# Decomposition Sampling for Efficient Region Annotations in Active Learning

arXiv: https://arxiv.org/abs/2512.07606 · HTML: https://mlsanity.com/paper/2512.07606/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 8 Dec 2025.

## Builds on (most cited first, 22 of 22)

- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 Challenge](https://mlsanity.com/paper/1912.01054/) (2019)
- [The KiTS19 Challenge Data: 300 Kidney Tumor Cases with Clinical Context, CT Semantic Segmentations, and Surgical Outcomes](https://mlsanity.com/paper/1904.00445/) (2019)
- [A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1910.02923/) (2019)
- [Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation](https://mlsanity.com/paper/1706.04737/) (2017)
- [BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Images](https://mlsanity.com/paper/2111.04740/) (2021)
- [The KiTS21 Challenge: Automatic segmentation of kidneys, renal tumors, and renal cysts in corticomedullary-phase CT](https://mlsanity.com/paper/2307.01984/) (2023)
- [Hierarchical Graph Representations in Digital Pathology](https://mlsanity.com/paper/2102.11057/) (2021)
- [CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation](https://mlsanity.com/paper/1810.09726/) (2018)
- [Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessment](https://mlsanity.com/paper/2301.10625/) (2023)
- [An attempt at beating the 3D U-Net](https://mlsanity.com/paper/1908.02182/) (2019)
- [Labeling instructions matter in biomedical image analysis](https://mlsanity.com/paper/2207.09899/) (2022)
- [Pan-tumor CAnine cuTaneous Cancer Histology (CATCH) dataset](https://mlsanity.com/paper/2201.11446/) (2022)
- [Active Learning Strategies for Weakly-supervised Object Detection](https://mlsanity.com/paper/2207.12112/) (2022)
- [Optical Flow Training under Limited Label Budget via Active Learning](https://mlsanity.com/paper/2203.05053/) (2022)
- [Adaptive Region Selection for Active Learning in Whole Slide Image Semantic Segmentation](https://mlsanity.com/paper/2307.07168/) (2023)

## Built on by (most cited first, 1 of 1)

- [Efficient Semi-Automated Material Microstructure Analysis Using Deep Learning: A Case Study in Additive Manufacturing](https://mlsanity.com/paper/2603.13831/) (2026)

## Abstract (arXiv)

Active learning improves annotation efficiency by selecting the most informative samples for annotation and model training. While most prior work has focused on selecting informative images for classification tasks, we investigate the more challenging setting of dense prediction, where annotations are more costly and time-intensive, especially in medical imaging. Region-level annotation has been shown to be more efficient than image-level annotation for these tasks. However, existing methods for representative annotation region selection suffer from high computational and memory costs, irrelevant region choices, and heavy reliance on uncertainty sampling. We propose decomposition sampling (DECOMP), a new active learning sampling strategy that addresses these limitations. It enhances annotation diversity by decomposing images into class-specific components using pseudo-labels and sampling regions from each class. Class-wise predictive confidence further guides the sampling process, ensuring that difficult classes receive additional annotations. Across ROI classification, 2-D segmentation, and 3-D segmentation, DECOMP consistently surpasses baseline methods by better sampling minority-class regions and boosting performance on these challenging classes. Code is in https://github.com/JingnaQiu/DECOMP.git.