SGPMIL: Sparse Gaussian Process Multiple Instance Learning

TL;DR

SGPMIL introduces a probabilistic MIL framework based on Sparse Gaussian Processes that quantifies uncertainty in instance relevance, improving interpretability and reliability in digital pathology applications.

Contribution

It is the first to incorporate uncertainty quantification into attention-based MIL using Sparse Gaussian Processes, enhancing interpretability and efficiency.

Findings

Improved instance-level relevance maps with uncertainty estimates.

Maintains competitive bag-level classification performance.

Faster training and better efficiency due to feature scaling in SGP.

Abstract

Multiple Instance Learning (MIL) offers a natural solution for settings where only coarse, bag-level labels are available, without having access to instance-level annotations. This is usually the case in digital pathology, which consists of gigapixel-sized images. While deterministic attention-based MIL approaches achieve strong bag-level performance, they often overlook the uncertainty inherent in instance relevance. In this paper, we address the lack of uncertainty quantification in instance-level attention scores by introducing SGPMIL, a new probabilistic attention-based MIL framework grounded in Sparse Gaussian Processes (SGP). By learning a posterior distribution over attention scores, SGPMIL enables principled uncertainty estimation, resulting in more reliable and calibrated instance relevance maps. Our approach not only preserves competitive bag-level performance but also significantly improves the quality and interpretability of instance-level predictions under uncertainty. SGPMIL extends prior work by introducing feature scaling in the SGP predictive mean function, leading to faster training, improved efficiency, and enhanced instance-level performance. Extensive experiments on multiple well-established digital pathology datasets highlight the effectiveness of our approach across both bag- and instance-level evaluations. Our code is available at https://github.com/mandlos/SGPMIL.