Atten4Vis/GroupDETR
[ICCV 2023] Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment
This project helps machine learning engineers and researchers accelerate the training of DETR-based object detection models. It takes existing DETR model architectures and training data, and outputs a more quickly converged and higher-performing trained model. This is for professionals working on computer vision tasks like image recognition and object localization.
No commits in the last 6 months.
Use this if you are a machine learning practitioner looking to significantly reduce the training time and improve the accuracy of your DETR-based object detection models.
Not ideal if you are not working with DETR models or are looking for a pre-trained model rather than a training acceleration method.
Stars
43
Forks
3
Language
—
License
—
Category
Last pushed
Jul 20, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Atten4Vis/GroupDETR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lucasjinreal/yolov7_d2
🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with...
fredzzhang/upt
[CVPR'22] Official PyTorch implementation for paper "Efficient Two-Stage Detection of...
coderonion/awesome-yolo-object-detection
🚀🚀🚀 A collection of some awesome public YOLO object detection series projects and the related...
qubvel/rt-pose
Real-time pose estimation pipeline with 🤗 Transformers
MasterSkepticista/detr
JAX implementation of DETR