mlsanityData to 7 Oct 2026

AIO2: Online Correction of Object Labels for Deep Learning with Incomplete Annotation in Remote Sensing Image Segmentation

arXiv 2403.01641 ↗First posted 3 Mar 2024cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

While the volume of remote sensing data is increasing daily, deep learning in Earth Observation faces lack of accurate annotations for supervised optimization. Crowdsourcing projects such as OpenStreetMap distribute the annotation load to their community. However, such annotation inevitably generates noise due to insufficient control of the label quality, lack of annotators, frequent changes of the Earth's surface as a result of natural disasters and urban development, among many other factors. We present Adaptively trIggered Online Object-wise correction (AIO2) to address annotation noise induced by incomplete label sets. AIO2 features an Adaptive Correction Trigger (ACT) module that avoids label correction when the model training under- or overfits, and an Online Object-wise Correction (O2C) methodology that employs spatial information for automated label modification. AIO2 utilizes a mean teacher model to enhance training robustness with noisy labels to both stabilize the training accuracy curve for fitting in ACT and provide pseudo labels for correction in O2C. Moreover, O2C is implemented online without the need to store updated labels every training epoch. We validate our approach on two building footprint segmentation datasets with different spatial resolutions. Experimental results with varying degrees of building label noise demonstrate the robustness of AIO2. Source code will be available at https://github.com/zhu-xlab/AIO2.git.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 32 of its 78 references that are in the map. First posted on arXiv 3 Mar 2024.

Builds on

32 of 78 references.

References · 32

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  3. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  4. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  5. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  6. 2017A Closer Look at Memorization in Deep Networkscited by 936
  7. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  8. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  9. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  10. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  11. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 441
  12. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
20 more
  1. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  2. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  3. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  4. 2020Identifying Mislabeled Data using the Area Under the Margin Rankingcited by 259
  5. 2021Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotationscited by 253
  6. 2017Decoupling "when to update" from "how to update"cited by 230
  7. 2020A survey of loss functions for semantic segmentationcited by 216
  8. 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
  9. 2019Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Ratescited by 142
  10. 2019Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approachcited by 88
  11. 2019Curriculum Loss: Robust Learning and Generalization against Label Corruptioncited by 87
  12. 2021Adaptive Early-Learning Correction for Segmentation from Noisy Annotationscited by 61
  13. 2022A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Predictioncited by 46
  14. 2017Learning Aerial Image Segmentation from Online Mapscited by 30
  15. 2022On the Effects of Different Types of Label Noise in Multi-Label Remote Sensing Image Classificationcited by 17
  16. 2020Multi-Label Noise Robust Collaborative Learning for Remote Sensing Image Classificationcited by 13
  17. 2020Classification of Large-Scale High-Resolution SAR Images with Deep Transfer Learningcited by 12
  18. 2018An Entropic Optimal Transport Loss for Learning Deep Neural Networks under Label Noise in Remote Sensing Imagescited by 11
  19. 2022AutoGeoLabel: Automated Label Generation for Geospatial Machine Learningcited by 6
  20. 2022Generative Reasoning Integrated Label Noise Robust Deep Image Representation Learningcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 2.

9 papers.

  1. 2024CromSS: Cross-modal pre-training with noisy labels for remote sensing image segmentationcited by 7
  2. 2025SAM2-ELNet: Label Enhancement and Automatic Annotation for Remote Sensing Segmentationcited by 1
  3. 2025A Bayesian Approach to Segmentation with Noisy Labels via Spatially Correlated Distributionscited by 1
  4. 2025NSegment : Label-specific Deformations for Remote Sensing Image Segmentationcited by 0
  5. 2025Enhancing Monocular Height Estimation via Weak Supervision from Imperfect Labelscited by 0
  6. 2025Adaptive Gradient Calibration for Single-Positive Multi-Label Learning in Remote Sensing Image Scene Classificationcited by 0
  7. 2025LandSegmenter: Towards a Flexible Foundation Model for Land Use and Land Cover Mappingcited by 0
  8. 2026Delineate Anything v2: A Global Foundation Model for Field Delineationcited by 0
  9. 2026UniBuild: Unified Building Mapping From Multi-Source Optical Remote Sensing Imagery With Detail Decoding and Geometry Regularizationcited by 0