# Supervision and Source Domain Impact on Representation Learning: A Histopathology Case Study

arXiv: https://arxiv.org/abs/2005.08629 · HTML: https://mlsanity.com/paper/2005.08629/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2020.

## Built on by (most cited first, 6 of 6)

- [Towards better understanding and better generalization of few-shot classification in histology images with contrastive learning](https://mlsanity.com/paper/2202.09059/) (2022)
- [Learning to Predict RNA Sequence Expressions from Whole Slide Images with Applications for Search and Classification](https://mlsanity.com/paper/2203.13997/) (2022)
- [Spectral, Probabilistic, and Deep Metric Learning: Tutorial and Survey](https://mlsanity.com/paper/2201.09267/) (2022)
- [Hospital-Agnostic Image Representation Learning in Digital Pathology](https://mlsanity.com/paper/2204.02404/) (2022)
- [Classification of Microscopy Images of Breast Tissue: Region Duplication based Self-Supervision vs. Off-the Shelf Deep Representations](https://mlsanity.com/paper/2202.06073/) (2022)
- [Attention-based Dynamic Subspace Learners for Medical Image Analysis](https://mlsanity.com/paper/2206.09068/) (2022)

## Abstract (arXiv)

As many algorithms depend on a suitable representation of data, learning unique features is considered a crucial task. Although supervised techniques using deep neural networks have boosted the performance of representation learning, the need for a large set of labeled data limits the application of such methods. As an example, high-quality delineations of regions of interest in the field of pathology is a tedious and time-consuming task due to the large image dimensions. In this work, we explored the performance of a deep neural network and triplet loss in the area of representation learning. We investigated the notion of similarity and dissimilarity in pathology whole-slide images and compared different setups from unsupervised and semi-supervised to supervised learning in our experiments. Additionally, different approaches were tested, applying few-shot learning on two publicly available pathology image datasets. We achieved high accuracy and generalization when the learned representations were applied to two different pathology datasets.