# Semi-supervised Active Learning for Instance Segmentation via Scoring Predictions

arXiv: https://arxiv.org/abs/2012.04829 · HTML: https://mlsanity.com/paper/2012.04829/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2020.

## Built on by (most cited first, 8 of 8)

- [Warm Start Active Learning with Proxy Labels & Selection via Semi-Supervised Fine-Tuning](https://mlsanity.com/paper/2209.06285/) (2022)
- [Class-Balanced Active Learning for Image Classification](https://mlsanity.com/paper/2110.04543/) (2021)
- [Active Pointly-Supervised Instance Segmentation](https://mlsanity.com/paper/2207.11493/) (2022)
- [Monocular 3D Object Detection with LiDAR Guided Semi Supervised Active Learning](https://mlsanity.com/paper/2307.08415/) (2023)
- [Active learning with MaskAL reduces annotation effort for training Mask R-CNN](https://mlsanity.com/paper/2112.06586/) (2021)
- [Two-Step Active Learning for Instance Segmentation with Uncertainty and Diversity Sampling](https://mlsanity.com/paper/2309.16139/) (2023)
- [CandidateDrug4Cancer: An Open Molecular Graph Learning Benchmark on Drug Discovery for Cancer](https://mlsanity.com/paper/2203.00836/) (2022)
- [Hybrid supervised instance segmentation by learning label noise suppression](https://mlsanity.com/paper/2610.20412/) (2026)

## Abstract (arXiv)

Active learning generally involves querying the most representative samples for human labeling, which has been widely studied in many fields such as image classification and object detection. However, its potential has not been explored in the more complex instance segmentation task that usually has relatively higher annotation cost. In this paper, we propose a novel and principled semi-supervised active learning framework for instance segmentation. Specifically, we present an uncertainty sampling strategy named Triplet Scoring Predictions (TSP) to explicitly incorporate samples ranking clues from classes, bounding boxes and masks. Moreover, we devise a progressive pseudo labeling regime using the above TSP in semi-supervised manner, it can leverage both the labeled and unlabeled data to minimize labeling effort while maximize performance of instance segmentation. Results on medical images datasets demonstrate that the proposed method results in the embodiment of knowledge from available data in a meaningful way. The extensive quantitatively and qualitatively experiments show that, our method can yield the best-performing model with notable less annotation costs, compared with state-of-the-arts.