Heedless Backbones
Backbones
Heads
Datasets
|
About
ImageNet-ReaL Dataset
Website
2
4
6
8
10
12
79
80
81
82
83
84
85
86
Top-1 on ImageNet-ReaL
GFLOPs
Top-1
plotly-logomark
Plot Options
axis
Results
Results
Parameters (M)
Images / Second
Publication Date
task
Classification
---------
Classification
metric
Top-1
----------
Top-1
Top-5
GFLOPs
resolution
Select an option
----------
224x224
384x384
512x512
axis
GFLOPs
Results
Parameters (M)
Images / Second
GFLOPs
Publication Date
Filters
pretrain dataset
Select an option
---------
JFT-3B
ImageNet-1k
ImageNet-22k
JFT-300M
pretrain method
Select an option
----------
Supervised
FCMAE
MAE
CL
Legend
Legend attribute
Family
Family
Pretrain Dataset
Pretrain Method
Classification Resolution
Legend attribute (second)
Select an option
----------
Pretrain Dataset
Pretrain Method
Classification Resolution
Filter:
family
model
params (m)
pretrain
finetune
GFLOPs
Top-1
ResNet (RSB)
ResNet-152 (RSB)
60.2
IN-1k : Sup. : 600
— : — : —
11.6
86.4
ResNet (RSB)
ResNet-101 (RSB)
44.5
IN-1k : Sup. : 600
— : — : —
7.9
86.3
ResNet (RSB)
ResNet-50 (RSB)
25.6
IN-1k : Sup. : 600
— : — : —
4.1
85.7
ResNet (RSB)
ResNet-34 (RSB)
21.8
IN-1k : Sup. : 600
— : — : —
3.7
83.4
ResNet (RSB)
ResNet-18 (RSB)
11.7
IN-1k : Sup. : 600
— : — : —
1.8
79.4
Classification Results
family
model
params (m)
pretrain
finetune
gflops
top-1
top-5
ResNet (RSB)
ResNet-152 (RSB)
60.2
IN-1k : Sup. : 600
— : — : —
11.6
86.4
—
ResNet (RSB)
ResNet-101 (RSB)
44.5
IN-1k : Sup. : 600
— : — : —
7.9
86.3
—
ResNet (RSB)
ResNet-50 (RSB)
25.6
IN-1k : Sup. : 600
— : — : —
4.1
85.7
—
ResNet (RSB)
ResNet-34 (RSB)
21.8
IN-1k : Sup. : 600
— : — : —
3.7
83.4
—
ResNet (RSB)
ResNet-18 (RSB)
11.7
IN-1k : Sup. : 600
— : — : —
1.8
79.4
—