集上，所提出的模型比现有最先进的MIL聚合模型有显著的性能提升。代码可在https://github.com/ChongQingNoSubway/DGR-MIL获取。
