Image Classification on ImageNet-1K (With LV-ViT-S)

Metric: GFLOPs (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	GFLOPs▼	Extra Data	Paper	Date↕	Code
1	Base (LV-ViT-S)	6.6	No	All Tokens Matter: Token Labeling for Training B...	2021-04-22	Code
2	DynamicViT (90%)	5.8	No	DynamicViT: Efficient Vision Transformers with D...	2021-06-03	Code
3	DynamicViT (80%)	5.1	No	DynamicViT: Efficient Vision Transformers with D...	2021-06-03	Code
4	MCTF ($r=8$)	4.9	No	Multi-criteria Token Fusion with One-step-ahead ...	2024-03-15	Code
5	BAT	4.7	No	Beyond Attentive Tokens: Incorporating Token Imp...	2022-11-21	Code
6	EViT (70%)	4.7	No	Not All Patches are What You Need: Expediting Vi...	2022-02-16	Code
7	PS-LV-ViT-S	4.7	No	Patch Slimming for Efficient Vision Transformers	2021-06-05	-
8	AS-LV-S (70%)	4.6	No	Adaptive Sparse ViT: Towards Learnable Adaptive ...	2022-09-28	Code
9	PPT	4.6	No	PPT: Token Pruning and Pooling for Efficient Vis...	2023-10-03	Code
10	DynamicViT (70%)	4.6	No	DynamicViT: Efficient Vision Transformers with D...	2021-06-03	Code
11	DPS-LV-ViT-S	4.5	No	Patch Slimming for Efficient Vision Transformers	2021-06-05	-
12	SPViT	4.3	No	SPViT: Enabling Faster Vision Transformers via S...	2021-12-27	Code
13	MCTF ($r=12$)	4.2	No	Multi-criteria Token Fusion with One-step-ahead ...	2024-03-15	Code
14	DiffRate	3.9	No	DiffRate : Differentiable Compression Rate for E...	2023-05-29	Code
15	AS-LV-S (60%)	3.9	No	Adaptive Sparse ViT: Towards Learnable Adaptive ...	2022-09-28	Code
16	EViT (50%)	3.9	No	Not All Patches are What You Need: Expediting Vi...	2022-02-16	Code
17	dTPS	3.8	No	Joint Token Pruning and Squeezing Towards More A...	2023-04-21	Code
18	eTPS	3.8	No	Joint Token Pruning and Squeezing Towards More A...	2023-04-21	Code
19	MCTF ($r=16$)	3.6	No	Multi-criteria Token Fusion with One-step-ahead ...	2024-03-15	Code

#1Base (LV-ViT-S)SOTA
6.6
GFLOPs· 2021-04-22
All Tokens Matter: Token Labeling for Training Better Vision Transformers Code
#2DynamicViT (90%)
5.8
GFLOPs· 2021-06-03
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification Code
#3DynamicViT (80%)
5.1
GFLOPs· 2021-06-03
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification Code
#4MCTF ($r=8$)
4.9
GFLOPs· 2024-03-15
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers Code
#5BAT
4.7
GFLOPs· 2022-11-21
Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers Code
#6EViT (70%)
4.7
GFLOPs· 2022-02-16
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations Code
#7PS-LV-ViT-S
4.7
GFLOPs· 2021-06-05
Patch Slimming for Efficient Vision Transformers
#8AS-LV-S (70%)
4.6
GFLOPs· 2022-09-28
Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention Code
#9PPT
4.6
GFLOPs· 2023-10-03
PPT: Token Pruning and Pooling for Efficient Vision Transformers Code
#10DynamicViT (70%)
4.6
GFLOPs· 2021-06-03
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification Code
#11DPS-LV-ViT-S
4.5
GFLOPs· 2021-06-05
Patch Slimming for Efficient Vision Transformers
#12SPViT
4.3
GFLOPs· 2021-12-27
SPViT: Enabling Faster Vision Transformers via Soft Token Pruning Code
#13MCTF ($r=12$)
4.2
GFLOPs· 2024-03-15
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers Code
#14DiffRate
3.9
GFLOPs· 2023-05-29
DiffRate : Differentiable Compression Rate for Efficient Vision Transformers Code
#15AS-LV-S (60%)
3.9
GFLOPs· 2022-09-28
Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention Code
#16EViT (50%)
3.9
GFLOPs· 2022-02-16
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations Code
#17dTPS
3.8
GFLOPs· 2023-04-21
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers Code
#18eTPS
3.8
GFLOPs· 2023-04-21
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers Code
#19MCTF ($r=16$)
3.6
GFLOPs· 2024-03-15
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers Code