Papers › MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for...

MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing

27 Aug 2023ICCV 2023 1arXiv:2308.14036archive 2025-07-28

Yuwei Qiu, Kaihao Zhang, Chenxi Wang, Wenhan Luo, Hongdong Li, Zhi Jin

In recent years, Transformer networks are beginning to replace pure convolutional neural networks (CNNs) in the field of computer vision due to their global receptive field and adaptability to input. However, the quadratic computational complexity of softmax-attention limits the wide application in image dehazing task, especially for high-resolution images. To address this issue, we propose a new Transformer variant, which applies the Taylor expansion to approximate the softmax-attention and achieves linear computational complexity. A multi-scale attention refinement module is proposed as a complement to correct the error of the Taylor expansion. Furthermore, we introduce a multi-branch architecture with multi-scale patch embedding to the proposed Transformer, which embeds features by overlapping deformable convolution of different scales. The design of multi-scale patch embedding is based on three key ideas: 1) various sizes of the receptive field; 2) multi-level semantic information; 3) flexible shapes of the receptive field. Our model, named Multi-branch Transformer expanded by Taylor formula (MB-TaylorFormer), can embed coarse to fine features more flexibly at the patch embedding stage and capture long-distance pixel interactions with limited computational cost. Experimental results on several dehazing benchmarks show that MB-TaylorFormer achieves state-of-the-art (SOTA) performance with a light computational burden. The source code and pre-trained models are available at https://github.com/FVL2020/ICCV-2023-MB-TaylorFormer.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 26 code samples harvested from 1 repository linked to this paper: 22 ran (of which 7 constructed an object rather than computing a result; 15 with no instrument failure: 4 honoured, 0 violated, 11 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 5 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 26 samples from 1 repository, 22 ran (15 with no instrument failure; 7 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 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 22 samples that ran have no recorded date.

fvl2020/iccv-2023-mb-taylorformer officialmentioned in papermentioned on GitHubpytorchSyntology: 26 samples, 22 ran (7 instrument-failed) · 4 unverified 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

26 samples harvested: 22 ran (of which 7 constructed an object rather than computing a result; 15 with no instrument failure: 4 honoured, 0 violated, 11 with no contract checked; 7 where Syntology's instrument failed) · 4 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.

4ran · honoured contract
2ran · our draft was wrong
5ran; the contract check could not run
11ran
4unverified

Licence: 26 of the 26 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 fvl2020/iccv-2023-mb-taylorformer. “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”. For 6 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

fvl2020/iccv-2023-mb-taylorformer official repository 26 samples, 22 ran (7 instrument-failed) · 4 unverified
count_param in 6 papers basicsr/models/archs/MB_TaylorFormer.py ran · honoured contract no licence file found · pointer only · afd3c5ab4cb8face · report fixture: signature model:callable/0/? · returned int · level recorded, date not recorded
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
basicsr/models/archs/MB_TaylorFormer.py ran no licence file found · pointer only · 659261b010a72668 · report fixture: returned Attention · level recorded 2026-09-22
DWCPatchEmbed basicsr/models/archs/MB_TaylorFormer.py ran fingerprinted no licence file found · pointer only · 7e12b4a365754bb3 · report fixture: returned DWCPatchEmbed · level recorded 2026-09-22
DWConv2d_BN basicsr/models/archs/MB_TaylorFormer.py ran fingerprinted no licence file found · pointer only · 64cd61fee6349de6 · report fixture: returned DWConv2d_BN · level recorded 2026-09-22
Downsample in 58 papers basicsr/models/archs/MB_TaylorFormer.py ran no licence file found · pointer only · 428e6e039f598efa · report fixture: returned Downsample · level recorded 2026-09-22
Patch_Embed_stage basicsr/models/archs/MB_TaylorFormer.py ran fingerprinted no licence file found · pointer only · 2d32326ab1c1db16 · report fixture: returned Patch_Embed_stage · level recorded 2026-09-22
SKFF basicsr/models/archs/MB_TaylorFormer.py ran no licence file found · pointer only · 03b6adc687eca587 · report fixture: returned SKFF · level recorded 2026-09-22
TransformerBlock in 73 papers basicsr/models/archs/MB_TaylorFormer.py ran no licence file found · pointer only · 60ff91d683606241 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Upsample in 77 papers basicsr/models/archs/MB_TaylorFormer.py ran fingerprinted no licence file found · pointer only · 5499b5a997e32c0e · report fixture: returned Upsample · level recorded 2026-09-22
calculate_fid in 26 papers basicsr/metrics/fid.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 1d7ce6d6dd7ff5c1 · report fixture: signature mu1:ndarray/1/float, sigma1:ndarray/2/float, mu2:ndarray/1/float, sigma2:ndarray/2/float, eps:float/0/float · returned float64 · level recorded 2026-09-24
calculate_psnr in 51 papers utils.py ran · our draft was wrong no licence file found · pointer only · d292dd965ab59629 · report fixture: signature img1:ndarray/2/int, img2:ndarray/2/int, border:int/0/int · returned float · level recorded 2026-09-24
calculate_ssim in 24 papers utils.py ran · our draft was wrong no licence file found · pointer only · a05b184dc6c264a0 · report fixture: signature img1:ndarray/3/int, img2:ndarray/3/int, border:int/0/int · returned float64 · level recorded 2026-09-24
compute_feature in 10 papers basicsr/metrics/niqe.py ran · honoured contract fingerprinted no licence file found · pointer only · 5170ff1c4106b27a · report fixture: signature block:ndarray/2/float · returned list · level recorded 2026-09-24
estimate_aggd_param in 9 papers basicsr/metrics/niqe.py ran · honoured contract no licence file found · pointer only · a1282a48b0941f5d · report fixture: signature block:ndarray/2/float · returned tuple · level recorded 2026-09-24
extract_inception_features in 9 papers basicsr/metrics/fid.py ran no licence file found · pointer only · c9fb213c957dc82d · report fixture: signature data_generator:generator/0/?, inception:callable/0/?, len_generator:int/0/int, device:str/0/str · returned Tensor · level recorded 2026-09-24
get_position_from_periods in 59 papers basicsr/models/lr_scheduler.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · cd569444547de84f · report fixture: signature iteration:int/0/int, cumulative_period:list/1/int · returned int · level recorded 2026-09-24
refine_att basicsr/models/archs/MB_TaylorFormer.py ran no licence file found · pointer only · 59ccf227e7c920d2 · report fixture: signature q:Tensor/4/float, k:Tensor/4/float, v:Tensor/4/float, size:tuple/1/int · returned Tensor · level recorded 2026-09-24
reorder_image in 18 papers basicsr/metrics/metric_util.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 95067518dc16b3e5 · report fixture: signature img:ndarray/3/int, input_order:str/0/str · returned ndarray · level recorded 2026-09-24
ssim in 112 papers utils.py ran · honoured contract fingerprinted no licence file found · pointer only · ba721aeacc165234 · report fixture: signature img1:ndarray/2/int, img2:ndarray/2/int · returned float64 · level recorded 2026-09-24
ssim_cv2 Dehazing/calculate_compare.py ran fingerprinted no licence file found · pointer only · bbbdfc579e51326c · report fixture: signature img1:ndarray/2/int, img2:ndarray/2/int · returned float64 · level recorded 2026-09-24
to_3d in 66 papers
census: 3 implementations from 20 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
basicsr/models/archs/MB_TaylorFormer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 82a15cc1e46f7e4d · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded, date not recorded
to_4d in 69 papers basicsr/models/archs/MB_TaylorFormer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · b20f2a5df739a59e · report fixture: signature x:Tensor/3/float, h:int/0/int, w:int/0/int · returned Tensor · level recorded, date not recorded
MB_TaylorFormer basicsr/models/archs/MB_TaylorFormer.py unverified no licence file found · pointer only · 5b4b5591be8c70df · report
MHCAEncoder basicsr/models/archs/MB_TaylorFormer.py unverified no licence file found · pointer only · 579b7505e2f45641 · report
MHCA_stage basicsr/models/archs/MB_TaylorFormer.py unverified no licence file found · pointer only · ed01ae5f23d33199 · report
niqe in 9 papers basicsr/metrics/niqe.py unverified no licence file found · pointer only · 0029cb1566e47350 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for MB-TaylorFormer (graph method: MB-TaylorFormer). 19 bricks; individually on a fixture: 16 ran (of which 12 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. MB_TaylorFormer entry · level 0 · unverified · 5b4b5591be8c70df
  2. Downsample model · level 1 · ran · 428e6e039f598efa
  3. MHCA_stage model · level 0 · unverified · ed01ae5f23d33199
  4. OverlapPatchEmbed model · level 1 · ran · 099f2dc5f59fa05f
  5. Patch_Embed_stage model · level 1 · ran · 2d32326ab1c1db16
  6. Upsample model · level 1 · ran · 5499b5a997e32c0e
  7. MHCAEncoder model · level 0 · unverified · 579b7505e2f45641
  8. SKFF model · level 1 · ran · 03b6adc687eca587
  9. DWCPatchEmbed model · level 1 · ran · 7e12b4a365754bb3
  10. TransformerBlock model · level 1 · ran · 60ff91d683606241
  11. DWConv2d_BN model · level 1 · ran · 64cd61fee6349de6
  12. Attention model · level 1 · ran · 659261b010a72668
  13. FeedForward model · level 1 · ran · 479ae430111a6061
  14. LayerNorm helper · level 1 · ran · 7add138148389ff5
  15. refine_att model · level 1 · ran · 59ccf227e7c920d2
  16. BiasFree_LayerNorm helper · level 1 · ran · db9f0e70f3f18049
  17. WithBias_LayerNorm helper · level 1 · ran · 1d90d30671b0d4b8
  18. to_3d helper · level 1 · ran; the contract check could not run (RAISES) · 82a15cc1e46f7e4d
  19. to_4d helper · level 1 · ran; the contract check could not run (RAISES) · b20f2a5df739a59e

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2308.14036") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image Dehazing

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEConvolutionDeformable ConvolutionDense 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