# CLoPA: Continual Low Parameter Adaptation of Interactive Segmentation for Medical Image Annotation

arXiv: https://arxiv.org/abs/2603.06426 · HTML: https://mlsanity.com/paper/2603.06426/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 17 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 12 of 12)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [A survey of loss functions for semantic segmentation](https://mlsanity.com/paper/2006.14822/) (2020)
- [SegVol: Universal and Interactive Volumetric Medical Image Segmentation](https://mlsanity.com/paper/2311.13385/) (2023)
- [ScribblePrompt: Fast and Flexible Interactive Segmentation for Any Biomedical Image](https://mlsanity.com/paper/2312.07381/) (2023)
- [nnInteractive: Redefining 3D Promptable Segmentation](https://mlsanity.com/paper/2503.08373/) (2025)
- [MultiverSeg: Scalable Interactive Segmentation of Biomedical Imaging Datasets with In-Context Guidance](https://mlsanity.com/paper/2412.15058/) (2024)
- [You Point, I Learn: Online Adaptation of Interactive Segmentation Models for Handling Distribution Shifts in Medical Imaging](https://mlsanity.com/paper/2503.06717/) (2025)
- [A methodology for clinically driven interactive segmentation evaluation](https://mlsanity.com/paper/2510.09499/) (2025)

## Abstract (arXiv)

Interactive segmentation enables clinicians to guide annotation, but existing zero-shot models like nnInteractive fail to consistently reach expert-level performance across diverse medical imaging tasks. Because annotation campaigns produce a growing stream of task-specific labelled data, online adaptation of the segmentation model is a natural complement to zero-shot inference. We propose CLoPA, a continual adaptation strategy that tunes a small fraction of nnInteractive's parameters on the annotation cache, triggered by lightweight episode scheduling. CLoPA requires no new parameters or changes to the inference pipeline, and operates entirely within the existing annotation workflow. Across eight Medical Segmentation Decathlon tasks spanning diverse anatomical targets and imaging characteristics, CLoPA rapidly elevates performance to expert-level, even for tasks where nnInteractive previously failed, with the majority of gains realised after a single training episode. We show that the benefits of tuning different parameter groups depends on task characteristics and data regimes. Also, that for targets with complex geometries (e.g., hepatic vessels), instance normalisation and low-level feature tuning saturates, suggesting a need for deeper feature-representation alignment in the most challenging scenarios.