Papers › GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation

GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation

6 Nov 2023arXiv:2311.03035archive 2025-07-28

Xuwei Xu, Sen Wang, Yudong Chen, Yanping Zheng, Zhewei Wei, Jiajun Liu

Vision Transformers (ViTs) have revolutionized the field of computer vision, yet their deployments on resource-constrained devices remain challenging due to high computational demands. To expedite pre-trained ViTs, token pruning and token merging approaches have been developed, which aim at reducing the number of tokens involved in the computation. However, these methods still have some limitations, such as image information loss from pruned tokens and inefficiency in the token-matching process. In this paper, we introduce a novel Graph-based Token Propagation (GTP) method to resolve the challenge of balancing model efficiency and information preservation for efficient ViTs. Inspired by graph summarization algorithms, GTP meticulously propagates less significant tokens' information to spatially and semantically connected tokens that are of greater importance. Consequently, the remaining few tokens serve as a summarization of the entire token graph, allowing the method to reduce computational complexity while preserving essential information of eliminated tokens. Combined with an innovative token selection strategy, GTP can efficiently identify image tokens to be propagated. Extensive experiments have validated GTP's effectiveness, demonstrating both efficiency and performance improvements. Specifically, GTP decreases the computational complexity of both DeiT-S and DeiT-B by up to 26% with only a minimal 0.3% accuracy drop on ImageNet-1K without finetuning, and remarkably surpasses the state-of-the-art token merging method on various backbones at an even faster inference speed. The source code is available at https://github.com/Ackesnal/GTP-ViT.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2311.03035")

Code

Syntology Ran 1 of 2 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · fixture could not drive it.

By repository: official repository: 2 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ackesnal/gtp-vit officialmentioned in papermentioned on GitHubpytorch 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

2 samples harvested; 1 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · fixture could not drive it
1unverified

Licence: 0 of the 2 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ackesnal/gtp-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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

select ackesnal/gtp-vit/models_v3.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · fc2f6c8685c520eb · report
propagate ackesnal/gtp-vit/models_v3.py official repository unverified Apache-2.0 (permissive) · 0e95f70efaf7910b · report

Tasks

Efficient ViTsImage Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet GTP-ViT-B-Patch8/P20 Top 1 Accuracy 85.8% #191 of 1060 Archive leaderboard report
Image Classification ImageNet GTP-EVA-L/P8 Top 1 Accuracy 85.4% #229 of 1060 Archive leaderboard report
Image Classification ImageNet GTP-ViT-L/P8 Top 1 Accuracy 83.7% #393 of 1060 Archive leaderboard report
Image Classification ImageNet GTP-LV-ViT-M/P8 GFLOPs 8 #492 of 1060 Archive leaderboard report
Image Classification ImageNet GTP-LV-ViT-M/P8 Top 1 Accuracy 82.8% #492 of 1060 Archive leaderboard report
Image Classification ImageNet GTP-LV-ViT-S/P8 GFLOPs 4.8 #592 of 1060 Archive leaderboard report
Image Classification ImageNet GTP-LV-ViT-S/P8 Top 1 Accuracy 81.9% #592 of 1060 Archive leaderboard report
Image Classification ImageNet GTP-DeiT-B/P8 GFLOPs 13.1 #630 of 1060 Archive leaderboard report
Image Classification ImageNet GTP-DeiT-B/P8 Top 1 Accuracy 81.5% #630 of 1060 Archive leaderboard report
Image Classification ImageNet GTP-DeiT-S/P8 GFLOPs 3.4 #750 of 1060 Archive leaderboard report
Image Classification ImageNet GTP-DeiT-S/P8 Top 1 Accuracy 79.5% #750 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

Pruning

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