Papers › Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers

Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers

15 Mar 2024CVPR 2024 1arXiv:2403.10030archive 2025-07-28

Sanghyeok Lee, Joonmyung Choi, Hyunwoo J. Kim

Vision Transformer (ViT) has emerged as a prominent backbone for computer vision. For more efficient ViTs, recent works lessen the quadratic cost of the self-attention layer by pruning or fusing the redundant tokens. However, these works faced the speed-accuracy trade-off caused by the loss of information. Here, we argue that token fusion needs to consider diverse relations between tokens to minimize information loss. In this paper, we propose a Multi-criteria Token Fusion (MCTF), that gradually fuses the tokens based on multi-criteria (e.g., similarity, informativeness, and size of fused tokens). Further, we utilize the one-step-ahead attention, which is the improved approach to capture the informativeness of the tokens. By training the model equipped with MCTF using a token reduction consistency, we achieve the best speed-accuracy trade-off in the image classification (ImageNet1K). Experimental results prove that MCTF consistently surpasses the previous reduction methods with and without training. Specifically, DeiT-T and DeiT-S with MCTF reduce FLOPs by about 44% while improving the performance (+0.5%, and +0.3%) over the base model, respectively. We also demonstrate the applicability of MCTF in various Vision Transformers (e.g., T2T-ViT, LV-ViT), achieving at least 31% speedup without performance degradation. Code is available at https://github.com/mlvlab/MCTF.

PaperPDFConference PDFCodeCode 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="2403.10030")

Code

Syntology Ran 3 of 5 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 3 ran with no contract checked.

By repository: official repository: 5 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mlvlab/mctf 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

5 samples harvested; 3 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran
2unverified

Licence: 0 of the 5 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 mlvlab/MCTF. “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.

do_nothing mlvlab/MCTF/utils/mctf.py official repository ran fingerprinted MIT (permissive) · 00e9d5d63d4079de · report
merge_source mlvlab/MCTF/utils/mctf.py official repository ran MIT (permissive) · 8a67c271b170dd65 · report
merge_wavg mlvlab/MCTF/utils/mctf.py official repository ran MIT (permissive) · 35fd12a5c86d3087 · report
bipartite_soft_matching mlvlab/MCTF/utils/mctf.py official repository unverified MIT (permissive) · 58a3d8aacef250bc · report
mctf mlvlab/MCTF/utils/mctf.py official repository unverified MIT (permissive) · 92d18f3cf6ae00a5 · report

Tasks

Computational EfficiencyEfficient ViTsImage Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Efficient ViTs ImageNet-1K (With LV-ViT-S) MCTF ($r=8$) GFLOPs 4.9 #1 of 19 Archive leaderboard report
Efficient ViTs ImageNet-1K (With LV-ViT-S) MCTF ($r=8$) Top 1 Accuracy 83.5 #1 of 19 Archive leaderboard report
Efficient ViTs ImageNet-1K (With LV-ViT-S) MCTF ($r=12$) GFLOPs 4.2 #2 of 19 Archive leaderboard report
Efficient ViTs ImageNet-1K (With LV-ViT-S) MCTF ($r=12$) Top 1 Accuracy 83.4 #2 of 19 Archive leaderboard report
Efficient ViTs ImageNet-1K (With LV-ViT-S) MCTF ($r=16$) GFLOPs 3.6 #19 of 19 Archive leaderboard report
Efficient ViTs ImageNet-1K (With LV-ViT-S) MCTF ($r=16$) Top 1 Accuracy 82.3 #19 of 19 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-S) MCTF ($r=16$) GFLOPs 2.6 #1 of 41 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-S) MCTF ($r=16$) Top 1 Accuracy 80.1 #1 of 41 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-S) MCTF ($r=18$) GFLOPs 2.4 #3 of 41 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-S) MCTF ($r=18$) Top 1 Accuracy 79.9 #3 of 41 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-S) MCTF ($r=20$) GFLOPs 2.2 #19 of 41 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-S) MCTF ($r=20$) Top 1 Accuracy 79.5 #19 of 41 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-T) MCTF ($r=8$) GFLOPs 1.0 #2 of 22 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-T) MCTF ($r=8$) Top 1 Accuracy 72.9 #2 of 22 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-T) MCTF ($r=16$) GFLOPs 0.7 #3 of 22 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-T) MCTF ($r=16$) Top 1 Accuracy 72.7 #3 of 22 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-T) MCTF ($r=20$) GFLOPs 0.6 #16 of 22 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-T) MCTF ($r=20$) Top 1 Accuracy 71.4 #16 of 22 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

DeiTDropoutLV-ViTPruningT2T-ViTVision Transformer

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