Methods › Computer Vision › Vision Transformers › T2T-ViT
Tokens-To-Token Vision Transformer
T2T-ViT
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
T2T-ViT (Tokens-To-Token Vision Transformer) is a type of Vision Transformer which incorporates 1) a layerwise Tokens-to-Token (T2T) transformation to progressively structurize the image to tokens by recursively aggregating neighboring Tokens into one Token (Tokens-to-Token), such that local structure represented by surrounding tokens can be modeled and tokens length can be reduced; 2) an efficient backbone with a deep-narrow structure for vision transformer motivated by CNN architecture design after empirical study.
Papers archive 2025-07-28
11 shown of 11, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Changing Base Without Losing Pace: A GPU-Efficient Alternative to MatMul in DNNs 15 Mar 2025 · 0 repositories · arXiv:2503.12211
-
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers 15 Mar 2024 · 1 repository · arXiv:2403.10030Syntology ran 3 of 5 samples · 2 unverified
-
USDC: Unified Static and Dynamic Compression for Visual Transformer 17 Oct 2023 · 0 repositories · arXiv:2310.11117
-
KDEformer: Accelerating Transformers via Kernel Density Estimation 5 Feb 2023 · 1 repository · arXiv:2302.02451Syntology ran 7 of 12 samples · 5 unverified
-
Unified Visual Transformer Compression 15 Mar 2022 · 1 repository · arXiv:2203.08243Syntology ran 9 of 16 samples · 7 unverified · 3 pointer-only (licence)
-
BViT: Broad Attention based Vision Transformer 13 Feb 2022 · 1 repository · arXiv:2202.06268
-
Multi-Dimensional Model Compression of Vision Transformer 31 Dec 2021 · 1 repository · arXiv:2201.00043
-
Dynamic Token Normalization Improves Vision Transformers 5 Dec 2021 · 1 repository · arXiv:2112.02624Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
-
Scatterbrain: Unifying Sparse and Low-rank Attention Approximation 28 Oct 2021 · 1 repository · arXiv:2110.15343Syntology ran 1 of 1 samples · 0 unverified
-
Scatterbrain: Unifying Sparse and Low-rank Attention 21 May 2021 · 1 repository
-
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet 28 Jan 2021 · 13 repositories · arXiv:2101.11986Syntology ran 21 of 26 samples · 5 unverified · 8 pointer-only (licence)
Tasks archive 2025-07-28
17 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections