mlsanityData to 14 Oct 2026

Frugal Satellite Image Change Detection with Deep-Net Inversion

arXiv 2309.14781 ↗First posted 26 Sep 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Change detection in satellite imagery seeks to find occurrences of targeted changes in a given scene taken at different instants. This task has several applications ranging from land-cover mapping, to anthropogenic activity monitory as well as climate change and natural hazard damage assessment. However, change detection is highly challenging due to the acquisition conditions and also to the subjectivity of changes. In this paper, we devise a novel algorithm for change detection based on active learning. The proposed method is based on a question and answer model that probes an oracle (user) about the relevance of changes only on a small set of critical images (referred to as virtual exemplars), and according to oracle's responses updates deep neural network (DNN) classifiers. The main contribution resides in a novel adversarial model that allows learning the most representative, diverse and uncertain virtual exemplars (as inverted preimages of the trained DNNs) that challenge (the most) the trained DNNs, and this leads to a better re-estimate of these networks in the subsequent iterations of active learning. Experiments show the out-performance of our proposed deep-net inversion against the related work.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 45 of its 135 references that are in the map. First posted on arXiv 26 Sep 2023.

Builds on

45 of 135 references.

References · 45

  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
33 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. 2020Deep Visual Domain Adaptationcited by 91
  23. 2018Efficient Active Learning for Image Classification and Segmentation using a Sample Selection and Conditional Generative Adversarial Networkcited by 74
  24. 2018Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoderscited by 74
  25. 2017Generative Adversarial Active Learningcited by 70
  26. 2019Bayesian Batch Active Learning as Sparse Subset Approximationcited by 68
  27. 2017Automated Scalable Bayesian Inference via Hilbert Coresetscited by 55
  28. 2018Adversarial Sampling for Active Learningcited by 51
  29. 2018Active Learning for Deep Object Detectioncited by 50
  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. 2021Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 20
  33. 2018Cost-effective Object Detection: Active Sample Mining with Switchable Selection Criteriacited by 12

Built on by

Not cited yet.