Exploiting Low-Dimensional Manifold of Features for Few-Shot Whole Slide Image Classification

TL;DR

This paper introduces a geometry-aware residual module called the Manifold Residual (MR) block, which preserves the low-dimensional feature manifold in few-shot Whole Slide Image classification, leading to improved performance with fewer parameters.

Contribution

The paper proposes the MR block, a novel plug-and-play module that maintains feature manifold geometry and enhances few-shot WSI classification.

Findings

Achieves state-of-the-art results on few-shot WSI tasks.

Reduces model complexity with fewer parameters.

Demonstrates the importance of geometry-aware modules in medical imaging.

Abstract

Few-shot Whole Slide Image (WSI) classification is severely hampered by overfitting. We argue that this is not merely a data-scarcity issue but a fundamentally geometric problem. Grounded in the manifold hypothesis, our analysis shows that features from pathology foundation models exhibit a low-dimensional manifold geometry that is easily perturbed by downstream models. This insight reveals a key potential issue in downstream multiple instance learning models: linear layers are geometry-agnostic and, as we show empirically, can distort the manifold geometry of the features. To address this, we propose the Manifold Residual (MR) block, a plug-and-play module that is explicitly geometry-aware. The MR block reframes the linear layer as residual learning and decouples it into two pathways: (1) a fixed, random matrix serving as a geometric anchor that approximately preserves topology while also acting as a spectral shaper to sharpen the feature spectrum; and (2) a trainable, low-rank residual pathway that acts as a residual learner for task-specific adaptation, with its structural bottleneck explicitly mirroring the low effective rank of the features. This decoupling imposes a structured inductive bias and reduces learning to a simpler residual fitting task. Through extensive experiments, we demonstrate that our approach achieves state-of-the-art results with significantly fewer parameters, offering a new paradigm for few-shot WSI classification. Code is available in https://github.com/BearCleverProud/MR-Block.