# Aggregation Schemes for Single-Vector WSI Representation Learning in Digital Pathology

arXiv: https://arxiv.org/abs/2501.17822 · HTML: https://mlsanity.com/paper/2501.17822/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 29 references that are in the map.
- First posted on arXiv 29 Jan 2025.

## Builds on (most cited first, 15 of 15)

- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [PRISM: A Multi-Modal Generative Foundation Model for Slide-Level Histopathology](https://mlsanity.com/paper/2405.10254/) (2024)
- [Molecular-driven Foundation Model for Oncologic Pathology](https://mlsanity.com/paper/2501.16652/) (2025)
- [Yottixel -- An Image Search Engine for Large Archives of Histopathology Whole Slide Images](https://mlsanity.com/paper/1911.08748/) (2019)
- [Representation Learning of Histopathology Images using Graph Neural Networks](https://mlsanity.com/paper/2004.07399/) (2020)
- [On Image Search in Histopathology](https://mlsanity.com/paper/2401.08699/) (2024)
- [Deep Quantization: Encoding Convolutional Activations with Deep Generative Model](https://mlsanity.com/paper/1611.09502/) (2016)
- [Learning Permutation Invariant Representations using Memory Networks](https://mlsanity.com/paper/1911.07984/) (2019)
- [Learning Binary and Sparse Permutation-Invariant Representations for Fast and Memory Efficient Whole Slide Image Search](https://mlsanity.com/paper/2208.13653/) (2022)
- [Analysis and Validation of Image Search Engines in Histopathology](https://mlsanity.com/paper/2401.03271/) (2024)
- [Adversarial Fisher Vectors for Unsupervised Representation Learning](https://mlsanity.com/paper/1910.13101/) (2019)
- [Pay Attention with Focus: A Novel Learning Scheme for Classification of Whole Slide Images](https://mlsanity.com/paper/2106.06623/) (2021)
- [Are the Latent Representations of Foundation Models for Pathology Invariant to Rotation?](https://mlsanity.com/paper/2412.11938/) (2024)

## Abstract (arXiv)

A crucial step to efficiently integrate Whole Slide Images (WSIs) in computational pathology is assigning a single high-quality feature vector, i.e., one embedding, to each WSI. With the existence of many pre-trained deep neural networks and the emergence of foundation models, extracting embeddings for sub-images (i.e., tiles or patches) is straightforward. However, for WSIs, given their high resolution and gigapixel nature, inputting them into existing GPUs as a single image is not feasible. As a result, WSIs are usually split into many patches. Feeding each patch to a pre-trained model, each WSI can then be represented by a set of patches, hence, a set of embeddings. Hence, in such a setup, WSI representation learning reduces to set representation learning where for each WSI we have access to a set of patch embeddings. To obtain a single embedding from a set of patch embeddings for each WSI, multiple set-based learning schemes have been proposed in the literature. In this paper, we evaluate the WSI search performance of multiple recently developed aggregation techniques (mainly set representation learning techniques) including simple average or max pooling operations, Deep Sets, Memory networks, Focal attention, Gaussian Mixture Model (GMM) Fisher Vector, and deep sparse and binary Fisher Vector on four different primary sites including bladder, breast, kidney, and Colon from TCGA. Further, we benchmark the search performance of these methods against the median of minimum distances of patch embeddings, a non-aggregating approach used for WSI retrieval.