mlsanityData to 7 Oct 2026

Federated Online Adaptation for Deep Stereo

arXiv 2405.14873 ↗First posted 23 May 2024cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

We introduce a novel approach for adapting deep stereo networks in a collaborative manner. By building over principles of federated learning, we develop a distributed framework allowing for demanding the optimization process to a number of clients deployed in different environments. This makes it possible, for a deep stereo network running on resourced-constrained devices, to capitalize on the adaptation process carried out by other instances of the same architecture, and thus improve its accuracy in challenging environments even when it cannot carry out adaptation on its own. Experimental results show how federated adaptation performs equivalently to on-device adaptation, and even better when dealing with challenging environments.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 50 of its 77 references that are in the map. First posted on arXiv 23 May 2024.

Builds on

50 of 77 references.

References · 50

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  3. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  4. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  5. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  6. 2021Model-Contrastive Federated Learningcited by 762
  7. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
  8. 2018Pyramid Stereo Matching Networkcited by 486
  9. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 371
  10. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 359
  11. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
  12. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 348
38 more
  1. 2021DSEC: A Stereo Event Camera Dataset for Driving Scenarioscited by 297
  2. 2022Unifying Flow, Stereo and Depth Estimationcited by 270
  3. 2019GA-Net: Guided Aggregation Net for End-to-end Stereo Matchingcited by 242
  4. 2020AANet: Adaptive Aggregation Network for Efficient Stereo Matchingcited by 202
  5. 2022Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlationcited by 197
  6. 2020Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformerscited by 190
  7. 2023Iterative Geometry Encoding Volume for Stereo Matchingcited by 188
  8. 2022Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learningcited by 172
  9. 2020Hierarchical Neural Architecture Search for Deep Stereo Matchingcited by 166
  10. 2021CFNet: Cascade and Fused Cost Volume for Robust Stereo Matchingcited by 153
  11. 2015Stereo Matching by Training a Convolutional Neural Network to Compare Image Patchescited by 151
  12. 2019Hierarchical Deep Stereo Matching on High-resolution Imagescited by 126
  13. 2020HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matchingcited by 120
  14. 2021SMD-Nets: Stereo Mixture Density Networkscited by 118
  15. 2021Local Learning Matters: Rethinking Data Heterogeneity in Federated Learningcited by 114
  16. 2019Domain-invariant Stereo Matching Networkscited by 108
  17. 2022Layer-wised Model Aggregation for Personalized Federated Learningcited by 95
  18. 2018Real-time self-adaptive deep stereocited by 80
  19. 2022On the Importance and Applicability of Pre-Training for Federated Learningcited by 71
  20. 2021Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitationcited by 47
  21. 2022Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspectivecited by 46
  22. 2023NeRF-Supervised Deep Stereocited by 46
  23. 2020Learning Stereo from Single Imagescited by 44
  24. 2022GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Featurecited by 43
  25. 2019Learning to Adapt for Stereocited by 42
  26. 2022ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networkscited by 39
  27. 2022Context-Enhanced Stereo Transformercited by 37
  28. 2020Reversing the cycle: self-supervised deep stereo through enhanced monocular distillationcited by 34
  29. 2017Self-Supervised Learning for Stereo Matching with Self-Improving Abilitycited by 32
  30. 2020Matching-space Stereo Networks for Cross-domain Generalizationcited by 32
  31. 2019Unsupervised Domain Adaptation for Depth Prediction from Imagescited by 29
  32. 2019Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondencecited by 23
  33. 2020Continual Adaptation for Deep Stereocited by 23
  34. 2023Digging Into Uncertainty-based Pseudo-label for Robust Stereo Matchingcited by 22
  35. 2021Neural Disparity Refinement for Arbitrary Resolution Stereocited by 20
  36. 2022Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditionscited by 16
  37. 2023To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentationcited by 14
  38. 2022TemporalStereo: Efficient Spatial-Temporal Stereo Matching Networkcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 4; 2026: 3.

12 papers.

  1. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 45
  2. 2024LightStereo: Channel Boost Is All You Need for Efficient 2D Cost Aggregationcited by 28
  3. 2024A Survey on Deep Stereo Matching in the Twentiescited by 23
  4. 2025Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentationcited by 7
  5. 2024LiDAR-Event Stereo Fusion with Hallucinationscited by 6
  6. 2025NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfacescited by 3
  7. 2025RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereocited by 1
  8. 2024Active Stereo in the Wild through Virtual Pattern Projectioncited by 0
  9. 2025Preserving Guidance in Cost-Volume Retrieval under Extreme LiDAR Sparsity in Iterative Stereocited by 0
  10. 2026EventHub: Data Factory for Generalizable Event-Based Stereo Networks without Active Sensorscited by 0
  11. 2026Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereocited by 0
  12. 2026FeDepth: Federated Learning for Depth Estimation under Robot Heterogeneitycited by 0