ModelYOLOv8 small / YOLOv8-s
YOLOv8s
The small-scale variant of the YOLOv8 object detection series released by Ultralytics, based on a single-stage detection architecture. It is characterized by real-time inference speed and low computational resource requirements, and is widely applied to computer vision tasks such as pedestrian detection and autonomous driving perception.
Timeline (last 90 days)
Oct 16
At a sample size of 200-500, YOLO-series models (such as YOLOv8n and YOLOv8s) can usually converge to usable accuracy.
Unverified50%
Oct 5
The study selected a fixed YOLOv8s pedestrian detector and conducted cross-domain auditing on the PIE and JAAD pedestrian datasets.
Unverified50%