Papers › Couplformer:Rethinking Vision Transformer with Coupling Attention Map

Couplformer:Rethinking Vision Transformer with Coupling Attention Map

10 Dec 2021arXiv:2112.05425archive 2025-07-28

Hai Lan, Xihao Wang, Xian Wei

With the development of the self-attention mechanism, the Transformer model has demonstrated its outstanding performance in the computer vision domain. However, the massive computation brought from the full attention mechanism became a heavy burden for memory consumption. Sequentially, the limitation of memory reduces the possibility of improving the Transformer model. To remedy this problem, we propose a novel memory economy attention mechanism named Couplformer, which decouples the attention map into two sub-matrices and generates the alignment scores from spatial information. A series of different scale image classification tasks are applied to evaluate the effectiveness of our model. The result of experiments shows that on the ImageNet-1k classification task, the Couplformer can significantly decrease 28% memory consumption compared with regular Transformer while accessing sufficient accuracy requirements and outperforming 0.92% on Top-1 accuracy while occupying the same memory footprint. As a result, the Couplformer can serve as an efficient backbone in visual tasks, and provide a novel perspective on the attention mechanism for researchers.

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="2112.05425")

Code

Syntology Ran 6 of 12 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 3 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

wer010/Couplformer officialpytorch 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

12 samples harvested; 6 ran; 1 honoured the contract we drafted; 6 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.

1ran · honoured contract
1ran · our draft was wrong
3ran · fixture could not drive it
1ran
6unverified

Licence: 12 of the 12 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 wer010/Couplformer. “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.

window_partition wer010/Couplformer/src/swin.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 144d10b49baeb8a6 · report
accuracy wer010/Couplformer/evaluate.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · d5edbca041111ce3 · report
cls_validate wer010/Couplformer/evaluate.py official repository ran · honoured contract no licence file found · pointer only · 3bca64f194bf9a4c · report
count_parameters wer010/Couplformer/ddp_train.py official repository ran no licence file found · pointer only · 6a41f5e3194a54b1 · report
drop_path wer010/Couplformer/src/utils/stochastic_depth.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 6bb7492655ecbda4 · report
window_reverse wer010/Couplformer/src/swin.py official repository ran · our draft was wrong no licence file found · pointer only · 61bf152e6a42a184 · report
cct_sd wer010/Couplformer/src/cct.py official repository unverified no licence file found · pointer only · a05e508be34863c6 · report
kct_sd wer010/Couplformer/src/kct.py official repository unverified no licence file found · pointer only · 24bd7de1ce705a4b · report
simple_accuracy wer010/Couplformer/ddp_train.py official repository unverified no licence file found · pointer only · 3c241ecfe3749a6d · report
vic_10 wer010/Couplformer/src/vic.py official repository unverified no licence file found · pointer only · 59cf6b7b765b5627 · report
vic_6 wer010/Couplformer/src/vic.py official repository unverified no licence file found · pointer only · 438fd905dba1403f · report
vic_sd wer010/Couplformer/src/vic.py official repository unverified no licence file found · pointer only · 2241f1a5c5f4a2c2 · report

Tasks

Image Classificationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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