mlsanityData to 14 Oct 2026

Continual Barlow Twins: continual self-supervised learning for remote sensing semantic segmentation

arXiv 2205.11319 ↗First posted 23 May 2022cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

In the field of Earth Observation (EO), Continual Learning (CL) algorithms have been proposed to deal with large datasets by decomposing them into several subsets and processing them incrementally. The majority of these algorithms assume that data is (a) coming from a single source, and (b) fully labeled. Real-world EO datasets are instead characterized by a large heterogeneity (e.g., coming from aerial, satellite, or drone scenarios), and for the most part they are unlabeled, meaning they can be fully exploited only through the emerging Self-Supervised Learning (SSL) paradigm. For these reasons, in this paper we propose a new algorithm for merging SSL and CL for remote sensing applications, that we call Continual Barlow Twins (CBT). It combines the advantages of one of the simplest self-supervision techniques, i.e., Barlow Twins, with the Elastic Weight Consolidation method to avoid catastrophic forgetting. In addition, for the first time we evaluate SSL methods on a highly heterogeneous EO dataset, showing the effectiveness of these strategies on a novel combination of three almost non-overlapping domains datasets (airborne Potsdam dataset, satellite US3D dataset, and drone UAVid dataset), on a crucial downstream task in EO, i.e., semantic segmentation. Encouraging results show the superiority of SSL in this setting, and the effectiveness of creating an incremental effective pretrained feature extractor, based on ResNet50, without the need of relying on the complete availability of all the data, with a valuable saving of time and resources.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 33 of its 75 references that are in the map. First posted on arXiv 23 May 2022.

Builds on

33 of 75 references.

References · 33

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  5. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  6. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
  7. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  8. 2019Contrastive Multiview Codingcited by 1,301
  9. 2020Self-supervised Learning: Generative or Contrastivecited by 694
  10. 2020A Survey on Contrastive Self-supervised Learningcited by 554
  11. 2021Graph Self-Supervised Learning: A Surveycited by 289
  12. 2019BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understandingcited by 234
21 more
  1. 2021Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Datacited by 215
  2. 2020Geography-Aware Self-Supervised Learningcited by 190
  3. 2021Self-Supervised Models are Continual Learnerscited by 149
  4. 2021Self-Supervised Representation Learning: Introduction, Advances and Challengescited by 148
  5. 2021Self-Supervised Pretraining Improves Self-Supervised Pretrainingcited by 82
  6. 2022DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentationcited by 78
  7. 2018Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blockscited by 76
  8. 2020Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunitiescited by 71
  9. 2020OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learningcited by 65
  10. 2020Multi-Attention-Network for Semantic Segmentation of Fine Resolution Remote Sensing Imagescited by 59
  11. 2021Self-Supervised Learning of Remote Sensing Scene Representations Using Contrastive Multiview Codingcited by 58
  12. 2018Semantic Stereo for Incidental Satellite Imagescited by 53
  13. 2021Geographical Knowledge-driven Representation Learning for Remote Sensing Imagescited by 37
  14. 2020Remote Sensing Image Scene Classification with Self-Supervised Paradigm under Limited Labeled Samplescited by 36
  15. 2022The Challenges of Continuous Self-Supervised Learningcited by 36
  16. 2018Incremental Learning for Semantic Segmentation of Large-Scale Remote Sensing Datacited by 35
  17. 2020The color out of space: learning self-supervised representations for Earth Observation imagerycited by 34
  18. 2021Global and Local Contrastive Self-Supervised Learning for Semantic Segmentation of HR Remote Sensing Imagescited by 31
  19. 2021Self-supervised Change Detection in Multi-view Remote Sensing Imagescited by 25
  20. 2021SPeCiaL: Self-Supervised Pretraining for Continual Learningcited by 12
  21. 2022Weakly-supervised continual learning for class-incremental segmentationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 8; 2024: 6; 2025: 4; 2026: 2.

22 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  2. 2022Self-supervised Learning in Remote Sensing: A Reviewcited by 137
  3. 2023SynDrone -- Multi-modal UAV Dataset for Urban Scenarioscited by 28
  4. 2022Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Workscited by 24
  5. 2023A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Applicationcited by 21
  6. 2023Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learningcited by 18
  7. 2023Knowledge Accumulation in Continually Learned Representations and the Issue of Feature Forgettingcited by 16
  8. 2023GeoMultiTaskNet: remote sensing unsupervised domain adaptation using geographical coordinatescited by 12
  9. 2025Parameter-Efficient Adaptation of Geospatial Foundation Models through Embedding Deflectioncited by 10
  10. 2024Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applicationscited by 8
  11. 2023From MNIST to ImageNet and Back: Benchmarking Continual Curriculum Learningcited by 6
  12. 2024Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learningcited by 4
10 more
  1. 2024Continual Panoptic Perception: Towards Multi-modal Incremental Interpretation of Remote Sensing Imagescited by 4
  2. 2023Out-of-distribution forgetting: vulnerability of continual learning to intra-class distribution shiftcited by 3
  3. 2024Cross-sensor self-supervised training and alignment for remote sensingcited by 3
  4. 2024Towards Non-Exemplar Semi-Supervised Class-Incremental Learningcited by 1
  5. 2024Towards Synchronous Memorizability and Generalizability with Site-Modulated Diffusion Replay for Cross-Site Continual Segmentationcited by 1
  6. 2025Continual Self-Supervised Learning with Masked Autoencoders in Remote Sensingcited by 1
  7. 2025A Plasticity-Aware Method for Continual Self-Supervised Learning in Remote Sensingcited by 0
  8. 2025CL-BioGAN: Biologically-Inspired Cross-Domain Continual Learning for Hyperspectral Anomaly Detectioncited by 0
  9. 2026Evolving Without Ending: Unifying Multimodal Incremental Learning for Continual Panoptic Perceptioncited by 0
  10. 2026Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Modelscited by 0