Object Detection: Supported Models

Object Detection & Tracking is built on the robust Ultralytics model architecture. We offer support for a wide range of models, each tailored to specific tasks like object detection, instance segmentation, image classification, pose estimation and multi-object tracking.

Featured Models

Here are some of the key models supported:

YOLOv5

• Description: An improved version of the YOLO architecture by Ultralytics, offering better performance and speed trade-offs compared to previous versions.

YOLOv8

• Description: The latest version of the YOLO family, featuring enhanced capabilities such as instance segmentation, pose/keypoints estimation, and classification.

YOLOv9

• Description: An experimental model trained on the Ultralytics YOLOv5 codebase implementing Programmable Gradient Information (PGI).

YOLOv10

• Description: By Tsinghua University, featuring NMS-free training and efficiency-accuracy driven architecture, delivering state-of-the-art performance and latency.

Segment Anything Model (SAM)

• Description: Meta's Segment Anything Model (SAM).

Mobile Segment Anything Model (MobileSAM)

• Description: MobileSAM for mobile applications, by Kyung Hee University.

Fast Segment Anything Model (FastSAM)

• Description: FastSAM by Image & Video Analysis Group, Institute of Automation, Chinese Academy of Sciences.

YOLO-NAS

• Description: YOLO Neural Architecture Search (NAS) Models.

Realtime Detection Transformers (RT-DETR)

• Description: Baidu's PaddlePaddle Realtime Detection Transformer (RT-DETR) models.

YOLO-World

• Description: Real-time Open Vocabulary Object Detection models from Tencent AI Lab.