# From Human Corrections to Learned Segmentations: A Critical Mathematical Review of Information, Learning, and Human Effort

arXiv: https://arxiv.org/abs/2610.20396 · HTML: https://mlsanity.com/paper/2610.20396/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 78 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Builds on (most cited first, 30 of 34)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Performative Prediction](https://mlsanity.com/paper/2002.06673/) (2020)
- [A Probabilistic U-Net for Segmentation of Ambiguous Images](https://mlsanity.com/paper/1806.05034/) (2018)
- [Time-uniform, nonparametric, nonasymptotic confidence sequences](https://mlsanity.com/paper/1810.08240/) (2018)
- [Learning from positive and unlabeled data: a survey](https://mlsanity.com/paper/1811.04820/) (2018)
- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [Interactive Learning from Policy-Dependent Human Feedback](https://mlsanity.com/paper/1701.06049/) (2017)
- [Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning](https://mlsanity.com/paper/1710.04043/) (2017)
- [SimpleClick: Interactive Image Segmentation with Simple Vision Transformers](https://mlsanity.com/paper/2210.11006/) (2022)
- [Large-scale interactive object segmentation with human annotators](https://mlsanity.com/paper/1903.10830/) (2019)
- [FocalClick: Towards Practical Interactive Image Segmentation](https://mlsanity.com/paper/2204.02574/) (2022)
- [Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty](https://mlsanity.com/paper/2006.06015/) (2020)
- [On Statistical Bias In Active Learning: How and When To Fix It](https://mlsanity.com/paper/2101.11665/) (2021)
- [The Description Length of Deep Learning Models](https://mlsanity.com/paper/1802.07044/) (2018)
- [CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation](https://mlsanity.com/paper/1810.09726/) (2018)
- [Iterative Machine Teaching](https://mlsanity.com/paper/1705.10470/) (2017)
- [MONAI Label: A framework for AI-assisted Interactive Labeling of 3D Medical Images](https://mlsanity.com/paper/2203.12362/) (2022)
- [Minimum Description Length Revisited](https://mlsanity.com/paper/1908.08484/) (2019)
- [SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories](https://mlsanity.com/paper/2503.08625/) (2025)
- [Deep Interactive Segmentation of Medical Images: A Systematic Review and Taxonomy](https://mlsanity.com/paper/2311.13964/) (2023)
- [Towards Black-box Iterative Machine Teaching](https://mlsanity.com/paper/1710.07742/) (2017)
- [PRISM: A Promptable and Robust Interactive Segmentation Model with Visual Prompts](https://mlsanity.com/paper/2404.15028/) (2024)
- [MultiverSeg: Scalable Interactive Segmentation of Biomedical Imaging Datasets with In-Context Guidance](https://mlsanity.com/paper/2412.15058/) (2024)
- [Iterative Teacher-Aware Learning](https://mlsanity.com/paper/2110.00137/) (2021)
- [Towards Clinician-Preferred Segmentation: Leveraging Human-in-the-Loop for Test Time Adaptation in Medical Image Segmentation](https://mlsanity.com/paper/2405.08270/) (2024)
- [RClicks: Realistic Click Simulation for Benchmarking Interactive Segmentation](https://mlsanity.com/paper/2410.11722/) (2024)
- [SPA: Efficient User-Preference Alignment against Uncertainty in Medical Image Segmentation](https://mlsanity.com/paper/2411.15513/) (2024)

## Abstract (arXiv)

When does a human correction become useful learning, and what establishes better segmentation at matched human effort? This critical narrative review follows feedback through its selection, learner update, and evaluation. It compares active learning, machine teaching, interactive segmentation, and sequential predictive evaluation using a common mathematical account of target information, predictive error, response predictability, and human work. An exact Bayesian update converts evaluation-label information into expected log-loss improvement; an excess-risk decomposition explains what an approximate learner can lose. Conditional information decompositions separate the roles of selected locations, labels, and displayed context. Empirical comparisons show why response protocols, update mechanisms, and effort denominators matter, distinguishing current-mask refinement from reusable learning and simulated interaction from human evidence. We identify what logs can reveal, what requires independent evaluation, and what remains model-dependent. The resulting research priorities are to test what selection reveals, whether using it improves assimilation, and whether the resulting interaction policy benefits segmentation at matched effort. These are distinct claims: predicting a teacher's responses need not identify human intentions or establish better learning. No new acquisition algorithm or empirical superiority is claimed.