81
RF-DETR
🔥
SOTA real-time object detection model
Subhansh Malviya
Subh775
AI & ML interests
Applied Computer Vision Researcher | Vision + Perception + Interpretation
Recent Activity
liked
a Space
3 days ago
Roboflow/RF-DETR
updated
a model
3 days ago
Subh775/Seg-Basil-rfdetr
upvoted
a
paper
5 days ago
Simple Open-Vocabulary Object Detection with Vision Transformers
Organizations
liked
a
Space
3 days ago
updated
a
model
3 days ago
upvoted
a
paper
5 days ago
Runtime Error
#9 opened 5 days ago
by
Subh775
updated
a
model
5 days ago
reacted to
SkalskiP's
post with 🔥
5 days ago
Post
YOLO-World: Real-Time, Zero-Shot Object Detection 🔥 🔥 🔥
YOLO-World was designed to solve a limitation of existing zero-shot object detection models: speed. Whereas other state-of-the-art models use Transformers, a powerful but typically slower architecture, YOLO-World uses the faster CNN-based YOLO architecture.
YOLO-World provides three models: small with 13M (re-parametrized 77M), medium with 29M (re-parametrized 92M), and large with 48M (re-parametrized 110M) parameters.
The YOLO-World team benchmarked the model on the LVIS dataset and measured their performance on the V100 without any performance acceleration mechanisms like quantization or TensorRT.
According to the paper, YOLO-World reached 35.4 AP with 52.0 FPS for the L version and 26.2 AP with 74.1 FPS for the S version. While the V100 is a powerful GPU, achieving such high FPS on any device is impressive.
- 🔗 YOLO-World arXiv paper: https://lnkd.in/ddRBKCCX
- 🔗 my YOLO-World technical report: https://blog.roboflow.com/what-is-yolo-world
- 🤗 YOLO-World space: SkalskiP/YOLO-World
YOLO-World was designed to solve a limitation of existing zero-shot object detection models: speed. Whereas other state-of-the-art models use Transformers, a powerful but typically slower architecture, YOLO-World uses the faster CNN-based YOLO architecture.
YOLO-World provides three models: small with 13M (re-parametrized 77M), medium with 29M (re-parametrized 92M), and large with 48M (re-parametrized 110M) parameters.
The YOLO-World team benchmarked the model on the LVIS dataset and measured their performance on the V100 without any performance acceleration mechanisms like quantization or TensorRT.
According to the paper, YOLO-World reached 35.4 AP with 52.0 FPS for the L version and 26.2 AP with 74.1 FPS for the S version. While the V100 is a powerful GPU, achieving such high FPS on any device is impressive.
- 🔗 YOLO-World arXiv paper: https://lnkd.in/ddRBKCCX
- 🔗 my YOLO-World technical report: https://blog.roboflow.com/what-is-yolo-world
- 🤗 YOLO-World space: SkalskiP/YOLO-World
liked
a
model
5 days ago
Space coorection
#15 opened 5 days ago
by
Subh775
REPORT: Space is not working
#2 opened 5 days ago
by
Subh775
liked
a
Space
6 days ago
liked
a
model
6 days ago
upvoted
a
collection
6 days ago
updated
a
dataset
6 days ago
published
a
dataset
6 days ago
liked
a
model
7 days ago
liked
a
Space
7 days ago
upvoted
a
collection
7 days ago
updated
2
models
8 days ago
updated
a
Space
8 days ago