# DEAL: Difficulty-aware Active Learning for Semantic Segmentation

arXiv: https://arxiv.org/abs/2010.08705 · HTML: https://mlsanity.com/paper/2010.08705/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Oct 2020.

## Built on by (most cited first, 30 of 32)

- [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://mlsanity.com/paper/2202.11094/) (2022)
- [Learning 3D Semantic Segmentation with only 2D Image Supervision](https://mlsanity.com/paper/2110.11325/) (2021)
- [Unsupervised Salient Object Detection with Spectral Cluster Voting](https://mlsanity.com/paper/2203.12614/) (2022)
- [All you need are a few pixels: semantic segmentation with PixelPick](https://mlsanity.com/paper/2104.06394/) (2021)
- [Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation](https://mlsanity.com/paper/2108.12545/) (2021)
- [ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation](https://mlsanity.com/paper/2401.08501/) (2024)
- [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)
- [Not All Samples Should Be Utilized Equally: Towards Understanding and Improving Dataset Distillation](https://mlsanity.com/paper/2408.12483/) (2024)
- [Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite Images](https://mlsanity.com/paper/2110.07782/) (2021)
- [Multi-Task Consistency for Active Learning](https://mlsanity.com/paper/2306.12398/) (2023)
- [Improving Interpretability of Deep Active Learning for Flood Inundation Mapping Through Class Ambiguity Indices Using Multi-spectral Satellite Imagery](https://mlsanity.com/paper/2404.19043/) (2024)
- [AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners](https://mlsanity.com/paper/2505.16322/) (2025)
- [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)
- [Semantic Segmentation with Active Semi-Supervised Representation Learning](https://mlsanity.com/paper/2210.08403/) (2022)
- [Joint Salient Object Detection and Camouflaged Object Detection via Uncertainty-aware Learning](https://mlsanity.com/paper/2307.04651/) (2023)
- [SegXAL: Explainable Active Learning for Semantic Segmentation in Driving Scene Scenarios](https://mlsanity.com/paper/2408.04482/) (2024)
- [DEAL-300K: Diffusion-based Editing Area Localization with a 300K-Scale Dataset and Frequency-Prompted Baseline](https://mlsanity.com/paper/2511.23377/) (2025)
- [An Active and Contrastive Learning Framework for Fine-Grained Off-Road Semantic Segmentation](https://mlsanity.com/paper/2202.09002/) (2022)
- [Lirot.ai: A Novel Platform for Crowd-Sourcing Retinal Image Segmentations](https://mlsanity.com/paper/2208.10100/) (2022)
- [Active Learning for Fine-Grained Sketch-Based Image Retrieval](https://mlsanity.com/paper/2309.08743/) (2023)
- [Integrating Semi-Supervised and Active Learning for Semantic Segmentation](https://mlsanity.com/paper/2501.19227/) (2025)
- [Active Learning Inspired ControlNet Guidance for Augmenting Semantic Segmentation Datasets](https://mlsanity.com/paper/2503.09221/) (2025)
- [Semantic Segmentation by Semantic Proportions](https://mlsanity.com/paper/2305.15608/) (2023)
- [Uncertainty Driven Active Learning for Image Segmentation in Underwater Inspection](https://mlsanity.com/paper/2403.14002/) (2024)
- [Maturity-Aware Active Learning for Semantic Segmentation with Hierarchically-Adaptive Sample Assessment](https://mlsanity.com/paper/2308.14904/) (2023)
- [Effective Data Selection for Seismic Interpretation through Disagreement](https://mlsanity.com/paper/2406.05149/) (2024)
- [Cross-Domain Semantic Segmentation with Large Language Model-Assisted Descriptor Generation](https://mlsanity.com/paper/2501.16467/) (2025)
- [Active Learning Methods for Efficient Data Utilization and Model Performance Enhancement](https://mlsanity.com/paper/2504.16136/) (2025)

## Abstract (arXiv)

Active learning aims to address the paucity of labeled data by finding the most informative samples. However, when applying to semantic segmentation, existing methods ignore the segmentation difficulty of different semantic areas, which leads to poor performance on those hard semantic areas such as tiny or slender objects. To deal with this problem, we propose a semantic Difficulty-awarE Active Learning (DEAL) network composed of two branches: the common segmentation branch and the semantic difficulty branch. For the latter branch, with the supervision of segmentation error between the segmentation result and GT, a pixel-wise probability attention module is introduced to learn the semantic difficulty scores for different semantic areas. Finally, two acquisition functions are devised to select the most valuable samples with semantic difficulty. Competitive results on semantic segmentation benchmarks demonstrate that DEAL achieves state-of-the-art active learning performance and improves the performance of the hard semantic areas in particular.