Image Classification on ImageNet-1K (with DeiT-T)

Metric: Top 1 Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Top 1 Accuracy▼	Extra Data	Paper	Date↕	Code
1	dTPS	72.9	No	Joint Token Pruning and Squeezing Towards More A...	2023-04-21	Code
2	MCTF ($r=8$)	72.9	No	Multi-criteria Token Fusion with One-step-ahead ...	2024-03-15	Code
3	MCTF ($r=16$)	72.7	No	Multi-criteria Token Fusion with One-step-ahead ...	2024-03-15	Code
4	BAT	72.3	No	Beyond Attentive Tokens: Incorporating Token Imp...	2022-11-21	Code
5	eTPS	72.3	No	Joint Token Pruning and Squeezing Towards More A...	2023-04-21	Code
6	SPViT (1.0G)	72.2	No	SPViT: Enabling Faster Vision Transformers via S...	2021-12-27	Code
7	Base (DeiT-T)	72.2	No	Training data-efficient image transformers & dis...	2020-12-23	Code
8	DPS-ViT	72.1	No	Patch Slimming for Efficient Vision Transformers	2021-06-05	-
9	PPT	72.1	No	PPT: Token Pruning and Pooling for Efficient Vis...	2023-10-03	Code
10	SPViT (0.9G)	72.1	No	SPViT: Enabling Faster Vision Transformers via S...	2021-12-27	Code
11	PS-ViT	72	No	Patch Slimming for Efficient Vision Transformers	2021-06-05	-
12	EvoViT	72	No	Evo-ViT: Slow-Fast Token Evolution for Dynamic V...	2021-08-03	Code
13	LTMP (80%)	72	No	Learned Thresholds Token Merging and Pruning for...	2023-07-20	Code
14	ToMe ($r=8$)	71.7	No	Token Merging: Your ViT But Faster	2022-10-17	Code
15	LTMP (60%)	71.5	No	Learned Thresholds Token Merging and Pruning for...	2023-07-20	Code
16	MCTF ($r=20$)	71.4	No	Multi-criteria Token Fusion with One-step-ahead ...	2024-03-15	Code
17	ToMe ($r=12$)	71.4	No	Token Merging: Your ViT But Faster	2022-10-17	Code
18	ToMe ($r=16$)	70.7	No	Token Merging: Your ViT But Faster	2022-10-17	Code
19	SPViT	70.7	No	Pruning Self-attentions into Convolutional Layer...	2021-11-23	Code
20	S$^2$ViTE	70.1	No	Chasing Sparsity in Vision Transformers: An End-...	2021-06-08	Code
21	LTMP (45%)	69.8	No	Learned Thresholds Token Merging and Pruning for...	2023-07-20	Code
22	HVT-Ti-1	69.6	No	Scalable Vision Transformers with Hierarchical P...	2021-03-19	Code

#1dTPSSOTA
72.9
Top 1 Accuracy· 2023-04-21
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers Code
#2MCTF ($r=8$)
72.9
Top 1 Accuracy· 2024-03-15
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers Code
#3MCTF ($r=16$)
72.7
Top 1 Accuracy· 2024-03-15
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers Code
#4BATSOTA
72.3
Top 1 Accuracy· 2022-11-21
Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers Code
#5eTPS
72.3
Top 1 Accuracy· 2023-04-21
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers Code
#6SPViT (1.0G)
72.2
Top 1 Accuracy· 2021-12-27
SPViT: Enabling Faster Vision Transformers via Soft Token Pruning Code
#7Base (DeiT-T)SOTA
72.2
Top 1 Accuracy· 2020-12-23
Training data-efficient image transformers & distillation through attention Code
#8DPS-ViT
72.1
Top 1 Accuracy· 2021-06-05
Patch Slimming for Efficient Vision Transformers
#9PPT
72.1
Top 1 Accuracy· 2023-10-03
PPT: Token Pruning and Pooling for Efficient Vision Transformers Code
#10SPViT (0.9G)
72.1
Top 1 Accuracy· 2021-12-27
SPViT: Enabling Faster Vision Transformers via Soft Token Pruning Code
#11PS-ViT
72
Top 1 Accuracy· 2021-06-05
Patch Slimming for Efficient Vision Transformers
#12EvoViT
72
Top 1 Accuracy· 2021-08-03
Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer Code
#13LTMP (80%)
72
Top 1 Accuracy· 2023-07-20
Learned Thresholds Token Merging and Pruning for Vision Transformers Code
#14ToMe ($r=8$)
71.7
Top 1 Accuracy· 2022-10-17
Token Merging: Your ViT But Faster Code
#15LTMP (60%)
71.5
Top 1 Accuracy· 2023-07-20
Learned Thresholds Token Merging and Pruning for Vision Transformers Code
#16MCTF ($r=20$)
71.4
Top 1 Accuracy· 2024-03-15
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers Code
#17ToMe ($r=12$)
71.4
Top 1 Accuracy· 2022-10-17
Token Merging: Your ViT But Faster Code
#18ToMe ($r=16$)
70.7
Top 1 Accuracy· 2022-10-17
Token Merging: Your ViT But Faster Code
#19SPViT
70.7
Top 1 Accuracy· 2021-11-23
Pruning Self-attentions into Convolutional Layers in Single Path Code
#20S$^2$ViTE
70.1
Top 1 Accuracy· 2021-06-08
Chasing Sparsity in Vision Transformers: An End-to-End Exploration Code
#21LTMP (45%)
69.8
Top 1 Accuracy· 2023-07-20
Learned Thresholds Token Merging and Pruning for Vision Transformers Code
#22HVT-Ti-1
69.6
Top 1 Accuracy· 2021-03-19
Scalable Vision Transformers with Hierarchical Pooling Code