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

Metric: GFLOPs (higher is better)

LeaderboardDataset

Loading chart...

Results

#	Model↕	GFLOPs▼	Extra Data	Paper	Date↕	Code
1	Base (DeiT-S)	4.6	No	Training data-efficient image transformers & dis...	2020-12-23	Code
2	EViT (90%)	4	No	Not All Patches are What You Need: Expediting Vi...	2022-02-16	Code
3	DynamicViT (90%)	4	No	DynamicViT: Efficient Vision Transformers with D...	2021-06-03	Code
4	SPViT (3.9G)	3.9	No	SPViT: Enabling Faster Vision Transformers via S...	2021-12-27	Code
5	LTMP (80%)	3.8	No	Learned Thresholds Token Merging and Pruning for...	2023-07-20	Code
6	A-ViT	3.6	No	AdaViT: Adaptive Tokens for Efficient Vision Tra...	2021-12-14	Code
7	EViT (80%)	3.5	No	Not All Patches are What You Need: Expediting Vi...	2022-02-16	Code
8	DynamicViT (80%)	3.4	No	DynamicViT: Efficient Vision Transformers with D...	2021-06-03	Code
9	ToMe ($r=8$)	3.4	No	Token Merging: Your ViT But Faster	2022-10-17	Code
10	SPViT	3.3	No	Pruning Self-attentions into Convolutional Layer...	2021-11-23	Code
11	S$^2$ViTE	3.2	No	Chasing Sparsity in Vision Transformers: An End-...	2021-06-08	Code
12	IA-RED$^2$	3.2	No	IA-RED$^2$: Interpretability-Aware Redundancy Re...	2021-06-23	-
13	dTPS	3	No	Joint Token Pruning and Squeezing Towards More A...	2023-04-21	Code
14	eTPS	3	No	Joint Token Pruning and Squeezing Towards More A...	2023-04-21	Code
15	BAT (70%)	3	No	Beyond Attentive Tokens: Incorporating Token Imp...	2022-11-21	Code
16	AS-DeiT-S (65%)	3	No	Adaptive Sparse ViT: Towards Learnable Adaptive ...	2022-09-28	Code
17	LTMP (60%)	3	No	Learned Thresholds Token Merging and Pruning for...	2023-07-20	Code
18	EViT (70%)	3	No	Not All Patches are What You Need: Expediting Vi...	2022-02-16	Code
19	EvoViT	3	No	Evo-ViT: Slow-Fast Token Evolution for Dynamic V...	2021-08-03	Code
20	DiffRate	2.9	No	DiffRate : Differentiable Compression Rate for E...	2023-05-29	Code
21	PPT	2.9	No	PPT: Token Pruning and Pooling for Efficient Vis...	2023-10-03	Code
22	ATS	2.9	No	Adaptive Token Sampling For Efficient Vision Tra...	2021-11-30	Code
23	DynamicViT (70%)	2.9	No	DynamicViT: Efficient Vision Transformers with D...	2021-06-03	Code
24	ToMe ($r=13$)	2.7	No	Token Merging: Your ViT But Faster	2022-10-17	Code
25	HVT-S-1	2.7	No	Scalable Vision Transformers with Hierarchical P...	2021-03-19	Code
26	MCTF ($r=16$)	2.6	No	Multi-criteria Token Fusion with One-step-ahead ...	2024-03-15	Code
27	PS-ViT	2.6	No	Patch Slimming for Efficient Vision Transformers	2021-06-05	-
28	SPViT (2.6G)	2.6	No	SPViT: Enabling Faster Vision Transformers via S...	2021-12-27	Code
29	BAT (60%)	2.6	No	Beyond Attentive Tokens: Incorporating Token Imp...	2022-11-21	Code
30	EViT (60%)	2.6	No	Not All Patches are What You Need: Expediting Vi...	2022-02-16	Code
31	MCTF ($r=18$)	2.4	No	Multi-criteria Token Fusion with One-step-ahead ...	2024-03-15	Code
32	DPS-ViT	2.4	No	Patch Slimming for Efficient Vision Transformers	2021-06-05	-
33	ToMe ($r=16$)	2.3	No	Token Merging: Your ViT But Faster	2022-10-17	Code
34	BAT (50%)	2.3	No	Beyond Attentive Tokens: Incorporating Token Imp...	2022-11-21	Code
35	AS-DeiT-S (50%)	2.3	No	Adaptive Sparse ViT: Towards Learnable Adaptive ...	2022-09-28	Code
36	LTMP (45%)	2.3	No	Learned Thresholds Token Merging and Pruning for...	2023-07-20	Code
37	EViT (50%)	2.3	No	Not All Patches are What You Need: Expediting Vi...	2022-02-16	Code
38	MCTF ($r=20$)	2.2	No	Multi-criteria Token Fusion with One-step-ahead ...	2024-03-15	Code
39	BAT (40%)	2	No	Beyond Attentive Tokens: Incorporating Token Imp...	2022-11-21	Code
40	BAT (30%)	1.8	No	Beyond Attentive Tokens: Incorporating Token Imp...	2022-11-21	Code
41	BAT (20%)	1.6	No	Beyond Attentive Tokens: Incorporating Token Imp...	2022-11-21	Code