2022/12/28 by Matthew Keaton, Keaton, Matthew, Ram Zaveri +3 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · #AI in cancer detection #Adaptation (eye) #Annotation #Artificial intelligence #Cell Image Analysis Techniques #Classifier (UML) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Data mining #Domain (mathematical analysis) #Domain adaptation #FOS: Computer and information sciences #Labeled data #Leverage (statistics) #Machine learning #Molecular Biology Techniques and Applications #Process (computing) #Retraining #Segmentation #Training set #cs.CV
paper · pdf · doi:10.48550/arxiv.2212.14121
published in arXiv (Cornell University) (Cornell University) · Accepted in WACV 2023
arxiv created 2022/12/28 · openalex publication_date 2022/12/28 · arxiv updated 2023/01/02 · openalex created_date 2023/01/06 · openalex updated_date 2026/07/28
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.