Nonparametric Distribution Matching for Self-Supervised Whole-Slide Image Condensation

Duong M. Nguyen, Trong Nghia Hoang, Hang Thi Nguyen, Thanh Trung Huynh, Phi Le Nguyen, Minh N. Do

Keywords: data condensation, histology image, probabilistic inference, nonparametric prior

TL;DR: This paper introduces NICER, a novel framework that enables scalable WSI learning by condensing slides through distribution-aware feature matching with nonparametric point process prior, improving accuracy and efficiency over prior heuristic methods.

Abstract: Histological whole-slide images (WSIs) are central to computational pathology but pose severe computational challenges due to their extremely high resolution, often spanning several gigabytes per slide. To enable scalable learning, existing methods apply self-supervised data condensation to reduce computational cost, but typically rely on heuristic prototype learning and do not explicitly preserve learning-relevant feature distributions for downstream tasks. In response, we introduce a principled reformulation of WSI condensation as a distribution-matching problem under a fixed representational lens, and develop a tractable approximation based on a nonparametric prior with slide-adaptive capacity. Experiments on five histopathology datasets, together with clinical evaluation from a board-certified pathologist, show that NICER consistently outperforms prior methods, achieving an average accuracy improvement of 7.44% while offering improved efficiency–accuracy trade-offs, highlighting the benefits of principled, distribution-aware condensation for scalable histological representation learning.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 192