mlsanityData to 7 Oct 2026

Frugal Learning of Virtual Exemplars for Label-Efficient Satellite Image Change Detection

arXiv 2203.11559 ↗First posted 22 Mar 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we devise a novel interactive satellite image change detection algorithm based on active learning. The proposed framework is iterative and relies on a question and answer model which asks the oracle (user) questions about the most informative display (subset of critical images), and according to the user's responses, updates change detections. The contribution of our framework resides in a novel display model which selects the most representative and diverse virtual exemplars that adversely challenge the learned change detection functions, thereby leading to highly discriminating functions in the subsequent iterations of active learning. Extensive experiments, conducted on the challenging task of interactive satellite image change detection, show the superiority of the proposed virtual display model against the related work.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 114 references that are in the map. First posted on arXiv 22 Mar 2022.

Builds on

31 of 114 references.

References · 31

  1. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  2. 2016Matching Networks for One Shot Learningcited by 2,246
  3. 2017Deep Bayesian Active Learning with Image Datacited by 812
  4. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 806
  5. 2020Self-supervised Learning: Generative or Contrastivecited by 693
  6. 2017Generative Adversarial Networks: An Overviewcited by 588
  7. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  8. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 453
  9. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  10. 2019Revisiting Self-Supervised Visual Representation Learningcited by 250
  11. 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
  12. 2017Semantic Autoencoder for Zero-Shot Learningcited by 133
19 more
  1. 2018CurriculumNet: Weakly Supervised Learning from Large-Scale Web Imagescited by 126
  2. 2017Generalized Zero-Shot Learning via Synthesized Examplescited by 114
  3. 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
  4. 2017Self-supervised Learning of Motion Capturecited by 97
  5. 2017A Generative Adversarial Approach for Zero-Shot Learning from Noisy Textscited by 96
  6. 2018Boosting Self-Supervised Learning via Knowledge Transfercited by 92
  7. 2021S2Looking: A Satellite Side-Looking Dataset for Building Change Detectioncited by 77
  8. 2015Zero-Shot Learning via Semantic Similarity Embeddingcited by 74
  9. 2017Automated Scalable Bayesian Inference via Hilbert Coresetscited by 55
  10. 2018Preserving Semantic Relations for Zero-Shot Learningcited by 35
  11. 2020Hi-UCD: A Large-scale Dataset for Urban Semantic Change Detection in Remote Sensing Imagerycited by 33
  12. 2018Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learningcited by 26
  13. 2021Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 20
  14. 2020A Weakly Supervised Convolutional Network for Change Segmentation and Classificationcited by 11
  15. 2017Stochastic Graphlet Embeddingcited by 9
  16. 2020Epipolar-Guided Deep Object Matching for Scene Change Detectioncited by 7
  17. 2019Procedural Synthesis of Remote Sensing Images for Robust Change Detection with Neural Networkscited by 6
  18. 2016Learning deep structured network for weakly supervised change detectioncited by 3
  19. 2018Targeted change detection in remote sensing imagescited by 3

Built on by

Not cited yet.