mlsanityData to 7 Oct 2026

YOLOv14: Adaptive Real-Time Object Detection for Diverse Imaging Conditions

arXiv 2608.04720 ↗First posted 5 Aug 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Real-time object detectors achieve remarkable accuracy under controlled conditions, yet degrade sharply on non-ideal inputs-fisheye distortion, game-rendered content, aerial views, and 360degpanoramas. We present YOLOv14, a unified adaptive detection framework that addresses these variations through four complementary mechanisms, formalized under a novel Adaptive Routing and Modulation (ARM) paradigm. Unlike conventional unsupervised domain adaptation, our approach employs Target-Prior Guided Source-Domain Augmentation(TP-SDA), using only 50 unlabeled target images offline to estimate style statistics, while adversarial alignment serves as a lightweight regularizer rather than the primary adaptation driver. Together, these components enable YOLOv14 to achieve 49.1 mAP on COCO val2017 at 2.91 ms (T4 GPU), with substantial gains of +4.1 (fisheye), +6.6 (panorama), +6.4 (drone), and +26.1 (gamestylized) mAP over YOLOv12s. Crucially, we validate generalization on real-world game screenshots (GTA-V, Unity), achieving +14.2 mAP, confirming practical transferability beyond synthetic benchmarks. Code and models are released at https://github.com/zhangcbb/yolov14.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 44 of its 60 references that are in the map. First posted on arXiv 5 Aug 2026.

Builds on

44 of 60 references.

References · 44

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2020End-to-End Object Detection with Transformerscited by 7,384
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  6. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  7. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  8. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  9. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  10. 2018YOLOv3: An Incremental Improvementcited by 2,652
  11. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  12. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
32 more
  1. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  2. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  3. 2017Deformable Convolutional Networkscited by 1,481
  4. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  5. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  6. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  7. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  8. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  9. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  10. 2021Domain Generalization: A Surveycited by 760
  11. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  12. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  13. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  14. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  15. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  16. 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 454
  17. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
  18. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
  19. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 408
  20. 2025YOLOv12: Attention-Centric Real-Time Object Detectorscited by 300
  21. 2022Vision Transformer with Deformable Attentioncited by 293
  22. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
  23. 2020VarifocalNet: An IoU-aware Dense Object Detectorcited by 230
  24. 2021TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentationcited by 225
  25. 2018DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptationcited by 212
  26. 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 202
  27. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 177
  28. 2019WoodScape: A multi-task, multi-camera fisheye dataset for autonomous drivingcited by 142
  29. 2019Learning Data Augmentation Strategies for Object Detectioncited by 139
  30. 2022PP-YOLOE: An evolved version of YOLOcited by 75
  31. 2023Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanismcited by 51
  32. 2022SIoU Loss: More Powerful Learning for Bounding Box Regressioncited by 49

Built on by

Not cited yet.