# Multi-scale Feature Fusion

SAM2 model based on HieraDet image encoder, focusing on image feature extraction tasks.

A PyTorch-implemented FPN image segmentation model that supports various encoder architectures, suitable for semantic segmentation tasks.

A semantic segmentation model based on PyTorch, utilizing an improved UNet++ architecture, suitable for image segmentation tasks.

Unet image segmentation model implemented in PyTorch, supporting multiple encoder architectures

LeYOLO is an object detection model based on the YOLO architecture, offering multiple size versions (nano, small, medium, large) suitable for real-time object detection tasks.

RT-DETR is the first real-time end-to-end object detector, achieving a balance of speed and accuracy surpassing the YOLO series through efficient hybrid encoders and query selection mechanisms

RT-DETR is the first real-time end-to-end object detection Transformer model, achieving efficient NMS-free detection through a hybrid encoder and query selection mechanism

RT-DETR is the first real-time end-to-end object detector, achieving 53.1% AP and 108 FPS on the COCO dataset through an efficient hybrid encoder and uncertainty-minimized query selection mechanism.