# Adaptive Superpixel for Active Learning in Semantic Segmentation

arXiv: https://arxiv.org/abs/2303.16817 · HTML: https://mlsanity.com/paper/2303.16817/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 43 references that are in the map.
- First posted on arXiv 29 Mar 2023.

## Builds on (most cited first, 21 of 21)

- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation](https://mlsanity.com/paper/1706.04737/) (2017)
- [ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation](https://mlsanity.com/paper/1911.11789/) (2019)
- [SEEDS: Superpixels Extracted via Energy-Driven Sampling](https://mlsanity.com/paper/1309.3848/) (2013)
- [Adaptive Early-Learning Correction for Segmentation from Noisy Annotations](https://mlsanity.com/paper/2110.03740/) (2021)
- [Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.12940/) (2021)
- [Reinforced active learning for image segmentation](https://mlsanity.com/paper/2002.06583/) (2020)
- [CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation](https://mlsanity.com/paper/1810.09726/) (2018)
- [Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2104.00905/) (2021)
- [Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformers](https://mlsanity.com/paper/2204.11432/) (2022)
- [Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotations](https://mlsanity.com/paper/1904.07934/) (2019)
- [DEAL: Difficulty-aware Active Learning for Semantic Segmentation](https://mlsanity.com/paper/2010.08705/) (2020)
- [Superpixel-guided Iterative Learning from Noisy Labels for Medical Image Segmentation](https://mlsanity.com/paper/2107.10100/) (2021)
- [MetaBox+: A new Region Based Active Learning Method for Semantic Segmentation using Priority Maps](https://mlsanity.com/paper/2010.01884/) (2020)
- [Importance of Self-Consistency in Active Learning for Semantic Segmentation](https://mlsanity.com/paper/2008.01860/) (2020)
- [Suggestive Annotation of Brain Tumour Images with Gradient-guided Sampling](https://mlsanity.com/paper/2006.14984/) (2020)
- [Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite Images](https://mlsanity.com/paper/2110.07782/) (2021)
- [CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation](https://mlsanity.com/paper/2112.05975/) (2021)
- [Robust Shape Regularity Criteria for Superpixel Evaluation](https://mlsanity.com/paper/1903.07146/) (2019)

## Built on by (most cited first, 14 of 14)

- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [Active Learning for Semantic Segmentation with Multi-class Label Query](https://mlsanity.com/paper/2309.09319/) (2023)
- [Active Label Correction for Semantic Segmentation with Foundation Models](https://mlsanity.com/paper/2403.10820/) (2024)
- [Pseudo-triplet Guided Few-shot Composed Image Retrieval](https://mlsanity.com/paper/2407.06001/) (2024)
- [Superpixel Anything: A general object-based framework for accurate yet regular superpixel segmentation](https://mlsanity.com/paper/2509.12791/) (2025)
- [Rethinking Superpixel Segmentation from Biologically Inspired Mechanisms](https://mlsanity.com/paper/2309.13438/) (2023)
- [Free-Mask: A Novel Paradigm of Integration Between the Segmentation Diffusion Model and Image Editing](https://mlsanity.com/paper/2411.01819/) (2024)
- [Active Prompt Learning with Vision-Language Model Priors](https://mlsanity.com/paper/2411.16722/) (2024)
- [Active Learning with Context Sampling and One-vs-Rest Entropy for Semantic Segmentation](https://mlsanity.com/paper/2412.06470/) (2024)
- [A2LC: Active and Automated Label Correction for Semantic Segmentation](https://mlsanity.com/paper/2506.11599/) (2025)
- [The Accuracy Cost of Weakness: A Theoretical Analysis of Fixed-Segment Weak Labeling for Events in Time](https://mlsanity.com/paper/2502.09363/) (2025)
- [SSeg: Active Sparse Point-Label Augmentation for Semantic Segmentation](https://mlsanity.com/paper/2510.10163/) (2025)
- [QuickDraw: Fast Visualization, Analysis and Active Learning for Medical Image Segmentation](https://mlsanity.com/paper/2503.09885/) (2025)
- [Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation](https://mlsanity.com/paper/2510.22229/) (2025)

## Abstract (arXiv)

Learning semantic segmentation requires pixel-wise annotations, which can be time-consuming and expensive. To reduce the annotation cost, we propose a superpixel-based active learning (AL) framework, which collects a dominant label per superpixel instead. To be specific, it consists of adaptive superpixel and sieving mechanisms, fully dedicated to AL. At each round of AL, we adaptively merge neighboring pixels of similar learned features into superpixels. We then query a selected subset of these superpixels using an acquisition function assuming no uniform superpixel size. This approach is more efficient than existing methods, which rely only on innate features such as RGB color and assume uniform superpixel sizes. Obtaining a dominant label per superpixel drastically reduces annotators' burden as it requires fewer clicks. However, it inevitably introduces noisy annotations due to mismatches between superpixel and ground truth segmentation. To address this issue, we further devise a sieving mechanism that identifies and excludes potentially noisy annotations from learning. Our experiments on both Cityscapes and PASCAL VOC datasets demonstrate the efficacy of adaptive superpixel and sieving mechanisms.