A real-time detector with deformable attention, domain alignment, view-conditioning, and adaptive augmentation reports 49.1 COCO mAP and large gains on self-built fisheye, panorama, drone, and game-style benchmarks.
Yolo-ms: Rethinking multi-scale representation learning for real-time object detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
YOLOv14: Adaptive Real-Time Object Detection for Diverse Imaging Conditions
A real-time detector with deformable attention, domain alignment, view-conditioning, and adaptive augmentation reports 49.1 COCO mAP and large gains on self-built fisheye, panorama, drone, and game-style benchmarks.