YOLOv14在复杂影像条件下实现高精度实时检测，适应鱼眼、全景等挑战性场景。
YOLOv14: Adaptive Real-Time Object Detection for Diverse Imaging Conditions
- 采用自适应路由与调制机制，通过少量目标域图像实现高效风格迁移。
- 在COCO上达49.1 mAP，对游戏、无人机等场景提升超26点，推理仅需2.91毫秒。
- 适合部署于自动驾驶、无人机等真实复杂环境，兼具速度与鲁棒性。
实时目标检测器在理想条件下表现优异，但在非理想输入（如鱼眼畸变、游戏渲染内容、航拍视角、360°全景）下性能急剧下降。本文提出YOLOv14，一种统一的自适应检测框架，通过四种互补机制实现对多种影像变化的鲁棒性，其核心为新颖的自适应路由与调制（ARM）范式。不同于传统无监督域适应，本方法采用目标先验引导的源域增强（TP-SDA），仅需50张未标注的目标域图像离线估计风格统计量，对抗性对齐作为轻量正则器而非主要适应驱动力。该框架在T4 GPU上实现2.91毫秒推理速度，COCO val2017上达到49.1 mAP，相较YOLOv12s在鱼眼、全景、无人机和游戏风格场景分别提升+4.1、+6.6、+6.4和+26.1 mAP。关键的是，在真实游戏截图（GTA-V、Unity）上验证了泛化能力，获得+14.2 mAP提升，证实其超越合成基准的实际迁移能力。代码与模型已开源。
原文摘要 · Abstract (English)
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 360°panoramas. 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。