# Domain Adversarial RetinaNet as a Reference Algorithm for the MItosis DOmain Generalization Challenge

arXiv: https://arxiv.org/abs/2108.11269 · HTML: https://mlsanity.com/paper/2108.11269/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 15 references that are in the map.
- First posted on arXiv 25 Aug 2021.

## Builds on (most cited first, 6 of 6)

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Quantifying the Scanner-Induced Domain Gap in Mitosis Detection](https://mlsanity.com/paper/2103.16515/) (2021)
- [Are pathologist-defined labels reproducible? Comparison of the TUPAC16 mitotic figure dataset with an alternative set of labels](https://mlsanity.com/paper/2007.05351/) (2020)
- [Deep Learning-Based Quantification of Pulmonary Hemosiderophages in Cytology Slides](https://mlsanity.com/paper/1908.04767/) (2019)

## Built on by (most cited first, 10 of 10)

- [Self-supervised Pseudo Multi-class Pre-training for Unsupervised Anomaly Detection and Segmentation in Medical Images](https://mlsanity.com/paper/2109.01303/) (2021)
- [A Systematic Review of Generalization Research in Medical Image Classification](https://mlsanity.com/paper/2403.12167/) (2024)
- [Mitosis Detection, Fast and Slow: Robust and Efficient Detection of Mitotic Figures](https://mlsanity.com/paper/2208.12587/) (2022)
- [Multi-Scanner Canine Cutaneous Squamous Cell Carcinoma Histopathology Dataset](https://mlsanity.com/paper/2301.04423/) (2023)
- [Domain-Robust Mitotic Figure Detection with Style Transfer](https://mlsanity.com/paper/2109.01124/) (2021)
- [Characterizing the Features of Mitotic Figures Using a Conditional Diffusion Probabilistic Model](https://mlsanity.com/paper/2310.03893/) (2023)
- [Improving Mitosis Detection Via UNet-based Adversarial Domain Homogenizer](https://mlsanity.com/paper/2209.09193/) (2022)
- [A bag of tricks for real-time Mitotic Figure detection](https://mlsanity.com/paper/2508.19804/) (2025)
- [MIDOG 2025: Mitotic Figure Detection with Attention-Guided False Positive Correction](https://mlsanity.com/paper/2509.02598/) (2025)
- [MiTHras: Task-specific Hierarchical Semi-supervised Contrastive Masked Autoencoder for Mitotic Figure Analysis](https://mlsanity.com/paper/2609.24736/) (2026)

## Abstract (arXiv)

Assessing the Mitotic Count has a known high degree of intra- and inter-rater variability. Computer-aided systems have proven to decrease this variability and reduce labeling time. These systems, however, are generally highly dependent on their training domain and show poor applicability to unseen domains. In histopathology, these domain shifts can result from various sources, including different slide scanning systems used to digitize histologic samples. The MItosis DOmain Generalization challenge focused on this specific domain shift for the task of mitotic figure detection. This work presents a mitotic figure detection algorithm developed as a baseline for the challenge, based on domain adversarial training. On the challenge's test set, the algorithm scored an F1 score of 0.7183. The corresponding network weights and code for implementing the network are made publicly available.