mlsanityData to 14 Oct 2026

Label-frugal satellite image change detection with generative virtual exemplar learning

arXiv 2510.06926 ↗First posted 8 Oct 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Change detection is a major task in remote sensing which consists in finding all the occurrences of changes in multi-temporal satellite or aerial images. The success of existing methods, and particularly deep learning ones, is tributary to the availability of hand-labeled training data that capture the acquisition conditions and the subjectivity of the user (oracle). In this paper, we devise a novel change detection algorithm, based on active learning. The main contribution of our work resides in a new model that measures how important is each unlabeled sample, and provides an oracle with only the most critical samples (also referred to as virtual exemplars) for further labeling. These exemplars are generated, using an invertible graph convnet, as the optimum of an adversarial loss that (i) measures representativity, diversity and ambiguity of the data, and thereby (ii) challenges (the most) the current change detection criteria, leading to a better re-estimate of these criteria in the subsequent iterations of active learning. Extensive experiments show the positive impact of our label-efficient learning model against comparative methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 46 of its 143 references that are in the map. First posted on arXiv 8 Oct 2025.

Builds on

46 of 143 references.

References · 46

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  8. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  9. 2016Matching Networks for One Shot Learningcited by 2,255
  10. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  11. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  12. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
34 more
  1. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,066
  2. 2017Deep Bayesian Active Learning with Image Datacited by 819
  3. 2015Gated Graph Sequence Neural Networkscited by 796
  4. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 657
  5. 2018Deep Visual Domain Adaptation: A Surveycited by 635
  6. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  7. 2017Generative Adversarial Networks: An Overviewcited by 590
  8. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 584
  9. 2018Is Q-learning Provably Efficient?cited by 487
  10. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
  11. 2019Learning Loss for Active Learningcited by 336
  12. 2015Diffusion-Convolutional Neural Networkscited by 268
  13. 2019Revisiting Self-Supervised Visual Representation Learningcited by 251
  14. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  15. 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
  16. 2018Adaptive Sampling Towards Fast Graph Representation Learningcited by 180
  17. 2018GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphscited by 165
  18. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  19. 2020Contextual Diversity for Active Learningcited by 139
  20. 2018Large-Scale Learnable Graph Convolutional Networkscited by 113
  21. 2017Learning Active Learning from Datacited by 101
  22. 2018Efficient Active Learning for Image Classification and Segmentation using a Sample Selection and Conditional Generative Adversarial Networkcited by 74
  23. 2018Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoderscited by 74
  24. 2017Generative Adversarial Active Learningcited by 70
  25. 2019Bayesian Batch Active Learning as Sparse Subset Approximationcited by 68
  26. 2017Automated Scalable Bayesian Inference via Hilbert Coresetscited by 55
  27. 2018Adversarial Sampling for Active Learningcited by 51
  28. 2018Active Learning for Deep Object Detectioncited by 50
  29. 2023Change Detection Methods for Remote Sensing in the Last Decade: A Comprehensive Reviewcited by 41
  30. 2018Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learningcited by 26
  31. 2020DEAL: Deep Evidential Active Learning for Image Classificationcited by 22
  32. 2023GCD-DDPM: A Generative Change Detection Model Based on Difference-Feature Guided DDPMcited by 21
  33. 2021Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 20
  34. 2018Cost-effective Object Detection: Active Sample Mining with Switchable Selection Criteriacited by 12

Built on by

Not cited yet.