mlsanityData to 7 Oct 2026

Unsupervised Domain Adaptation for Nighttime Aerial Tracking

arXiv 2203.10541 ↗First posted 20 Mar 2022cs.CVcited by 56

Not on the map. Why?

Abstract (arXiv)

Previous advances in object tracking mostly reported on favorable illumination circumstances while neglecting performance at nighttime, which significantly impeded the development of related aerial robot applications. This work instead develops a novel unsupervised domain adaptation framework for nighttime aerial tracking (named UDAT). Specifically, a unique object discovery approach is provided to generate training patches from raw nighttime tracking videos. To tackle the domain discrepancy, we employ a Transformer-based bridging layer post to the feature extractor to align image features from both domains. With a Transformer day/night feature discriminator, the daytime tracking model is adversarially trained to track at night. Moreover, we construct a pioneering benchmark namely NAT2021 for unsupervised domain adaptive nighttime tracking, which comprises a test set of 180 manually annotated tracking sequences and a train set of over 276k unlabelled nighttime tracking frames. Exhaustive experiments demonstrate the robustness and domain adaptability of the proposed framework in nighttime aerial tracking. The code and benchmark are available at https://github.com/vision4robotics/UDAT.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Builds on 42 of its 56 references that are in the map. First posted on arXiv 20 Mar 2022.

Builds on

42 of 56 references.

References · 42

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  7. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  8. 2016Least Squares Generative Adversarial Networkscited by 1,000
  9. 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 566
  10. 2018GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wildcited by 471
  11. 2018SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networkscited by 445
  12. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
30 more
  1. 2021Transformer Trackingcited by 412
  2. 2015Return of Frustratingly Easy Domain Adaptationcited by 389
  3. 2021Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Trackingcited by 220
  4. 2020Ocean: Object-aware Anchor-free Trackingcited by 212
  5. 2021Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimationcited by 192
  6. 2020Siamese Box Adaptive Network for Visual Trackingcited by 189
  7. 2018Distractor-aware Siamese Networks for Visual Object Trackingcited by 187
  8. 2019SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelinescited by 177
  9. 2019Deeper and Wider Siamese Networks for Real-Time Visual Trackingcited by 156
  10. 2019SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Trackingcited by 147
  11. 2020LaSOT: A High-quality Large-scale Single Object Tracking Benchmarkcited by 130
  12. 2017YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Videocited by 109
  13. 2020Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentationcited by 86
  14. 2021DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentationcited by 80
  15. 2019Learning the Model Update for Siamese Trackerscited by 75
  16. 2021HiFT: Hierarchical Feature Transformer for Aerial Trackingcited by 72
  17. 2019D3S -- A Discriminative Single Shot Segmentation Trackercited by 69
  18. 2017Learning Background-Aware Correlation Filters for Visual Trackingcited by 65
  19. 2020AutoTrack: Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal Regularizationcited by 62
  20. 2016Siamese Instance Search for Trackingcited by 60
  21. 2019Learning Aberrance Repressed Correlation Filters for Real-Time UAV Trackingcited by 47
  22. 2021SiamAPN++: Siamese Attentional Aggregation Network for Real-Time UAV Trackingcited by 38
  23. 2020Scale Equivariance Improves Siamese Trackingcited by 32
  24. 2021Learning to Relate Depth and Semantics for Unsupervised Domain Adaptationcited by 32
  25. 2020Unsupervised Deep Representation Learning for Real-Time Trackingcited by 29
  26. 2021DarkLighter: Light Up the Darkness for UAV Trackingcited by 24
  27. 2020Siamese Anchor Proposal Network for High-Speed Aerial Trackingcited by 22
  28. 2021Learning to Track Objects from Unlabeled Videoscited by 21
  29. 2019Towards a Robust Aerial Cinematography Platform: Localizing and Tracking Moving Targets in Unstructured Environmentscited by 18
  30. 2021ADTrack: Target-Aware Dual Filter Learning for Real-Time Anti-Dark UAV Trackingcited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 13; 2024: 15; 2025: 14; 2026: 8.

56 papers.

Sort:

By area:

  1. 2023Foundational Models Defining a New Era in Vision: A Survey and Outlookcited by 109
  2. 20232PCNet: Two-Phase Consistency Training for Day-to-Night Unsupervised Domain Adaptive Object Detectioncited by 30
  3. 2024EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognitioncited by 23
  4. 2023Bilevel Fast Scene Adaptation for Low-Light Image Enhancementcited by 22
  5. 2025Similarity-Guided Layer-Adaptive Vision Transformer for UAV Trackingcited by 22
  6. 2023SAM-DA: UAV Tracks Anything at Night with SAM-Powered Domain Adaptationcited by 17
  7. 2023Boosting Object Detection with Zero-Shot Day-Night Domain Adaptationcited by 17
  8. 2023DCPT: Darkness Clue-Prompted Tracking in Nighttime UAVscited by 16
  9. 2022HighlightNet: Highlighting Low-Light Potential Features for Real-Time UAV Trackingcited by 14
  10. 2023GeoMultiTaskNet: remote sensing unsupervised domain adaptation using geographical coordinatescited by 12
  11. 2022Siamese Object Tracking for Unmanned Aerial Vehicle: A Review and Comprehensive Analysiscited by 11
  12. 2023Black-box Unsupervised Domain Adaptation with Bi-directional Atkinson-Shiffrin Memorycited by 11
38 more
  1. 2025Securing the Skies: A Comprehensive Survey on Anti-UAV Methods, Benchmarking, and Future Directionscited by 11
  2. 2025AirScape: An Aerial Generative World Model with Motion Controllabilitycited by 7
  3. 2024Prompt-Driven Temporal Domain Adaptation for Nighttime UAV Trackingcited by 6
  4. 2022PVT++: A Simple End-to-End Latency-Aware Visual Tracking Frameworkcited by 5
  5. 2024Segment Anything for Videos: A Systematic Surveycited by 5
  6. 2024MambaTrack: Exploiting Dual-Enhancement for Night UAV Trackingcited by 5
  7. 2023Aerial Diffusion: Text Guided Ground-to-Aerial View Translation from a Single Image using Diffusion Modelscited by 4
  8. 2024Domain Adaptive Detection of MAVs: A Benchmark and Noise Suppression Networkcited by 4
  9. 2024NT-VOT211: A Large-Scale Benchmark for Night-time Visual Object Trackingcited by 3
  10. 2025DARTer: Dynamic Adaptive Representation Tracker for Nighttime UAV Trackingcited by 3
  11. 2023Mutual-Learning Knowledge Distillation for Nighttime UAV Trackingcited by 2
  12. 2023Singular Value Penalization and Semantic Data Augmentation for Fully Test-Time Adaptationcited by 2
  13. 2024Low-Light Object Tracking: A Benchmarkcited by 2
  14. 2024Camouflaged Object Tracking: A Benchmarkcited by 2
  15. 2024Enhancing Nighttime UAV Tracking with Light Distribution Suppressioncited by 2
  16. 2024MambaNUT: Nighttime UAV Tracking via Mamba-based Adaptive Curriculum Learningcited by 2
  17. 2025COST: Contrastive One-Stage Transformer for Vision-Language Small Object Trackingcited by 2
  18. 2025UMDATrack: Unified Multi-Domain Adaptive Tracking Under Adverse Weather Conditionscited by 2
  19. 2025Saliency-Guided Domain Adaptation for Left-Hand Driving in Autonomous Steeringcited by 2
  20. 2022Siamese Object Tracking for Vision-Based UAM Approaching with Pairwise Scale-Channel Attentioncited by 1
  21. 2022Day2Dark: Pseudo-Supervised Activity Recognition beyond Silent Daylightcited by 1
  22. 2023DDAM-PS: Diligent Domain Adaptive Mixer for Person Searchcited by 1
  23. 2024Tracking Reflected Objects: A Benchmarkcited by 1
  24. 2024Progressive Domain Adaptation for Thermal Infrared Object Trackingcited by 1
  25. 2024EventDance++: Language-guided Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognitioncited by 1
  26. 2024DaDiff: Domain-aware Diffusion Model for Nighttime UAV Trackingcited by 1
  27. 2025Prmpt2Adpt: Prompt-Based Zero-Shot Domain Adaptation for Resource-Constrained Environmentscited by 1
  28. 2025TrackingMiM: Efficient Mamba-in-Mamba Serialization for Real-time UAV Object Trackingcited by 1
  29. 2025Dynamic Semantic-Aware Correlation Modeling for UAV Trackingcited by 1
  30. 2022One-Time Model Adaptation to Heterogeneous Clients: An Intra-Client and Inter-Image Attention Designcited by 0
  31. 2023Dual Degradation-Inspired Deep Unfolding Network for Low-Light Image Enhancementcited by 0
  32. 2024Cooperative Students: Navigating Unsupervised Domain Adaptation in Nighttime Object Detectioncited by 0
  33. 2025SegDesicNet: Lightweight Semantic Segmentation in Remote Sensing with Geo-Coordinate Embeddings for Domain Adaptationcited by 0
  34. 2025T-SiamTPN: Temporal Siamese Transformer Pyramid Networks for Robust and Efficient UAV Trackingcited by 0
  35. 2025DPTrack:Directional Kernel-Guided Prompt Learning for Robust Nighttime Aerial Trackingcited by 0
  36. 2025MATrack: Efficient Multiscale Adaptive Tracker for Real-Time Nighttime UAV Operationscited by 0
  37. 2026Breaking Smooth-Motion Assumptions: A UAV Benchmark for Multi-Object Tracking in Complex and Adverse Conditionscited by 0
  38. 2026Dual Prompt-Driven Feature Encoding for Nighttime UAV Trackingcited by 0

50 most cited of 56 All 56 (JSON)