CellTranspose: Few-shot Domain Adaptation for Cellular Instance Segmentation

TL;DR

CellTranspose introduces a few-shot domain adaptation method for cellular instance segmentation that requires minimal annotated data and training time, effectively handling novel data distributions with high accuracy.

Contribution

The paper presents a novel contrastive loss-based approach for few-shot domain adaptation in cellular segmentation, reducing data and training requirements.

Findings

3 to 5 annotations achieve high accuracy

Mitigates covariate shift effectively

Matches or surpasses other adaptation methods

Abstract

Automated cellular instance segmentation is a process utilized for accelerating biological research for the past two decades, and recent advancements have produced higher quality results with less effort from the biologist. Most current endeavors focus on completely cutting the researcher out of the picture by generating highly generalized models. However, these models invariably fail when faced with novel data, distributed differently than the ones used for training. Rather than approaching the problem with methods that presume the availability of large amounts of target data and computing power for retraining, in this work we address the even greater challenge of designing an approach that requires minimal amounts of new annotated data as well as training time. We do so by designing specialized contrastive losses that leverage the few annotated samples very efficiently. A large set of results show that 3 to 5 annotations lead to models with accuracy that: 1) significantly mitigate the covariate shift effects; 2) matches or surpasses other adaptation methods; 3) even approaches methods that have been fully retrained on the target distribution. The adaptation training is only a few minutes, paving a path towards a balance between model performance, computing requirements and expert-level annotation needs.