# MetaBox+: A new Region Based Active Learning Method for Semantic Segmentation using Priority Maps

arXiv: https://arxiv.org/abs/2010.01884 · HTML: https://mlsanity.com/paper/2010.01884/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2020.

## Built on by (most cited first, 23 of 23)

- [ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation](https://mlsanity.com/paper/2401.08501/) (2024)
- [Automated Detection of Label Errors in Semantic Segmentation Datasets via Deep Learning and Uncertainty Quantification](https://mlsanity.com/paper/2207.06104/) (2022)
- [Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approach](https://mlsanity.com/paper/2101.06931/) (2021)
- [Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoning](https://mlsanity.com/paper/2202.12588/) (2022)
- [Semantic Segmentation with Active Semi-Supervised Learning](https://mlsanity.com/paper/2203.10730/) (2022)
- [Adaptive Superpixel for Active Learning in Semantic Segmentation](https://mlsanity.com/paper/2303.16817/) (2023)
- [Multi-Task Consistency for Active Learning](https://mlsanity.com/paper/2306.12398/) (2023)
- [Active Learning for Semantic Segmentation with Multi-class Label Query](https://mlsanity.com/paper/2309.09319/) (2023)
- [CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation](https://mlsanity.com/paper/2112.05975/) (2021)
- [Bayesian Active Learning for Semantic Segmentation](https://mlsanity.com/paper/2408.01694/) (2024)
- [Detecting and Learning the Unknown in Semantic Segmentation](https://mlsanity.com/paper/2202.08700/) (2022)
- [Semi-supervised domain adaptation with CycleGAN guided by a downstream task loss](https://mlsanity.com/paper/2208.08815/) (2022)
- [Correlation-aware active learning for surgery video segmentation](https://mlsanity.com/paper/2311.08811/) (2023)
- [Edge-guided and Class-balanced Active Learning for Semantic Segmentation of Aerial Images](https://mlsanity.com/paper/2405.18078/) (2024)
- [Adaptive Region Selection for Active Learning in Whole Slide Image Semantic Segmentation](https://mlsanity.com/paper/2307.07168/) (2023)
- [False Positive Detection and Prediction Quality Estimation for LiDAR Point Cloud Segmentation](https://mlsanity.com/paper/2110.15681/) (2021)
- [An Active and Contrastive Learning Framework for Fine-Grained Off-Road Semantic Segmentation](https://mlsanity.com/paper/2202.09002/) (2022)
- [Active Learning with Context Sampling and One-vs-Rest Entropy for Semantic Segmentation](https://mlsanity.com/paper/2412.06470/) (2024)
- [Background-Foreground Segmentation for Interior Sensing in Automotive Industry](https://mlsanity.com/paper/2109.09410/) (2021)
- [Uncertainty Quantification and Resource-Demanding Computer Vision Applications of Deep Learning](https://mlsanity.com/paper/2205.14917/) (2022)
- [Uncertainty and Prediction Quality Estimation for Semantic Segmentation via Graph Neural Networks](https://mlsanity.com/paper/2409.11373/) (2024)
- [Does Knowledge About Perceptual Uncertainty Help an Agent in Automated Driving?](https://mlsanity.com/paper/2502.11864/) (2025)
- [Cost-efficient Active Learning for Referring Image Segmentation and Grounding](https://mlsanity.com/paper/2608.30621/) (2026)

## Abstract (arXiv)

We present a novel region based active learning method for semantic image segmentation, called MetaBox+. For acquisition, we train a meta regression model to estimate the segment-wise Intersection over Union (IoU) of each predicted segment of unlabeled images. This can be understood as an estimation of segment-wise prediction quality. Queried regions are supposed to minimize to competing targets, i.e., low predicted IoU values / segmentation quality and low estimated annotation costs. For estimating the latter we propose a simple but practical method for annotation cost estimation. We compare our method to entropy based methods, where we consider the entropy as uncertainty of the prediction. The comparison and analysis of the results provide insights into annotation costs as well as robustness and variance of the methods. Numerical experiments conducted with two different networks on the Cityscapes dataset clearly demonstrate a reduction of annotation effort compared to random acquisition. Noteworthily, we achieve 95%of the mean Intersection over Union (mIoU), using MetaBox+ compared to when training with the full dataset, with only 10.47% / 32.01% annotation effort for the two networks, respectively.