# Reinforced active learning for image segmentation

arXiv: https://arxiv.org/abs/2002.06583 · HTML: https://mlsanity.com/paper/2002.06583/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Feb 2020.

## Built on by (most cited first, 30 of 56)

- [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://mlsanity.com/paper/2202.11094/) (2022)
- [A Comparative Survey of Deep Active Learning](https://mlsanity.com/paper/2203.13450/) (2022)
- [Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.12940/) (2021)
- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [All you need are a few pixels: semantic segmentation with PixelPick](https://mlsanity.com/paper/2104.06394/) (2021)
- [Learning the What and How of Annotation in Video Object Segmentation](https://mlsanity.com/paper/2311.04414/) (2023)
- [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)
- [DiscoBAX: Discovery of Optimal Intervention Sets in Genomic Experiment Design](https://mlsanity.com/paper/2312.04064/) (2023)
- [TAAL: Test-time Augmentation for Active Learning in Medical Image Segmentation](https://mlsanity.com/paper/2301.06624/) (2023)
- [Generative Active Learning for Long-tailed Instance Segmentation](https://mlsanity.com/paper/2406.02435/) (2024)
- [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)
- [AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning](https://mlsanity.com/paper/2406.00480/) (2024)
- [Deep Active Learning for Computer Vision: Past and Future](https://mlsanity.com/paper/2211.14819/) (2022)
- [Full or Weak annotations? An adaptive strategy for budget-constrained annotation campaigns](https://mlsanity.com/paper/2303.11678/) (2023)
- [Active Label Correction for Semantic Segmentation with Foundation Models](https://mlsanity.com/paper/2403.10820/) (2024)
- [CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation](https://mlsanity.com/paper/2112.05975/) (2021)
- [ARAIDA: Analogical Reasoning-Augmented Interactive Data Annotation](https://mlsanity.com/paper/2405.11912/) (2024)
- [Text-to-SQL Domain Adaptation via Human-LLM Collaborative Data Annotation](https://mlsanity.com/paper/2502.15980/) (2025)
- [Active learning for object detection in high-resolution satellite images](https://mlsanity.com/paper/2101.02480/) (2021)
- [MEAL: Manifold Embedding-based Active Learning](https://mlsanity.com/paper/2106.11858/) (2021)
- [D2ADA: Dynamic Density-aware Active Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2202.06484/) (2022)
- [Active Coarse-to-Fine Segmentation of Moveable Parts from Real Images](https://mlsanity.com/paper/2303.11530/) (2023)
- [Bayesian Active Learning for Semantic Segmentation](https://mlsanity.com/paper/2408.01694/) (2024)
- [A Unified Active Learning Framework for Annotating Graph Data with Application to Software Source Code Performance Prediction](https://mlsanity.com/paper/2304.13032/) (2023)
- [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)
- [How to Enable Effective Cooperation Between Humans and NLP Models: A Survey of Principles, Formalizations, and Beyond](https://mlsanity.com/paper/2501.05714/) (2025)
- [Deep reinforced active learning for multi-class image classification](https://mlsanity.com/paper/2206.13391/) (2022)

## Abstract (arXiv)

Learning-based approaches for semantic segmentation have two inherent challenges. First, acquiring pixel-wise labels is expensive and time-consuming. Second, realistic segmentation datasets are highly unbalanced: some categories are much more abundant than others, biasing the performance to the most represented ones. In this paper, we are interested in focusing human labelling effort on a small subset of a larger pool of data, minimizing this effort while maximizing performance of a segmentation model on a hold-out set. We present a new active learning strategy for semantic segmentation based on deep reinforcement learning (RL). An agent learns a policy to select a subset of small informative image regions -- opposed to entire images -- to be labeled, from a pool of unlabeled data. The region selection decision is made based on predictions and uncertainties of the segmentation model being trained. Our method proposes a new modification of the deep Q-network (DQN) formulation for active learning, adapting it to the large-scale nature of semantic segmentation problems. We test the proof of concept in CamVid and provide results in the large-scale dataset Cityscapes. On Cityscapes, our deep RL region-based DQN approach requires roughly 30% less additional labeled data than our most competitive baseline to reach the same performance. Moreover, we find that our method asks for more labels of under-represented categories compared to the baselines, improving their performance and helping to mitigate class imbalance.