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

• URL: http://arxiv.org/abs/2608.04720v2
• Date: Fri, 07 Aug 2026 05:16:40 GMT
• Title: YOLOv14: Adaptive Real-Time Object Detection for Diverse Imaging Conditions
• Abstract summary: Real-time object detectors achieve remarkable accuracy under controlled conditions, but degrade sharply on non-ideal inputs.<n>We present YOLOv14, a detection framework with four adaptive mechanisms designed for specific types of inputvariation.<n>YOLOv14 achieves 49.1 mAP on COCO val 2017 at 2.91 ms (T4 GPU), and delivers substantial gains on fisheye (+4.1 mAP), panorama (+6.6 mAP), drone (+6.4 mAP)
• Score: 8.040649850566211
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real-time object detectors achieve remarkable accuracy under controlled conditions, yet degrade sharply on non-ideal inputs: fisheye distortion, game-renderedcharacters, aerial viewpoints, and 360°panoramas. We present YOLOv14, a detection framework with four adaptive mechanisms designed for specific types of inputvariation:(1) Deformable Area-Attention with windowed computation and shiftedwindows for geometric distortion;(2) Multi-level Game2Real Alignment with progressive adversarial training for domain shift;(3) View-Aware Contrastive Learning with adaptive temperature for viewpoint invariance; and (4) Scene-Adaptive Augmentation with dynamic loss balancing for scene diversity. Together, YOLOv14 achieves 49.1 mAP on COCO val2017 at 2.91 ms (T4 GPU), and delivers substantial gains on fisheye (+4.1 mAP), panorama (+6.6 mAP), drone (+6.4 mAP), andour synthesized game-character benchmark (+26.1 mAP). We release code and models to facilitate reproducible research.

Related papers

• 4DP-QA: Scalable QA for 4D Perception in Vision Language Models [68.67551474392373]
  We present a generation pipeline that focuses on motion-related scene understanding.<n>We take particular care of the entanglement of camera and object motion by casting tracking in both the traditional way and in a novel, fixed reference system, dubbed True-Motion Tracking.<n>From this pipeline, we generate a large-scale training dataset of 400K samples, 4DP-QA (4D Perception QA), and a 2.2K-sample benchmark, 4DP-QA-Bench.
  arXiv  Detail & Related papers  (2026-06-10T01:49:55Z)
• Distortion-Aware PETR for BEV Object Detection with Mixed Pinhole-Fisheye Cameras [0.0]
  Fisheye cameras are widely deployed in autonomous driving perception suites for their low cost and full-coverage field of view (FOV)<n>Severe radial distortion challenges most BEV detectors by violating the fundamental assumption of uniform sampling.<n>We propose Distortion-Aware PETR (DAPETR), a projection-free detector tailored for mixed pinhole-fisheye camera setups.
  arXiv  Detail & Related papers  (2026-06-07T15:32:10Z)
• Real-Time Oriented Object Detection Transformer in Remote Sensing Images [36.48263676876599]
  We propose a real-time oriented object detection transformer, the first real-time end-to-end oriented object detector.<n>Specifically, angle distribution refinement is proposed to reformulate angle regression.<n>We also propose oriented contrastive denoising to stabilize training and analyze four noise modes.
  arXiv  Detail & Related papers  (2026-03-16T16:28:31Z)
• YOLO11-4K: An Efficient Architecture for Real-Time Small Object Detection in 4K Panoramic Images [7.5117172634019775]
  We introduce YOLO11-4K, an efficient real-time detection framework tailored for 4K panoramic images.<n>The architecture incorporates a novel multi-scale detection head with a P2 layer to improve sensitivity to small objects.<n>YOLO11-4K achieves 0.95 mAP at 0.50 IoU with 28.3 milliseconds inference per frame, representing a 75 percent latency reduction compared to YOLO11.
  arXiv  Detail & Related papers  (2025-12-18T13:00:05Z)
• Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models [79.06910348413861]
  We introduce Diff4Splat, a feed-forward method that synthesizes controllable and explicit 4D scenes from a single image.<n>Given a single input image, a camera trajectory, and an optional text prompt, Diff4Splat directly predicts a deformable 3D Gaussian field that encodes appearance, geometry, and motion.
  arXiv  Detail & Related papers  (2025-11-01T11:16:25Z)
• TY-RIST: Tactical YOLO Tricks for Real-time Infrared Small Target Detection [6.0340092200636475]
  Infrared small target detection (IRSTD) is critical for defense and surveillance but remains challenging.<n>We propose TY-RIST, an optimized YOLOv12n architecture that integrates a stride-aware backbone with fine-grained receptive fields.<n>Experiments on four benchmarks and across 20 different models demonstrate state-of-the-art performance, improving mAP at 0.5 IoU by +7.9%, Precision by +3%, and Recall by +10.2%.
  arXiv  Detail & Related papers  (2025-09-26T20:36:57Z)
• A Comparative Study of YOLOv8 to YOLOv11 Performance in Underwater Vision Tasks [0.0]
  One-stage detectors from the YOLO family are attractive because they fuse localization and classification in a single, low-latency network.<n>We curate two datasets that span contrasting operating conditions: a Coral Disease set (4,480 images, 18 classes) and a Fish Species set (7,500 images, 20 classes)<n>We train YOLOvs, YOLOv9-s, YOLOv10-s, and YOLOv11-s with identical hyperferences and evaluate precision, recall, mAP50, mAP50-95, per-image inference time, and frames-per-second (FPS)
  arXiv  Detail & Related papers  (2025-09-16T05:12:59Z)
• Enhancing Underwater Imaging with 4-D Light Fields: Dataset and Method [77.80712860663886]
  4-D light fields (LFs) enhance underwater imaging plagued by light absorption, scattering, and other challenges.<n>We propose a progressive framework for underwater 4-D LF image enhancement and depth estimation.<n>We construct the first 4-D LF-based underwater image dataset for quantitative evaluation and supervised training of learning-based methods.
  arXiv  Detail & Related papers  (2024-08-30T15:06:45Z)
• MonoTDP: Twin Depth Perception for Monocular 3D Object Detection in Adverse Scenes [49.21187418886508]
  This paper proposes a monocular 3D detection model designed to perceive twin depth in adverse scenes, termed MonoTDP. We first introduce an adaptive learning strategy to aid the model in handling uncontrollable weather conditions, significantly resisting degradation caused by various degrading factors. Then, to address the depth/content loss in adverse regions, we propose a novel twin depth perception module that simultaneously estimates scene and object depth.
  arXiv  Detail & Related papers  (2023-05-18T13:42:02Z)
• Geometric-aware Pretraining for Vision-centric 3D Object Detection [77.7979088689944]
  We propose a novel geometric-aware pretraining framework called GAPretrain. GAPretrain serves as a plug-and-play solution that can be flexibly applied to multiple state-of-the-art detectors. We achieve 46.2 mAP and 55.5 NDS on the nuScenes val set using the BEVFormer method, with a gain of 2.7 and 2.1 points, respectively.
  arXiv  Detail & Related papers  (2023-04-06T14:33:05Z)
• Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation [73.48323921632506]
  We address panoramic semantic segmentation which is under-explored due to two critical challenges. First, we propose an upgraded Transformer for Panoramic Semantic, i.e., Trans4PASS+, equipped with Deformable Patch Embedding (DPE) and Deformable (DMLPv2) modules. Second, we enhance the Mutual Prototypical Adaptation (MPA) strategy via pseudo-label rectification for unsupervised domain adaptive panoramic segmentation. Third, aside from Pinhole-to-Panoramic (Pin2Pan) adaptation, we create a new dataset (SynPASS) with 9,080 panoramic images
  arXiv  Detail & Related papers  (2022-07-25T00:42:38Z)
• EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm [111.17100512647619]
  This paper explains the rationality of Vision Transformer by analogy with the proven practical evolutionary algorithm (EA) We propose a novel pyramid EATFormer backbone that only contains the proposed EA-based transformer (EAT) block. Massive quantitative and quantitative experiments on image classification, downstream tasks, and explanatory experiments demonstrate the effectiveness and superiority of our approach.
  arXiv  Detail & Related papers  (2022-06-19T04:49:35Z)
• Decoupled Adaptation for Cross-Domain Object Detection [69.5852335091519]
  Cross-domain object detection is more challenging than object classification. D-adapt achieves a state-of-the-art results on four cross-domain object detection tasks.
  arXiv  Detail & Related papers  (2021-10-06T08:43:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.