# CUPre: Cross-domain Unsupervised Pre-training for Few-Shot Cell Segmentation

arXiv: https://arxiv.org/abs/2310.03981 · HTML: https://mlsanity.com/paper/2310.03981/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 48 references that are in the map.
- First posted on arXiv 6 Oct 2023.

## Builds on (most cited first, 17 of 17)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [ResNeSt: Split-Attention Networks](https://mlsanity.com/paper/2004.08955/) (2020)
- [Cascade R-CNN: High Quality Object Detection and Instance Segmentation](https://mlsanity.com/paper/1906.09756/) (2019)
- [Transfusion: Understanding Transfer Learning for Medical Imaging](https://mlsanity.com/paper/1902.07208/) (2019)
- [Explicit Inductive Bias for Transfer Learning with Convolutional Networks](https://mlsanity.com/paper/1802.01483/) (2018)
- [Neural Image Compression for Gigapixel Histopathology Image Analysis](https://mlsanity.com/paper/1811.02840/) (2018)
- [Self-Supervised Similarity Learning for Digital Pathology](https://mlsanity.com/paper/1905.08139/) (2019)
- [A Unified Framework for Generalized Low-Shot Medical Image Segmentation with Scarce Data](https://mlsanity.com/paper/2110.09260/) (2021)
- [MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts](https://mlsanity.com/paper/2310.02000/) (2023)
- [Few-Shot Microscopy Image Cell Segmentation](https://mlsanity.com/paper/2007.01671/) (2020)
- [Self-Supervised-RCNN for Medical Image Segmentation with Limited Data Annotation](https://mlsanity.com/paper/2207.11191/) (2022)
- [Point-supervised Single-cell Segmentation via Collaborative Knowledge Sharing](https://mlsanity.com/paper/2304.10671/) (2023)

## Built on by (most cited first, 1 of 1)

- [Benefit from public unlabeled data: A Frangi filtering-based pretraining network for 3D cerebrovascular segmentation](https://mlsanity.com/paper/2312.15273/) (2023)

## Abstract (arXiv)

While pre-training on object detection tasks, such as Common Objects in Contexts (COCO) [1], could significantly boost the performance of cell segmentation, it still consumes on massive fine-annotated cell images [2] with bounding boxes, masks, and cell types for every cell in every image, to fine-tune the pre-trained model. To lower the cost of annotation, this work considers the problem of pre-training DNN models for few-shot cell segmentation, where massive unlabeled cell images are available but only a small proportion is annotated. Hereby, we propose Cross-domain Unsupervised Pre-training, namely CUPre, transferring the capability of object detection and instance segmentation for common visual objects (learned from COCO) to the visual domain of cells using unlabeled images. Given a standard COCO pre-trained network with backbone, neck, and head modules, CUPre adopts an alternate multi-task pre-training (AMT2) procedure with two sub-tasks -- in every iteration of pre-training, AMT2 first trains the backbone with cell images from multiple cell datasets via unsupervised momentum contrastive learning (MoCo) [3], and then trains the whole model with vanilla COCO datasets via instance segmentation. After pre-training, CUPre fine-tunes the whole model on the cell segmentation task using a few annotated images. We carry out extensive experiments to evaluate CUPre using LIVECell [2] and BBBC038 [4] datasets in few-shot instance segmentation settings. The experiment shows that CUPre can outperform existing pre-training methods, achieving the highest average precision (AP) for few-shot cell segmentation and detection.