mlsanityData to 14 Oct 2026

Uncertainty-Guided Edge Learning for Deep Image Regression in Remote Sensing

arXiv 2605.05590 ↗First posted 7 May 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Edge learning refers to training machine learning models deployed on edge platforms, typically using new data accumulated onboard. The computational limitations on edge devices affect not only model optimisation, but also calculation of the predictive uncertainty of the current model on the unlabelled data, which is vital for informing model updating. In this paper, we investigate edge learning in the context of performing deep image regression on a remote sensing satellite, where a deep network is executed by an onboard computer to regress a scalar y from an input image, e.g., y is the percentage of pixels indicating cloud coverage or land use. We propose an uncertainty-guided edge learning (UGEL) algorithm that can accurately prioritise the data to speed up training convergence of the on-board regression model. Underpinning UGEL is the calculation of predictive uncertainty based on deep beta regression, where a deep network is used to estimate the parameters of a beta distribution for which the target y for an input image has a high likelihood. Compared to established methods for uncertainty estimation that are either too costly on edge devices (e.g., require many forward passes per sample) or make strict assumptions on the predictive distribution (e.g., Gaussian), deep beta regression is computable in a single forward pass and allows more general predictive distributions. Results show that UGEL delivers faster-converging edge learning than active or semi-supervised learning. Code and models are publicly available at https://github.com/anh-vunguyen/UGEL.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 58 references that are in the map. First posted on arXiv 7 May 2026.

Builds on

36 of 58 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Inductive Representation Learning on Large Graphscited by 6,320
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  4. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  5. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  6. 2017Deep Bayesian Active Learning with Image Datacited by 819
  7. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
  8. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  9. 2020A Survey of Deep Active Learningcited by 554
  10. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 463
  11. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 443
  12. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
24 more
  1. 2019Deep Evidential Regressioncited by 355
  2. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  3. 2021A Survey on Deep Semi-supervised Learningcited by 251
  4. 2018Deep Co-Training for Semi-Supervised Image Recognitioncited by 147
  5. 2019Convergence of Edge Computing and Deep Learning: A Comprehensive Surveycited by 120
  6. 2020Towards Deeper Graph Neural Networks with Differentiable Group Normalizationcited by 114
  7. 2024MobileNetV4 -- Universal Models for the Mobile Ecosystemcited by 99
  8. 2015Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networkscited by 95
  9. 2017Good Semi-supervised Learning that Requires a Bad GANcited by 86
  10. 2019On-Device Machine Learning: An Algorithms and Learning Theory Perspectivecited by 63
  11. 2020Towards Robust and Reproducible Active Learning Using Neural Networkscited by 54
  12. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 54
  13. 2020LandCover.ai: Dataset for Automatic Mapping of Buildings, Woodlands, Water and Roads from Aerial Imagerycited by 40
  14. 2022Enable Deep Learning on Mobile Devices: Methods, Systems, and Applicationscited by 32
  15. 2023Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forwardcited by 28
  16. 2019Cloud-Net: An end-to-end Cloud Detection Algorithm for Landsat 8 Imagerycited by 25
  17. 2021Diversity Enhanced Active Learning with Strictly Proper Scoring Rulescited by 22
  18. 2016Semi-Supervised Learning with Context-Conditional Generative Adversarial Networkscited by 19
  19. 2022On-device Training: A First Overview on Existing Systemscited by 19
  20. 2024Training Machine Learning models at the Edge: A Surveycited by 11
  21. 2018Deep Bayesian Active Semi-Supervised Learningcited by 7
  22. 2019The Label Complexity of Active Learning from Observational Datacited by 2
  23. 2025Integrating Semi-Supervised and Active Learning for Semantic Segmentationcited by 2
  24. 2023Domain Adaptation for Satellite-Borne Hyperspectral Cloud Detectioncited by 1

Built on by

Not cited yet.