# InsMix: Towards Realistic Generative Data Augmentation for Nuclei Instance Segmentation

arXiv: https://arxiv.org/abs/2206.15134 · HTML: https://mlsanity.com/paper/2206.15134/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 30 Jun 2022.

## Builds on (most cited first, 20 of 20)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Images](https://mlsanity.com/paper/1812.06499/) (2018)
- [Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection](https://mlsanity.com/paper/1708.01642/) (2017)
- [Modeling Visual Context is Key to Augmenting Object Detection Datasets](https://mlsanity.com/paper/1807.07428/) (2018)
- [InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting](https://mlsanity.com/paper/1908.07801/) (2019)
- [CIA-Net: Robust Nuclei Instance Segmentation with Contour-aware Information Aggregation](https://mlsanity.com/paper/1903.05358/) (2019)
- [Deep Semi-supervised Knowledge Distillation for Overlapping Cervical Cell Instance Segmentation](https://mlsanity.com/paper/2007.10787/) (2020)
- [Instance-aware Self-supervised Learning for Nuclei Segmentation](https://mlsanity.com/paper/2007.11186/) (2020)
- [A Deep Learning Algorithm for One-step Contour Aware Nuclei Segmentation of Histopathological Images](https://mlsanity.com/paper/1803.02786/) (2018)
- [IRNet: Instance Relation Network for Overlapping Cervical Cell Segmentation](https://mlsanity.com/paper/1908.06623/) (2019)
- [Boundary-assisted Region Proposal Networks for Nucleus Segmentation](https://mlsanity.com/paper/2006.02695/) (2020)

## Built on by (most cited first, 19 of 19)

- [DiffMix: Diffusion Model-based Data Synthesis for Nuclei Segmentation and Classification in Imbalanced Pathology Image Datasets](https://mlsanity.com/paper/2306.14132/) (2023)
- [A Survey on Mixup Augmentations and Beyond](https://mlsanity.com/paper/2409.05202/) (2024)
- [Label-Efficient Deep Learning in Medical Image Analysis: Challenges and Future Directions](https://mlsanity.com/paper/2303.12484/) (2023)
- [Backdoor Attack and Defense in Federated Generative Adversarial Network-based Medical Image Synthesis](https://mlsanity.com/paper/2210.10886/) (2022)
- [Deep Learning in Breast Cancer Imaging: A Decade of Progress and Future Directions](https://mlsanity.com/paper/2304.06662/) (2023)
- [Co-synthesis of Histopathology Nuclei Image-Label Pairs using a Context-Conditioned Joint Diffusion Model](https://mlsanity.com/paper/2407.14434/) (2024)
- [TRACE: Temporally Reliable Anatomically-Conditioned 3D CT Generation with Enhanced Efficiency](https://mlsanity.com/paper/2507.00802/) (2025)
- [Realistic Data Enrichment for Robust Image Segmentation in Histopathology](https://mlsanity.com/paper/2304.09534/) (2023)
- [LesionMix: A Lesion-Level Data Augmentation Method for Medical Image Segmentation](https://mlsanity.com/paper/2308.09026/) (2023)
- [Data efficient deep learning for medical image analysis: A survey](https://mlsanity.com/paper/2310.06557/) (2023)
- [Content Generation Models in Computational Pathology: A Comprehensive Survey on Methods, Applications, and Challenges](https://mlsanity.com/paper/2505.10993/) (2025)
- [Prompt-Guided Foundation Model Tuning for Pathology Image Classification](https://mlsanity.com/paper/2403.12537/) (2024)
- [URCDM: Ultra-Resolution Image Synthesis in Histopathology](https://mlsanity.com/paper/2407.13277/) (2024)
- [CellMix: A General Instance Relationship based Method for Data Augmentation Towards Pathology Image Classification](https://mlsanity.com/paper/2301.11513/) (2023)
- [USegMix: Unsupervised Segment Mix for Efficient Data Augmentation in Pathology Images](https://mlsanity.com/paper/2502.16160/) (2025)
- [A Survey on Cell Nuclei Instance Segmentation and Classification: Leveraging Context and Attention](https://mlsanity.com/paper/2407.18673/) (2024)
- [Weak-to-Strong Generalization Enables Fully Automated De Novo Training of Multi-head Mask-RCNN Model for Segmenting Densely Overlapping Cell Nuclei in Multiplex Whole-slice Brain Images](https://mlsanity.com/paper/2512.11722/) (2025)
- [SegMix:Shuffle-based Feedback Learning for Semantic Segmentation of Pathology Images](https://mlsanity.com/paper/2604.15777/) (2026)
- [NucEval: A Robust Evaluation Framework for Nuclear Instance Segmentation](https://mlsanity.com/paper/2605.03144/) (2026)

## Abstract (arXiv)

Nuclei Segmentation from histology images is a fundamental task in digital pathology analysis. However, deep-learning-based nuclei segmentation methods often suffer from limited annotations. This paper proposes a realistic data augmentation method for nuclei segmentation, named InsMix, that follows a Copy-Paste-Smooth principle and performs morphology-constrained generative instance augmentation. Specifically, we propose morphology constraints that enable the augmented images to acquire luxuriant information about nuclei while maintaining their morphology characteristics (e.g., geometry and location). To fully exploit the pixel redundancy of the background and improve the model's robustness, we further propose a background perturbation method, which randomly shuffles the background patches without disordering the original nuclei distribution. To achieve contextual consistency between original and template instances, a smooth-GAN is designed with a foreground similarity encoder (FSE) and a triplet loss. We validated the proposed method on two datasets, i.e., Kumar and CPS datasets. Experimental results demonstrate the effectiveness of each component and the superior performance achieved by our method to the state-of-the-art methods.