# Knowing What to Label for Few Shot Microscopy Image Cell Segmentation

arXiv: https://arxiv.org/abs/2211.10244 · HTML: https://mlsanity.com/paper/2211.10244/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 44 references that are in the map.
- First posted on arXiv 18 Nov 2022.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [3D Self-Supervised Methods for Medical Imaging](https://mlsanity.com/paper/2006.03829/) (2020)
- [Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation](https://mlsanity.com/paper/2007.09886/) (2020)
- [UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation](https://mlsanity.com/paper/2107.00781/) (2021)
- [Cost-Effective Active Learning for Melanoma Segmentation](https://mlsanity.com/paper/1711.09168/) (2017)
- [Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning](https://mlsanity.com/paper/1810.12241/) (2018)
- [Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate](https://mlsanity.com/paper/1910.04858/) (2019)
- [Self-Supervised Learning for Spinal MRIs](https://mlsanity.com/paper/1708.00367/) (2017)
- [Few-Shot Microscopy Image Cell Segmentation](https://mlsanity.com/paper/2007.01671/) (2020)
- [MetaMedSeg: Volumetric Meta-learning for Few-Shot Organ Segmentation](https://mlsanity.com/paper/2109.09734/) (2021)
- [Edge-Based Self-Supervision for Semi-Supervised Few-Shot Microscopy Image Cell Segmentation](https://mlsanity.com/paper/2208.02105/) (2022)

## Built on by (most cited first, 2 of 2)

- [One-shot and Partially-Supervised Cell Image Segmentation Using Small Visual Prompt](https://mlsanity.com/paper/2304.07991/) (2023)
- [SelectNAdapt: Support Set Selection for Few-Shot Domain Adaptation](https://mlsanity.com/paper/2308.04946/) (2023)

## Abstract (arXiv)

In microscopy image cell segmentation, it is common to train a deep neural network on source data, containing different types of microscopy images, and then fine-tune it using a support set comprising a few randomly selected and annotated training target images. In this paper, we argue that the random selection of unlabelled training target images to be annotated and included in the support set may not enable an effective fine-tuning process, so we propose a new approach to optimise this image selection process. Our approach involves a new scoring function to find informative unlabelled target images. In particular, we propose to measure the consistency in the model predictions on target images against specific data augmentations. However, we observe that the model trained with source datasets does not reliably evaluate consistency on target images. To alleviate this problem, we propose novel self-supervised pretext tasks to compute the scores of unlabelled target images. Finally, the top few images with the least consistency scores are added to the support set for oracle (i.e., expert) annotation and later used to fine-tune the model to the target images. In our evaluations that involve the segmentation of five different types of cell images, we demonstrate promising results on several target test sets compared to the random selection approach as well as other selection approaches, such as Shannon's entropy and Monte-Carlo dropout.