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

Metric: Top 1 Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Top 1 Accuracy▼	Extra Data	Paper	Date↕	Code
1	MCTF ($r=8$)	83.5	No	Multi-criteria Token Fusion with One-step-ahead ...	2024-03-15	Code
2	MCTF ($r=12$)	83.4	No	Multi-criteria Token Fusion with One-step-ahead ...	2024-03-15	Code
3	Base (LV-ViT-S)	83.3	No	All Tokens Matter: Token Labeling for Training B...	2021-04-22	Code
4	DynamicViT (90%)	83.3	No	DynamicViT: Efficient Vision Transformers with D...	2021-06-03	Code
5	DynamicViT (80%)	83.2	No	DynamicViT: Efficient Vision Transformers with D...	2021-06-03	Code
6	BAT	83.1	No	Beyond Attentive Tokens: Incorporating Token Imp...	2022-11-21	Code
7	AS-LV-S (70%)	83.1	No	Adaptive Sparse ViT: Towards Learnable Adaptive ...	2022-09-28	Code
8	PPT	83.1	No	PPT: Token Pruning and Pooling for Efficient Vis...	2023-10-03	Code
9	SPViT	83.1	No	SPViT: Enabling Faster Vision Transformers via S...	2021-12-27	Code
10	EViT (70%)	83	No	Not All Patches are What You Need: Expediting Vi...	2022-02-16	Code
11	DynamicViT (70%)	83	No	DynamicViT: Efficient Vision Transformers with D...	2021-06-03	Code
12	DPS-LV-ViT-S	82.9	No	Patch Slimming for Efficient Vision Transformers	2021-06-05	-
13	DiffRate	82.6	No	DiffRate : Differentiable Compression Rate for E...	2023-05-29	Code
14	AS-LV-S (60%)	82.6	No	Adaptive Sparse ViT: Towards Learnable Adaptive ...	2022-09-28	Code
15	dTPS	82.6	No	Joint Token Pruning and Squeezing Towards More A...	2023-04-21	Code
16	EViT (50%)	82.5	No	Not All Patches are What You Need: Expediting Vi...	2022-02-16	Code
17	eTPS	82.5	No	Joint Token Pruning and Squeezing Towards More A...	2023-04-21	Code
18	PS-LV-ViT-S	82.4	No	Patch Slimming for Efficient Vision Transformers	2021-06-05	-
19	MCTF ($r=16$)	82.3	No	Multi-criteria Token Fusion with One-step-ahead ...	2024-03-15	Code

#1MCTF ($r=8$)SOTA
83.5
Top 1 Accuracy· 2024-03-15
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers Code
#2MCTF ($r=12$)
83.4
Top 1 Accuracy· 2024-03-15
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers Code
#3Base (LV-ViT-S)SOTA
83.3
Top 1 Accuracy· 2021-04-22
All Tokens Matter: Token Labeling for Training Better Vision Transformers Code
#4DynamicViT (90%)
83.3
Top 1 Accuracy· 2021-06-03
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification Code
#5DynamicViT (80%)
83.2
Top 1 Accuracy· 2021-06-03
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification Code
#6BAT
83.1
Top 1 Accuracy· 2022-11-21
Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers Code
#7AS-LV-S (70%)
83.1
Top 1 Accuracy· 2022-09-28
Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention Code
#8PPT
83.1
Top 1 Accuracy· 2023-10-03
PPT: Token Pruning and Pooling for Efficient Vision Transformers Code
#9SPViT
83.1
Top 1 Accuracy· 2021-12-27
SPViT: Enabling Faster Vision Transformers via Soft Token Pruning Code
#10EViT (70%)
83
Top 1 Accuracy· 2022-02-16
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations Code
#11DynamicViT (70%)
83
Top 1 Accuracy· 2021-06-03
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification Code
#12DPS-LV-ViT-S
82.9
Top 1 Accuracy· 2021-06-05
Patch Slimming for Efficient Vision Transformers
#13DiffRate
82.6
Top 1 Accuracy· 2023-05-29
DiffRate : Differentiable Compression Rate for Efficient Vision Transformers Code
#14AS-LV-S (60%)
82.6
Top 1 Accuracy· 2022-09-28
Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention Code
#15dTPS
82.6
Top 1 Accuracy· 2023-04-21
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers Code
#16EViT (50%)
82.5
Top 1 Accuracy· 2022-02-16
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations Code
#17eTPS
82.5
Top 1 Accuracy· 2023-04-21
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers Code
#18PS-LV-ViT-S
82.4
Top 1 Accuracy· 2021-06-05
Patch Slimming for Efficient Vision Transformers
#19MCTF ($r=16$)
82.3
Top 1 Accuracy· 2024-03-15
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers Code