mlsanityData to 7 Oct 2026

Adversarial Virtual Exemplar Learning for Label-Frugal Satellite Image Change Detection

arXiv 2212.13974 ↗First posted 28 Dec 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Satellite image change detection aims at finding occurrences of targeted changes in a given scene taken at different instants. This task is highly challenging due to the acquisition conditions and also to the subjectivity of changes. In this paper, we investigate satellite image change detection using active learning. Our method is interactive and relies on a question and answer model which asks the oracle (user) questions about the most informative display (dubbed as virtual exemplars), and according to the user's responses, updates change detections. The main contribution of our method consists in a novel adversarial model that allows frugally probing the oracle with only the most representative, diverse and uncertain virtual exemplars. The latter are learned to challenge the most the trained change decision criteria which ultimately leads to a better re-estimate of these criteria in the following iterations of active learning. Conducted experiments show the out-performance of our proposed adversarial display model against other display strategies as well as the related work.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 131 references that are in the map. First posted on arXiv 28 Dec 2022.

Builds on

43 of 131 references.

References · 43

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  7. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  8. 2016Matching Networks for One Shot Learningcited by 2,246
  9. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  10. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  11. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  12. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
31 more
  1. 2017Deep Bayesian Active Learning with Image Datacited by 812
  2. 2015Gated Graph Sequence Neural Networkscited by 792
  3. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 656
  4. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  5. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  6. 2017Generative Adversarial Networks: An Overviewcited by 588
  7. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  8. 2018Is Q-learning Provably Efficient?cited by 485
  9. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  10. 2019Learning Loss for Active Learningcited by 335
  11. 2015Diffusion-Convolutional Neural Networkscited by 268
  12. 2019Revisiting Self-Supervised Visual Representation Learningcited by 250
  13. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  14. 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
  15. 2018Adaptive Sampling Towards Fast Graph Representation Learningcited by 180
  16. 2018GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphscited by 164
  17. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  18. 2020Contextual Diversity for Active Learningcited by 139
  19. 2018Large-Scale Learnable Graph Convolutional Networkscited by 113
  20. 2017Learning Active Learning from Datacited by 100
  21. 2018Efficient Active Learning for Image Classification and Segmentation using a Sample Selection and Conditional Generative Adversarial Networkcited by 74
  22. 2018Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoderscited by 74
  23. 2017Generative Adversarial Active Learningcited by 69
  24. 2019Bayesian Batch Active Learning as Sparse Subset Approximationcited by 68
  25. 2017Automated Scalable Bayesian Inference via Hilbert Coresetscited by 55
  26. 2018Adversarial Sampling for Active Learningcited by 51
  27. 2018Active Learning for Deep Object Detectioncited by 49
  28. 2018Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learningcited by 26
  29. 2020DEAL: Deep Evidential Active Learning for Image Classificationcited by 22
  30. 2021Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 20
  31. 2018Cost-effective Object Detection: Active Sample Mining with Switchable Selection Criteriacited by 12

Built on by

Not cited yet.