# Multi-scale feature fusion

SAM2 model based on HieraDet image encoder, focusing on efficient image feature extraction

SAM2 model based on the timm library, containing only the HieraDet image encoder part, suitable for image feature extraction tasks.

PyTorch-based semantic segmentation model supporting multiple encoder architectures

The first real-time end-to-end object detector based on Transformer architecture, eliminating the need for non-maximum suppression, surpassing YOLO series in speed and accuracy

RT-DETR is the first real-time end-to-end object detector, achieving efficient detection through hybrid encoders and query selection mechanisms without NMS post-processing.

The first real-time end-to-end object detector, achieving efficient NMS-free detection through hybrid encoder and query selection mechanism

RT-DETR is the first real-time end-to-end object detection Transformer model, achieving high-speed and high-precision detection through an efficient hybrid encoder and query selection mechanism