DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification

Wenhui Zhu*, Xiwen Chen*, Peijie Qiu*, Aristeidis Sotiras, Abolfazl Razi, Yalin Wang

Abstract: Multiple instance learning (MIL) stands as a powerful ap- proach in weakly supervised learning, regularly employed in histolog- ical whole slide image (WSI) classification for detecting tumorous le- sions. 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 ag- gregation 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 pre- defined 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 encour- ages the global vectors to align with the center of positive instances (e.g., instances containing tumors in WSI). To further diversify the global rep- resentations, we propose a novel diversification learning paradigm lever- aging 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.