mlsanityData to 14 Oct 2026

On the Effects of Different Types of Label Noise in Multi-Label Remote Sensing Image Classification

arXiv 2207.13975 ↗First posted 28 Jul 2022cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

The development of accurate methods for multi-label classification (MLC) of remote sensing (RS) images is one of the most important research topics in RS. To address MLC problems, the use of deep neural networks that require a high number of reliable training images annotated by multiple land-cover class labels (multi-labels) has been found popular in RS. However, collecting such annotations is time-consuming and costly. A common procedure to obtain annotations at zero labeling cost is to rely on thematic products or crowdsourced labels. As a drawback, these procedures come with the risk of label noise that can distort the learning process of the MLC algorithms. In the literature, most label noise robust methods are designed for single-label classification (SLC) problems in computer vision (CV), where each image is annotated by a single label. Unlike SLC, label noise in MLC can be associated with: 1) subtractive label-noise (a land cover class label is not assigned to an image while that class is present in the image); 2) additive label-noise (a land cover class label is assigned to an image although that class is not present in the given image); and 3) mixed label-noise (a combination of both). In this paper, we investigate three different noise robust CV SLC methods and adapt them to be robust for multi-label noise scenarios in RS. During experiments, we study the effects of different types of multi-label noise and evaluate the adapted methods rigorously. To this end, we also introduce a synthetic multi-label noise injection strategy that is more adequate to simulate operational scenarios compared to the uniform label noise injection strategy, in which the labels of absent and present classes are flipped at uniform probability. Further, we study the relevance of different evaluation metrics in MLC problems under noisy multi-labels.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 30 of its 54 references that are in the map. First posted on arXiv 28 Jul 2022.

Builds on

30 of 54 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  4. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  5. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
  6. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
  7. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 582
  8. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 443
  9. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 416
  10. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  11. 2019BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understandingcited by 234
  12. 2017Decoupling "when to update" from "how to update"cited by 230
18 more
  1. 2018Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noisecited by 216
  2. 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
  3. 2019SELF: Learning to Filter Noisy Labels with Self-Ensemblingcited by 164
  4. 2017Learning from Noisy Labels with Distillationcited by 161
  5. 2018Learning to Learn from Noisy Labeled Datacited by 160
  6. 2018CurriculumNet: Weakly Supervised Learning from Large-Scale Web Imagescited by 126
  7. 2020Self-Adaptive Training: beyond Empirical Risk Minimizationcited by 126
  8. 2019Learning a Deep ConvNet for Multi-label Classification with Partial Labelscited by 124
  9. 2019Deep Self-Learning From Noisy Labelscited by 122
  10. 2017Learning From Noisy Large-Scale Datasets With Minimal Supervisioncited by 115
  11. 2021BigEarthNet-MM: A Large Scale Multi-Modal Multi-Label Benchmark Archive for Remote Sensing Image Classification and Retrievalcited by 92
  12. 2018Collaborative Learning for Deep Neural Networkscited by 69
  13. 2017Learning with Confident Examples: Rank Pruning for Robust Classification with Noisy Labelscited by 52
  14. 2020BigEarthNet Dataset with A New Class-Nomenclature for Remote Sensing Image Understandingcited by 14
  15. 2020Multi-Label Noise Robust Collaborative Learning for Remote Sensing Image Classificationcited by 13
  16. 2018An Entropic Optimal Transport Loss for Learning Deep Neural Networks under Label Noise in Remote Sensing Imagescited by 11
  17. 2021Evaluating Multi-label Classifiers with Noisy Labelscited by 10
  18. 2022Weakly Supervised Semantic Segmentation of Remote Sensing Images for Tree Species Classification Based on Explanation Methodscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 6; 2025: 3; 2026: 4.

17 papers.

Sort:

By area:

  1. 2024Robust Multi-Task Learning with Excess Riskscited by 24
  2. 2023Better, Not Just More: Data-Centric Machine Learning for Earth Observationcited by 19
  3. 2024AIO2: Online Correction of Object Labels for Deep Learning with Incomplete Annotation in Remote Sensing Image Segmentationcited by 10
  4. 2022Generative Reasoning Integrated Label Noise Robust Deep Image Representation Learningcited by 5
  5. 2024Transformer-based Federated Learning for Multi-Label Remote Sensing Image Classificationcited by 5
  6. 2023A Robust Multilabel Method Integrating Rule-based Transparent Model, Soft Label Correlation Learning and Label Noise Resistancecited by 1
  7. 2023Label Noise Robust Image Representation Learning based on Supervised Variational Autoencoders in Remote Sensingcited by 1
  8. 2024Estimating Physical Information Consistency of Channel Data Augmentation for Remote Sensing Imagescited by 1
  9. 2024A Label Propagation Strategy for CutMix in Multi-Label Remote Sensing Image Classificationcited by 1
  10. 2025A Multi-Modal Federated Learning Framework for Remote Sensing Image Classificationcited by 1
  11. 2024When the Small-Loss Trick is Not Enough: Multi-Label Image Classification with Noisy Labels Applied to CCTV Sewer Inspectionscited by 0
  12. 2025Remote Sensing Image Classification with Decoupled Knowledge Distillationcited by 0
5 more
  1. 2025Adaptive Gradient Calibration for Single-Positive Multi-Label Learning in Remote Sensing Image Scene Classificationcited by 0
  2. 2026Noise-Adaptive Regularization for Robust Multi-Label Remote Sensing Image Classificationcited by 0
  3. 2026Data-Centric Benchmark for Label Noise Estimation and Ranking in Remote Sensing Binary Building Segmentationcited by 0
  4. 2026An assessment of data-centric methods for label noise identification in remote sensing data setscited by 0
  5. 2026Delineate Anything v2: A Global Foundation Model for Field Delineationcited by 0