# Class Balanced Dynamic Acquisition for Domain Adaptive Semantic Segmentation using Active Learning

arXiv: https://arxiv.org/abs/2311.14146 · HTML: https://mlsanity.com/paper/2311.14146/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 15 references that are in the map.
- First posted on arXiv 23 Nov 2023.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Deep Semantic Segmentation of Natural and Medical Images: A Review](https://mlsanity.com/paper/1910.07655/) (2019)
- [MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving](https://mlsanity.com/paper/1612.07695/) (2016)
- [Active Adversarial Domain Adaptation](https://mlsanity.com/paper/1904.07848/) (2019)
- [Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.12940/) (2021)
- [LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.05570/) (2021)
- [Multi-Anchor Active Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2108.08012/) (2021)
- [Class-Balanced Active Learning for Image Classification](https://mlsanity.com/paper/2110.04543/) (2021)
- [Minority Class Oriented Active Learning for Imbalanced Datasets](https://mlsanity.com/paper/2202.00390/) (2022)
- [Iterative Loop Method Combining Active and Semi-Supervised Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2301.13361/) (2023)

## Built on by (most cited first, 2 of 2)

- [A2LC: Active and Automated Label Correction for Semantic Segmentation](https://mlsanity.com/paper/2506.11599/) (2025)
- [Slide-Level Active Learning Reduces Annotation Burden in H&E images](https://mlsanity.com/paper/2607.09831/) (2026)

## Abstract (arXiv)

Domain adaptive active learning is leading the charge in label-efficient training of neural networks. For semantic segmentation, state-of-the-art models jointly use two criteria of uncertainty and diversity to select training labels, combined with a pixel-wise acquisition strategy. However, we show that such methods currently suffer from a class imbalance issue which degrades their performance for larger active learning budgets. We then introduce Class Balanced Dynamic Acquisition (CBDA), a novel active learning method that mitigates this issue, especially in high-budget regimes. The more balanced labels increase minority class performance, which in turn allows the model to outperform the previous baseline by 0.6, 1.7, and 2.4 mIoU for budgets of 5%, 10%, and 20%, respectively. Additionally, the focus on minority classes leads to improvements of the minimum class performance of 0.5, 2.9, and 4.6 IoU respectively. The top-performing model even exceeds the fully supervised baseline, showing that a more balanced label than the entire ground truth can be beneficial.