Papers › Pruning Self-attentions into Convolutional Layers in Single Path

Pruning Self-attentions into Convolutional Layers in Single Path

23 Nov 2021arXiv:2111.11802archive 2025-07-28

Haoyu He, Jianfei Cai, Jing Liu, Zizheng Pan, Jing Zhang, DaCheng Tao, Bohan Zhuang

Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks. However, modeling global correlations with multi-head self-attention (MSA) layers leads to two widely recognized issues: the massive computational resource consumption and the lack of intrinsic inductive bias for modeling local visual patterns. To solve both issues, we devise a simple yet effective method named Single-Path Vision Transformer pruning (SPViT), to efficiently and automatically compress the pre-trained ViTs into compact models with proper locality added. Specifically, we first propose a novel weight-sharing scheme between MSA and convolutional operations, delivering a single-path space to encode all candidate operations. In this way, we cast the operation search problem as finding which subset of parameters to use in each MSA layer, which significantly reduces the computational cost and optimization difficulty, and the convolution kernels can be well initialized using pre-trained MSA parameters. Relying on the single-path space, we introduce learnable binary gates to encode the operation choices in MSA layers. Similarly, we further employ learnable gates to encode the fine-grained MLP expansion ratios of FFN layers. In this way, our SPViT optimizes the learnable gates to automatically explore from a vast and unified search space and flexibly adjust the MSA-FFN pruning proportions for each individual dense model. We conduct extensive experiments on two representative ViTs showing that our SPViT achieves a new SOTA for pruning on ImageNet-1k. For example, our SPViT can trim 52.0% FLOPs for DeiT-B and get an impressive 0.6% top-1 accuracy gain simultaneously. The source code is available at https://github.com/ziplab/SPViT.

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 7 code samples harvested from 1 repository linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 5 ran (4 with no instrument failure; 1 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.

zhuang-group/spvit officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 7 samples, 5 ran (1 instrument-failed) · 2 unverified report
zip-group/spvit officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: not harvested report
ziplab/spvit officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: not harvested 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

7 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 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.

1ran · our draft was wrong
4ran
2unverified

Licence: 0 of the 7 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 zhuang-group/spvit. “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.

zhuang-group/spvit official repository 7 samples, 5 ran (1 instrument-failed) · 2 unverified
add_weight_decay_2ops SPViT_DeiT/utils.py ran Apache-2.0 (permissive) · 6e8ab5fd7940cb9f · report fixture: signature model:callable/0/?, weight_decay:float/0/float, skip_list:tuple/1/str · returned tuple · level recorded 2026-09-24
bernoulli_sample SPViT_DeiT/models_pruning.py ran fingerprinted Apache-2.0 (permissive) · d2fd8fea61da291c · report fixture: signature probs:Tensor/2/float, temperature:float/0/float · returned Tensor · level recorded 2026-09-24
build_transform in 170 papers SPViT_DeiT/datasets.py ran · our draft was wrong Apache-2.0 (permissive) · 3bc74137ab36aa79 · report fixture: signature is_train:bool/0/bool, args:ArgsConfig/0/? · returned Compose · level recorded 2026-09-26
create_2optimizers SPViT_DeiT/utils.py ran Apache-2.0 (permissive) · 4e98bc6a44b3e514 · report fixture: signature args:Args/0/?, model:callable/0/?, filter_bias_and_bn:bool/0/bool · returned tuple · level recorded 2026-09-24
relaxed_bernoulli_logits SPViT_DeiT/models_pruning.py ran fingerprinted Apache-2.0 (permissive) · 7144e31403543bf8 · report fixture: signature probs:Tensor/2/float, temperature:float/0/float · returned Tensor · level recorded 2026-09-24
build_dataset in 151 papers SPViT_DeiT/datasets.py unverified Apache-2.0 (permissive) · ee1f337457f629d5 · report
create_scheduler in 17 papers SPViT_DeiT/utils.py unverified Apache-2.0 (permissive) · d17e06164cf90aa8 · report

Tasks

Efficient ViTsInductive BiasNeural Architecture Search

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Efficient ViTs ImageNet-1K (with DeiT-S) SPViT GFLOPs 3.3 #39 of 41 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-S) SPViT Top 1 Accuracy 78.3 #39 of 41 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-T) SPViT GFLOPs 1.0 #19 of 22 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-T) SPViT Top 1 Accuracy 70.7 #19 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

Absolute Position EncodingsAdamAttentionBPEConvolutionDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerPruningResidual ConnectionSoftmaxTransformerVision 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