ZhangGongjie/SAM-DETR
[CVPR'2022] SAM-DETR & SAM-DETR++: Official PyTorch Implementation
This project helps computer vision researchers and practitioners efficiently train object detection models. It takes in annotated image datasets (like COCO) and produces a highly accurate object detection model that identifies multiple objects within an image. Anyone working on computer vision tasks requiring fast and precise object detection, such as in autonomous vehicles, surveillance, or content analysis, would find this beneficial.
302 stars. No commits in the last 6 months.
Use this if you need to train a state-of-the-art object detection model faster and more efficiently than traditional DETR-based methods, without sacrificing accuracy.
Not ideal if you are looking for a pre-trained model for immediate inference without needing to customize or train your own object detector.
Stars
302
Forks
46
Language
Python
License
MIT
Category
Last pushed
Aug 24, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ZhangGongjie/SAM-DETR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
roboflow/rf-detr
[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture...
stereolabs/zed-sdk
⚡️The spatial perception framework for rapidly building smart robots and spaces
mikel-brostrom/boxmot
BoxMOT: Pluggable SOTA multi-object tracking modules with support for axis-aligned and oriented...
RizwanMunawar/yolov7-object-tracking
YOLOv7 Object Tracking Using PyTorch, OpenCV and Sort Tracking
google-deepmind/tapnet
Tracking Any Point (TAP)