yandex/alchemist
Viewer
ā¢
Updated
ā¢
3.35k
ā¢
1.52k
ā¢
39
Jiannan Huang
Rbrq
Ā·
AI & ML interests
None yet
Recent Activity
liked
a dataset
about 1 month ago
yandex/alchemist
updated
a dataset
about 2 months ago
Rbrq/odd
published
a dataset
2 months ago
Rbrq/odd
Organizations
None yet
liked
a
dataset
about 1 month ago
updated
a
dataset
about 2 months ago
published
a
dataset
2 months ago
liked
a
dataset
3 months ago
upvoted
a
paper
3 months ago
liked
2
datasets
3 months ago
liked
a
model
4 months ago
liked
a
model
6 months ago
liked
a
Space
8 months ago
liked
a
model
9 months ago
liked
a
Space
9 months ago
liked
a
model
9 months ago
liked
a
dataset
10 months ago
upvoted
a
paper
10 months ago
upvoted
an
article
10 months ago
Article
MobileNet Baselines
By
ā¢
ā¢
24
liked
a
model
11 months ago
updated
a
model
12 months ago
reacted to
merve's
post with š„
12 months ago
Post
5169
Real-time DEtection Transformer (RT-DETR) landed in transformers š¤© with Apache 2.0 license š
š models:
PekingU
š demo: merve/RT-DETR-tracking-coco
š paper: DETRs Beat YOLOs on Real-time Object Detection (2304.08069)
š notebook: https://github.com/merveenoyan/example_notebooks/blob/main/RT_DETR_Notebook.ipynb
YOLO models are known to be super fast for real-time computer vision, but they have a downside with being volatile to NMS š„²
Transformer-based models on the other hand are computationally not as efficient š„²
Isn't there something in between? Enter RT-DETR!
The authors combined CNN backbone, multi-stage hybrid decoder (combining convs and attn) with a transformer decoder. In the paper, authors also claim one can adjust speed by changing decoder layers without retraining altogether.
The authors find out that the model performs better in terms of speed and accuracy compared to the previous state-of-the-art. š¤©
š models:
PekingU
š demo: merve/RT-DETR-tracking-coco
š paper: DETRs Beat YOLOs on Real-time Object Detection (2304.08069)
š notebook: https://github.com/merveenoyan/example_notebooks/blob/main/RT_DETR_Notebook.ipynb
YOLO models are known to be super fast for real-time computer vision, but they have a downside with being volatile to NMS š„²
Transformer-based models on the other hand are computationally not as efficient š„²
Isn't there something in between? Enter RT-DETR!
The authors combined CNN backbone, multi-stage hybrid decoder (combining convs and attn) with a transformer decoder. In the paper, authors also claim one can adjust speed by changing decoder layers without retraining altogether.
The authors find out that the model performs better in terms of speed and accuracy compared to the previous state-of-the-art. š¤©
updated
a
model
12 months ago