Papers › CycleMLP: A MLP-like Architecture for Dense Prediction

CycleMLP: A MLP-like Architecture for Dense Prediction

21 Jul 2021ICLR 2022 4arXiv:2107.10224archive 2025-07-28

Shoufa Chen, Enze Xie, Chongjian Ge, Runjian Chen, Ding Liang, Ping Luo

This paper presents a simple MLP-like architecture, CycleMLP, which is a versatile backbone for visual recognition and dense predictions. As compared to modern MLP architectures, e.g., MLP-Mixer, ResMLP, and gMLP, whose architectures are correlated to image size and thus are infeasible in object detection and segmentation, CycleMLP has two advantages compared to modern approaches. (1) It can cope with various image sizes. (2) It achieves linear computational complexity to image size by using local windows. In contrast, previous MLPs have O(N²) computations due to fully spatial connections. We build a family of models which surpass existing MLPs and even state-of-the-art Transformer-based models, e.g., Swin Transformer, while using fewer parameters and FLOPs. We expand the MLP-like models' applicability, making them a versatile backbone for dense prediction tasks. CycleMLP achieves competitive results on object detection, instance segmentation, and semantic segmentation. In particular, CycleMLP-Tiny outperforms Swin-Tiny by 1.3% mIoU on ADE20K dataset with fewer FLOPs. Moreover, CycleMLP also shows excellent zero-shot robustness on ImageNet-C dataset. Code is available at https://github.com/ShoufaChen/CycleMLP.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2107.10224")

Code

Syntology Ran 9 of 15 code samples harvested from 3 repositories linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · violated contract; 8 ran with no contract checked.

By repository: official repository: 4 samples from 1 repository, 1 ran; community (archive-listed): 10 samples from 2 repositories, 7 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ShoufaChen/CycleMLP officialmentioned in papermentioned on GitHubpytorchMIT report
Ahmad-Omar-Ahsan/CycleMLP mentioned on GitHubpytorch report
BR-IDL/PaddleViT mentioned on GitHubpaddleApache-2.0 report
flytocc/CycleMLP-paddle mentioned on GitHubpaddle report
liuruiyang98/Jittor-MLP mentioned on GitHubjax report
revsic/tf-mlptts mentioned on GitHubtfMIT report
shier1/CycleMLP-paddle mentioned on GitHubpaddle 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

15 samples harvested; 9 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · violated contract
8ran
6unverified

Licence: 1 of the 15 samples is 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 3 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

pil_loader ShoufaChen/CycleMLP/mcloader/mcloader.py official repository ran MIT (permissive) · 6cc5ed3b37c68d9d · report
basic_blocks ShoufaChen/CycleMLP/cycle_mlp.py official repository unverified MIT (permissive) · f679822e5f5f467c · report
build_transform ShoufaChen/CycleMLP/datasets.py official repository unverified MIT (permissive) · 3bc74137ab36aa79 · report
sfc_flop_jit ShoufaChen/CycleMLP/utils.py official repository unverified MIT (permissive) · 2a2617c52f0e6b56 · report
CycleFC Ahmad-Omar-Ahsan/CycleMLP/models/cycle_mlp.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 6ba716e31944fe22 · report
Cycle_Block Ahmad-Omar-Ahsan/CycleMLP/models/cycle_mlp.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · a7533815a60a5ff4 · report
MLP Ahmad-Omar-Ahsan/CycleMLP/models/cycle_mlp.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 65aa6021f94c1bd7 · report
MLP_Block Ahmad-Omar-Ahsan/CycleMLP/models/cycle_mlp.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 9f01e73d5c35c5b6 · report
OverlapPatchEmbed Ahmad-Omar-Ahsan/CycleMLP/models/cycle_mlp.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 93aac00d7f2d7fba · report
Spatial_Proj Ahmad-Omar-Ahsan/CycleMLP/models/cycle_mlp.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 3e5be041fd16d9c9 · report
load_state revsic/tf-mlptts/config.py community (archive-listed) ran MIT (permissive) · a93e65374343828b · report
CycleMLP Ahmad-Omar-Ahsan/CycleMLP/models/cycle_mlp.py community (archive-listed) unverified MIT (permissive) · a58aae0835a61b41 · report
CycleMLP_Block Ahmad-Omar-Ahsan/CycleMLP/models/cycle_mlp.py community (archive-listed) unverified MIT (permissive) · e8703140c0494e82 · report
Stage Ahmad-Omar-Ahsan/CycleMLP/models/cycle_mlp.py community (archive-listed) unverified MIT (permissive) · 20a854cf90927d91 · report
pair identical code first harvested elsewhere ran · violated contract fingerprinted licence of this copy not recorded · 6ba8cee9f5daea41 · report

Tasks

Image ClassificationInstance SegmentationObject DetectionPredictionSegmentationSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet CycleMLP-B5 GFLOPs 12.3 #461 of 1060 Archive leaderboard report
Image Classification ImageNet CycleMLP-B5 Number of params 76M #461 of 1060 Archive leaderboard report
Image Classification ImageNet CycleMLP-B5 Top 1 Accuracy 83.2% #461 of 1060 Archive leaderboard report
Semantic Segmentation DensePASS CycleMLP (MiT-B1) mIoU 40.16% #15 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

Absolute Position EncodingsAdamAffine OperatorAttentionAverage PoolingBPEDense ConnectionsDropoutFeedforward NetworkGlobal Average PoolingLabel SmoothingLayer NormalizationLinear LayerMLP-MixerMulti-Head AttentionPosition-Wise Feed-Forward LayerResMLPResidual ConnectionSoftmaxSpatial Gating UnitStochastic DepthSwin TransformerTransformergMLP

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