mlsanityData to 14 Oct 2026

Edge-guided and Class-balanced Active Learning for Semantic Segmentation of Aerial Images

arXiv 2405.18078 ↗First posted 28 May 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Semantic segmentation requires pixel-level annotation, which is time-consuming. Active Learning (AL) is a promising method for reducing data annotation costs. Due to the gap between aerial and natural images, the previous AL methods are not ideal, mainly caused by unreasonable labeling units and the neglect of class imbalance. Previous labeling units are based on images or regions, which does not consider the characteristics of segmentation tasks and aerial images, i.e., the segmentation network often makes mistakes in the edge region, and the edge of aerial images is often interlaced and irregular. Therefore, an edge-guided labeling unit is proposed and supplemented as the new unit. On the other hand, the class imbalance is severe, manifested in two aspects: the aerial image is seriously imbalanced, and the AL strategy does not fully consider the class balance. Both seriously affect the performance of AL in aerial images. We comprehensively ensure class balance from all steps that may occur imbalance, including initial labeled data, subsequent labeled data, and pseudo-labels. Through the two improvements, our method achieves more than 11.2% gains compared to state-of-the-art methods on three benchmark datasets, Deepglobe, Potsdam, and Vaihingen, and more than 18.6% gains compared to the baseline. Sufficient ablation studies show that every module is indispensable. Furthermore, we establish a fair and strong benchmark for future research on AL for aerial image segmentation.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 47 of its 82 references that are in the map. First posted on arXiv 28 May 2024.

Builds on

47 of 82 references.

References · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  6. 2016Pyramid Scene Parsing Networkcited by 2,479
  7. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  8. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  9. 2017Deep Bayesian Active Learning with Image Datacited by 819
  10. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  11. 2018Learning to Reweight Examples for Robust Deep Learningcited by 675
  12. 2015Holistically-Nested Edge Detectioncited by 592
35 more
  1. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 576
  2. 2020A Survey of Deep Active Learningcited by 554
  3. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
  4. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
  5. 2019Confidence Regularized Self-Trainingcited by 419
  6. 2019Learning Loss for Active Learningcited by 336
  7. 2019Variational Adversarial Active Learningcited by 284
  8. 2018DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Imagescited by 277
  9. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  10. 2021Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Datacited by 215
  11. 2018Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learningcited by 174
  12. 2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 152
  13. 2017Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentationcited by 146
  14. 2019ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentationcited by 96
  15. 2018Label Refinery: Improving ImageNet Classification through Label Progressioncited by 65
  16. 2020Reinforced active learning for image segmentationcited by 56
  17. 2019Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Imagescited by 51
  18. 2018CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentationcited by 49
  19. 2019A Relation-Augmented Fully Convolutional Network for Semantic Segmentation in Aerial Scenescited by 33
  20. 2020Self-Training for Class-Incremental Semantic Segmentationcited by 32
  21. 2021CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Imagescited by 29
  22. 2020MetaBox+: A new Region Based Active Learning Method for Semantic Segmentation using Priority Mapscited by 23
  23. 2015Hierarchical Subquery Evaluation for Active Learning on a Graphcited by 21
  24. 2023Generative Prompt Model for Weakly Supervised Object Localizationcited by 20
  25. 2020Dense Dilated Convolutions Merging Network for Land Cover Classificationcited by 19
  26. 2020Suggestive Annotation of Brain Tumour Images with Gradient-guided Samplingcited by 19
  27. 2020Self-Supervised Drivable Area and Road Anomaly Segmentation using RGB-D Data for Robotic Wheelchairscited by 18
  28. 2020Deep Active Learning for Joint Classification & Segmentation with Weak Annotatorcited by 16
  29. 2021Class-Balanced Active Learning for Image Classificationcited by 15
  30. 2024ControlCap: Controllable Region-level Captioningcited by 13
  31. 2023Continual Learning for Image Segmentation with Dynamic Querycited by 12
  32. 2022Explore Faster Localization Learning For Scene Text Detectioncited by 10
  33. 2023FlowText: Synthesizing Realistic Scene Text Video with Optical Flow Estimationcited by 10
  34. 2019Cost-efficient segmentation of electron microscopy images using active learningcited by 5
  35. 2019Deep Active Learning for Axon-Myelin Segmentation on Histology Datacited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025GDGS: 3D Gaussian Splatting Via Geometry-Guided Initialization And Dynamic Density Controlcited by 2
  2. 2025A Global-Local Cross-Attention Network for Ultra-high Resolution Remote Sensing Image Semantic Segmentationcited by 1
  3. 2026Dynamic Class-Aware Active Learning for Unbiased Satellite Image Segmentationcited by 0
  4. 2026MAViE: A Multi-scale Adaptive Vision Encoder for Fine-grained Visual Perception and Efficient Multimodal Reasoningcited by 0