Papers › Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer

Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer

3 Aug 2021arXiv:2108.01390archive 2025-07-28

Yifan Xu, Zhijie Zhang, Mengdan Zhang, Kekai Sheng, Ke Li, WeiMing Dong, Liqing Zhang, Changsheng Xu, Xing Sun

Vision transformers (ViTs) have recently received explosive popularity, but the huge computational cost is still a severe issue. Since the computation complexity of ViT is quadratic with respect to the input sequence length, a mainstream paradigm for computation reduction is to reduce the number of tokens. Existing designs include structured spatial compression that uses a progressive shrinking pyramid to reduce the computations of large feature maps, and unstructured token pruning that dynamically drops redundant tokens. However, the limitation of existing token pruning lies in two folds: 1) the incomplete spatial structure caused by pruning is not compatible with structured spatial compression that is commonly used in modern deep-narrow transformers; 2) it usually requires a time-consuming pre-training procedure. To tackle the limitations and expand the applicable scenario of token pruning, we present Evo-ViT, a self-motivated slow-fast token evolution approach for vision transformers. Specifically, we conduct unstructured instance-wise token selection by taking advantage of the simple and effective global class attention that is native to vision transformers. Then, we propose to update the selected informative tokens and uninformative tokens with different computation paths, namely, slow-fast updating. Since slow-fast updating mechanism maintains the spatial structure and information flow, Evo-ViT can accelerate vanilla transformers of both flat and deep-narrow structures from the very beginning of the training process. Experimental results demonstrate that our method significantly reduces the computational cost of vision transformers while maintaining comparable performance on image classification.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 9 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 7 ran (4 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 7 samples that ran have no recorded date.

YifanXu74/Evo-ViT officialmentioned in papermentioned on GitHubpytorchMITSyntology: 9 samples, 7 ran (3 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
3ran · our draft was wrong
1ran
2unverified

Licence: 1 of the 9 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from YifanXu74/Evo-ViT. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

YifanXu74/Evo-ViT official repository 9 samples, 7 ran (3 instrument-failed) · 2 unverified
count_params in 80 papers benchmark.py ran · honoured contract MIT (permissive) · 410bffb8a07b52e3 · report fixture: signature model:callable/0/? · returned int · level recorded, date not recorded
build_transform in 170 papers datasets.py ran · our draft was wrong MIT (permissive) · 3bc74137ab36aa79 · report fixture: signature is_train:bool/0/bool, args:ArgsConfig/0/? · returned Compose · level recorded 2026-09-26
checkpoint_filter_fn in 80 papers deit/evo_deit.py ran · our draft was wrong MIT (permissive) · 0b3795f9775ce118 · report fixture: signature state_dict:dict/0/?, model:callable/0/? · returned dict · level recorded 2026-09-24
cuda_timestamp in 11 papers benchmark.py ran · honoured contract fingerprinted MIT (permissive) · 50d653ee6a59955c · report fixture: signature sync:bool/0/bool, device:NoneType/0/? · returned float · level recorded, date not recorded
easy_gather deit/evo_deit.py ran MIT (permissive) · a402be7c553f216c · report fixture: signature x:Tensor/3/float, indices:Tensor/2/int · returned Tensor · level recorded 2026-09-25
resize_pos_embed in 102 papers deit/evo_deit.py ran · our draft was wrong MIT (permissive) · 109c74bc1997c975 · report fixture: signature posemb:Tensor/3/float, posemb_new:Tensor/3/float · returned Tensor · level recorded 2026-09-24
timestamp in 15 papers benchmark.py ran · honoured contract MIT (permissive) · 475160c5a1a1225a · report fixture: signature sync:bool/0/bool · returned float · level recorded, date not recorded
build_dataset in 151 papers datasets.py unverified MIT (permissive) · 9153241c4331eb1a · report
build_dataset2 datasets.py unverified MIT (permissive) here; the stored copy is pointer only · b6679d5755485cf9 · report

Tasks

Efficient ViTsImage Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Efficient ViTs ImageNet-1K (with DeiT-S) EvoViT GFLOPs 3.0 #24 of 41 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-S) EvoViT Top 1 Accuracy 79.4 #24 of 41 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-T) EvoViT GFLOPs 0.8 #12 of 22 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-T) EvoViT Top 1 Accuracy 72.0 #12 of 22 Archive leaderboard report
Image Classification ImageNet Evo-LeViT-384* Number of params 39.6M #563 of 1060 Archive leaderboard report
Image Classification ImageNet Evo-LeViT-384* Top 1 Accuracy 82.2% #563 of 1060 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Class AttentionPruning

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