# Unsupervised Mutual Transformer Learning for Multi-Gigapixel Whole Slide Image Classification

arXiv: https://arxiv.org/abs/2305.02032 · HTML: https://mlsanity.com/paper/2305.02032/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 79 references that are in the map.
- First posted on arXiv 3 May 2023.

## Builds on (most cited first, 30 of 39)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019)
- [TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2106.00908/) (2021)
- [Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2011.08939/) (2020)
- [Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning](https://mlsanity.com/paper/2206.02647/) (2022)
- [Keystroke Dynamics as Part of Lifelogging](https://mlsanity.com/paper/2010.10144/) (2020)
- [Graph Self-Supervised Learning: A Survey](https://mlsanity.com/paper/2103.00111/) (2021)
- [DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification](https://mlsanity.com/paper/2203.12081/) (2022)
- [Transformers in Medical Imaging: A Survey](https://mlsanity.com/paper/2201.09873/) (2022)
- [Pathomic Fusion: An Integrated Framework for Fusing Histopathology and Genomic Features for Cancer Diagnosis and Prognosis](https://mlsanity.com/paper/1912.08937/) (2019)
- [Deep neural network models for computational histopathology: A survey](https://mlsanity.com/paper/1912.12378/) (2019)
- [Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification](https://mlsanity.com/paper/1504.07947/) (2015)
- [Self supervised contrastive learning for digital histopathology](https://mlsanity.com/paper/2011.13971/) (2020)
- [Revisiting Multiple Instance Neural Networks](https://mlsanity.com/paper/1610.02501/) (2016)
- [Deep Learning-based Computational Pathology Predicts Origins for Cancers of Unknown Primary](https://mlsanity.com/paper/2006.13932/) (2020)
- [A graph-transformer for whole slide image classification](https://mlsanity.com/paper/2205.09671/) (2022)
- [Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated Histopathological Images](https://mlsanity.com/paper/2001.01599/) (2020)
- [CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentation](https://mlsanity.com/paper/1908.10555/) (2019)
- [Neural Image Compression for Gigapixel Histopathology Image Analysis](https://mlsanity.com/paper/1811.02840/) (2018)
- [Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2103.10626/) (2021)
- [Weakly supervised multiple instance learning histopathological tumor segmentation](https://mlsanity.com/paper/2004.05024/) (2020)
- [Differentiable Zooming for Multiple Instance Learning on Whole-Slide Images](https://mlsanity.com/paper/2204.12454/) (2022)

## Built on by (most cited first, 3 of 3)

- [Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysis](https://mlsanity.com/paper/2509.11526/) (2025)
- [TUMLS: Trustful Fully Unsupervised Multi-Level Segmentation for Whole Slide Images of Histology](https://mlsanity.com/paper/2504.12718/) (2025)
- [Tissue Classification and Whole-Slide Images Analysis via Modeling of the Tumor Microenvironment and Biological Pathways](https://mlsanity.com/paper/2601.08336/) (2026)

## Abstract (arXiv)

Classification of gigapixel Whole Slide Images (WSIs) is an important prediction task in the emerging area of computational pathology. There has been a surge of research in deep learning models for WSI classification with clinical applications such as cancer detection or prediction of molecular mutations from WSIs. Most methods require expensive and labor-intensive manual annotations by expert pathologists. Weakly supervised Multiple Instance Learning (MIL) methods have recently demonstrated excellent performance; however, they still require large slide-level labeled training datasets that need a careful inspection of each slide by an expert pathologist. In this work, we propose a fully unsupervised WSI classification algorithm based on mutual transformer learning. Instances from gigapixel WSI (i.e., image patches) are transformed into a latent space and then inverse-transformed to the original space. Using the transformation loss, pseudo-labels are generated and cleaned using a transformer label-cleaner. The proposed transformer-based pseudo-label generation and cleaning modules mutually train each other iteratively in an unsupervised manner. A discriminative learning mechanism is introduced to improve normal versus cancerous instance labeling. In addition to unsupervised classification, we demonstrate the effectiveness of the proposed framework for weak supervision for cancer subtype classification as downstream analysis. Extensive experiments on four publicly available datasets show excellent performance compared to the state-of-the-art methods. We intend to make the source code of our algorithm publicly available soon.