Papers › AS-MLP: An Axial Shifted MLP Architecture for Vision

AS-MLP: An Axial Shifted MLP Architecture for Vision

18 Jul 2021ICLR 2022 4arXiv:2107.08391archive 2025-07-28

Dongze Lian, Zehao Yu, Xing Sun, Shenghua Gao

An Axial Shifted MLP architecture (AS-MLP) is proposed in this paper. Different from MLP-Mixer, where the global spatial feature is encoded for information flow through matrix transposition and one token-mixing MLP, we pay more attention to the local features interaction. By axially shifting channels of the feature map, AS-MLP is able to obtain the information flow from different axial directions, which captures the local dependencies. Such an operation enables us to utilize a pure MLP architecture to achieve the same local receptive field as CNN-like architecture. We can also design the receptive field size and dilation of blocks of AS-MLP, etc, in the same spirit of convolutional neural networks. With the proposed AS-MLP architecture, our model obtains 83.3% Top-1 accuracy with 88M parameters and 15.2 GFLOPs on the ImageNet-1K dataset. Such a simple yet effective architecture outperforms all MLP-based architectures and achieves competitive performance compared to the transformer-based architectures (e.g., Swin Transformer) even with slightly lower FLOPs. In addition, AS-MLP is also the first MLP-based architecture to be applied to the downstream tasks (e.g., object detection and semantic segmentation). The experimental results are also impressive. Our proposed AS-MLP obtains 51.5 mAP on the COCO validation set and 49.5 MS mIoU on the ADE20K dataset, which is competitive compared to the transformer-based architectures. Our AS-MLP establishes a strong baseline of MLP-based architecture. Code is available at https://github.com/svip-lab/AS-MLP.

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="2107.08391")

Code

Syntology Ran 5 of 13 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 1 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

svip-lab/AS-MLP officialmentioned in papermentioned on GitHubpytorchMIT report
liuruiyang98/Jittor-MLP mentioned on GitHubjax 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

13 samples harvested; 5 ran; 1 honoured the contract we drafted; 8 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 · violated contract
1ran · our draft was wrong
2ran
8unverified

Licence: 0 of the 13 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 svip-lab/AS-MLP. “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.

GET_BLOCKS svip-lab/AS-MLP/models/shift_cuda.py official repository ran · violated contract fingerprinted MIT (permissive) · c5acf386fe00c470 · report
MyNorm svip-lab/AS-MLP/models/as_mlp.py official repository ran · our draft was wrong MIT (permissive) · c3f4c265067c1717 · report
build_optimizer svip-lab/AS-MLP/optimizer.py official repository ran MIT (permissive) · e35a4b2e4114b1a5 · report
get_grad_norm svip-lab/AS-MLP/utils.py official repository ran · honoured contract MIT (permissive) · eec1e7cba51d5e8e · report
set_weight_decay svip-lab/AS-MLP/optimizer.py official repository ran MIT (permissive) · b33222a09fc93bec · report
Dtype svip-lab/AS-MLP/models/shift_cuda.py official repository unverified MIT (permissive) · 1e624f979ea53ae4 · report
auto_resume_helper svip-lab/AS-MLP/utils.py official repository unverified MIT (permissive) · 0c32459bef92ff8c · report
build_model svip-lab/AS-MLP/models/build.py official repository unverified MIT (permissive) · 2f65366bea62ccc7 · report
build_scheduler svip-lab/AS-MLP/lr_scheduler.py official repository unverified MIT (permissive) · c02cc4e0b5720211 · report
check_keywords_in_name svip-lab/AS-MLP/optimizer.py official repository unverified MIT (permissive) · b0a5beb34716d5a6 · report
create_logger svip-lab/AS-MLP/logger.py official repository unverified MIT (permissive) · 80450600f7f09b0a · report
get_config svip-lab/AS-MLP/config.py official repository unverified MIT (permissive) · 02a9e80c2bb81815 · report
load_checkpoint svip-lab/AS-MLP/utils.py official repository unverified MIT (permissive) · 640408a0715e42c2 · report

Tasks

Object DetectionSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation DensePASS ASMLP (MiT-B1) mIoU 42.05% #13 of 36 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

Average PoolingConvolutionDense ConnectionsDropoutGlobal Average PoolingLayer NormalizationMLP-MixerResidual Connection

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