TASK |
DATASET |
MODEL |
METRIC NAME |
METRIC VALUE |
GLOBAL RANK |
REMOVE |
Semantic Segmentation
|
ADE20K
|
tiny-MOAT-2 (IN-1K pretraining, single scale)
|
Validation mIoU
|
44.9
|
# 190
|
|
Semantic Segmentation
|
ADE20K
|
tiny-MOAT-2 (IN-1K pretraining, single scale)
|
Params (M)
|
13
|
# 59
|
|
Semantic Segmentation
|
ADE20K
|
tiny-MOAT-3 (IN-1K pretraining, single scale)
|
Validation mIoU
|
47.5
|
# 155
|
|
Semantic Segmentation
|
ADE20K
|
tiny-MOAT-3 (IN-1K pretraining, single scale)
|
Params (M)
|
24
|
# 55
|
|
Semantic Segmentation
|
ADE20K
|
MOAT-2 (IN-22K pretraining, single-scale)
|
Validation mIoU
|
54.7
|
# 49
|
|
Semantic Segmentation
|
ADE20K
|
MOAT-2 (IN-22K pretraining, single-scale)
|
Params (M)
|
81
|
# 35
|
|
Semantic Segmentation
|
ADE20K
|
MOAT-3 (IN-22K pretraining, single-scale)
|
Validation mIoU
|
56.5
|
# 33
|
|
Semantic Segmentation
|
ADE20K
|
MOAT-3 (IN-22K pretraining, single-scale)
|
Params (M)
|
198
|
# 21
|
|
Semantic Segmentation
|
ADE20K
|
MOAT-4 (IN-22K pretraining, single-scale)
|
Validation mIoU
|
57.6
|
# 24
|
|
Semantic Segmentation
|
ADE20K
|
MOAT-4 (IN-22K pretraining, single-scale)
|
Params (M)
|
496
|
# 10
|
|
Semantic Segmentation
|
ADE20K
|
tiny-MOAT-0 (IN-1K pretraining, single scale)
|
Validation mIoU
|
41.2
|
# 208
|
|
Semantic Segmentation
|
ADE20K
|
tiny-MOAT-0 (IN-1K pretraining, single scale)
|
Params (M)
|
6
|
# 63
|
|
Semantic Segmentation
|
ADE20K
|
tiny-MOAT-1 (IN-1K pretraining, single scale)
|
Validation mIoU
|
43.1
|
# 204
|
|
Semantic Segmentation
|
ADE20K
|
tiny-MOAT-1 (IN-1K pretraining, single scale)
|
Params (M)
|
8
|
# 61
|
|
Instance Segmentation
|
COCO minival
|
tiny-MOAT-0 (IN-1K pretraining, single-scale)
|
mask AP
|
43.3
|
# 58
|
|
Instance Segmentation
|
COCO minival
|
tiny-MOAT-1 (IN-1K pretraining, single-scale)
|
mask AP
|
44.6
|
# 49
|
|
Instance Segmentation
|
COCO minival
|
tiny-MOAT-2 (IN-1K pretraining, single-scale)
|
mask AP
|
45.0
|
# 47
|
|
Instance Segmentation
|
COCO minival
|
tiny-MOAT-3 (IN-1K pretraining, single-scale)
|
mask AP
|
47.0
|
# 38
|
|
Instance Segmentation
|
COCO minival
|
MOAT-0 (IN-1K pretraining, single-scale)
|
mask AP
|
47.4
|
# 36
|
|
Instance Segmentation
|
COCO minival
|
MOAT-1 (IN-1K pretraining, single-scale)
|
mask AP
|
49.0
|
# 27
|
|
Instance Segmentation
|
COCO minival
|
MOAT-2 (IN-22K pretraining, single-scale)
|
mask AP
|
49.3
|
# 26
|
|
Instance Segmentation
|
COCO minival
|
MOAT-3 (IN-22K pretraining, single-scale)
|
mask AP
|
50.3
|
# 23
|
|
Object Detection
|
COCO minival
|
tiny-MOAT-1 (IN-1K pretraining, single-scale)
|
box AP
|
51.9
|
# 67
|
|
Object Detection
|
COCO minival
|
tiny-MOAT-0 (IN-1K pretraining, single-scale)
|
box AP
|
50.5
|
# 74
|
|
Object Detection
|
COCO minival
|
tiny-MOAT-2 (IN-1K pretraining, single-scale)
|
box AP
|
53.0
|
# 61
|
|
Object Detection
|
COCO minival
|
MOAT-2 (IN-22K pretraining, single-scale)
|
box AP
|
58.5
|
# 33
|
|
Object Detection
|
COCO minival
|
MOAT-1 (IN-1K pretraining, single-scale)
|
box AP
|
57.7
|
# 36
|
|
Object Detection
|
COCO minival
|
MOAT-0 (IN-1K pretraining, single-scale)
|
box AP
|
55.9
|
# 45
|
|
Object Detection
|
COCO minival
|
tiny-MOAT-3 (IN-1K pretraining, single-scale)
|
box AP
|
55.2
|
# 48
|
|
Object Detection
|
COCO minival
|
MOAT-3 (IN-22K pretraining, single-scale)
|
box AP
|
59.2
|
# 28
|
|
Image Classification
|
ImageNet
|
MOAT-3 1K only
|
Top 1 Accuracy
|
86.7%
|
# 126
|
|
Image Classification
|
ImageNet
|
MOAT-3 1K only
|
Number of params
|
190M
|
# 890
|
|
Image Classification
|
ImageNet
|
MOAT-3 1K only
|
GFLOPs
|
271
|
# 473
|
|
Image Classification
|
ImageNet
|
MOAT-0 1K only
|
Top 1 Accuracy
|
83.3%
|
# 403
|
|
Image Classification
|
ImageNet
|
MOAT-0 1K only
|
Number of params
|
27.8M
|
# 627
|
|
Image Classification
|
ImageNet
|
MOAT-0 1K only
|
GFLOPs
|
5.7
|
# 237
|
|
Image Classification
|
ImageNet
|
MOAT-4 22K+1K
|
Top 1 Accuracy
|
89.1%
|
# 33
|
|
Image Classification
|
ImageNet
|
MOAT-4 22K+1K
|
Number of params
|
483.2M
|
# 940
|
|
Image Classification
|
ImageNet
|
MOAT-4 22K+1K
|
GFLOPs
|
648.5
|
# 485
|
|
Image Classification
|
ImageNet V2
|
MOAT-2 (IN-22K pretraining)
|
Top 1 Accuracy
|
79.3
|
# 11
|
|
Image Classification
|
ImageNet V2
|
MOAT-1 (IN-22K pretraining)
|
Top 1 Accuracy
|
78.4
|
# 12
|
|
Image Classification
|
ImageNet V2
|
MOAT-4 (IN-22K pretraining)
|
Top 1 Accuracy
|
81.5
|
# 8
|
|
Image Classification
|
ImageNet V2
|
MOAT-3 (IN-22K pretraining)
|
Top 1 Accuracy
|
80.6
|
# 10
|
|
Object Detection
|
MS COCO
|
MOAT-3 22K+1K
|
box AP
|
59.2
|
# 1
|
|
Object Detection
|
MS COCO
|
MOAT-2
|
box AP
|
58.5
|
# 2
|
|