Papers › Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation

Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation

17 Mar 2020ECCV 2020 8arXiv:2003.07853archive 2025-07-28

Huiyu Wang, Yukun Zhu, Bradley Green, Hartwig Adam, Alan Yuille, Liang-Chieh Chen

Convolution exploits locality for efficiency at a cost of missing long range context. Self-attention has been adopted to augment CNNs with non-local interactions. Recent works prove it possible to stack self-attention layers to obtain a fully attentional network by restricting the attention to a local region. In this paper, we attempt to remove this constraint by factorizing 2D self-attention into two 1D self-attentions. This reduces computation complexity and allows performing attention within a larger or even global region. In companion, we also propose a position-sensitive self-attention design. Combining both yields our position-sensitive axial-attention layer, a novel building block that one could stack to form axial-attention models for image classification and dense prediction. We demonstrate the effectiveness of our model on four large-scale datasets. In particular, our model outperforms all existing stand-alone self-attention models on ImageNet. Our Axial-DeepLab improves 2.8% PQ over bottom-up state-of-the-art on COCO test-dev. This previous state-of-the-art is attained by our small variant that is 3.8x parameter-efficient and 27x computation-efficient. Axial-DeepLab also achieves state-of-the-art results on Mapillary Vistas and Cityscapes.

PaperPDFConference PDFCodeCode 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

No sample from the archive's official repository (google-research/deeplab2) is linked to this paper; the 10 samples below come from 1 repository the archive does not mark official, and 1 more is identical to code Syntology harvested from another paper's repository. Syntology harvested code from google-research/deeplab2 for another paper.

google-research/deeplab2: Syntology's graph links these samples to PolyMaX: General Dense Prediction with Mask Transformer (arXiv:2311.05770; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.

Syntology 11 code samples: 10 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 11: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: named in the paper: 10 samples from 1 repository, 8 ran (5 with no instrument failure; 3 where Syntology's instrument failed); 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.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 8 samples that ran have no recorded date.

google-research/deeplab2 officialtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PolyMaX: General Dense Prediction with Mask Transformer (arXiv:2311.05770; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
csrhddlam/axial-deeplab mentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 10 samples, 8 ran (3 instrument-failed) · 2 unverified report
MartinGer/Stand-Alone-Axial-Attention mentioned on GitHubpytorchSyntology: not harvested report
xiaofeng94/gmflownet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Global Matching with Overlapping Attention for Optical Flow Estimation (arXiv:2203.11335; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
The-AI-Summer/self_attention pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (arXiv:2010.11929; that paper's own run record: 307 ran (of which 165 constructed an object rather than computing a result; 286 with no instrument failure: 8 honoured, 2 violated, 276 with no contract checked; 21 where Syntology's instrument failed) · 112 unverified) and Bottleneck Transformers for Visual Recognition (arXiv:2101.11605; that paper's own run record: 26 ran (of which 9 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 7 where Syntology's instrument failed) · 23 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

11 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
5ran
3unverified

Licence: 1 of the 11 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 csrhddlam/axial-deeplab. 1 sample is listed last, in a group without a repository. “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.

csrhddlam/axial-deeplab named in the paper 10 samples, 8 ran (3 instrument-failed) · 2 unverified
cross_entropy_for_onehot in 5 papers lib/utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · e4df01238c9e5ba5 · report fixture: signature pred:Tensor/2/float, target:Tensor/2/float · returned Tensor · level recorded, date not recorded
adjust_learning_rate in 125 papers lib/utils.py ran Apache-2.0 (permissive) · 9d1a2a8f3cd2f263 · report fixture: signature args:Args/0/?, optimizer:SGD/0/?, epoch:int/0/int, batch_idx:int/0/int, data_nums:int/0/int, type:str/0/str · returned float · level recorded 2026-09-24
build_optimizer in 83 papers lib/build_optimizer.py ran Apache-2.0 (permissive) · 57c57f81551ed227 · report fixture: signature args:Args/0/?, model:callable/0/? · returned SGD · level recorded 2026-09-24
conv1x1 in 691 papers lib/models/axialnet.py ran · our draft was wrong Apache-2.0 (permissive) · d9def42110729a85 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers lib/models/resnet.py ran · our draft was wrong Apache-2.0 (permissive) · 160bb14bd76201b4 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded
imagenet1k lib/datasets/imagenet1k.py ran Apache-2.0 (permissive) · d951f27a92264740 · report fixture: signature args:Args/0/?, distributed:bool/0/bool · returned tuple · level recorded 2026-09-24
label_smoothing in 8 papers lib/utils.py ran Apache-2.0 (permissive) · 5c9e8b037a72dcd8 · report fixture: signature pred:Tensor/2/float, target:Tensor/1/int, eta:float/0/float · returned Tensor · level recorded 2026-09-24
resnet18 in 432 papers lib/models/resnet.py ran Apache-2.0 (permissive) · 72e76034eb3a8502 · report fixture: signature pretrained:bool/0/bool, progress:bool/0/bool · returned ResNet · level recorded 2026-09-24
axial26s lib/models/axialnet.py unverified Apache-2.0 (permissive) · 67a7daffbe6a2857 · report
axial50s lib/models/axialnet.py unverified Apache-2.0 (permissive) · 33a7ebf42fab13a5 · report
Repository not located 1 sample, 0 ran · 1 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
prepare_data in 87 papers repository not located unverified licence of this copy not recorded · 10b86d2ef7ff73c5 · report

Tasks

Image ClassificationPanoptic Segmentationimage-classification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Panoptic Segmentation COCO minival Axial-DeepLab-L (multi-scale) PQ 43.9 #28 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Axial-DeepLab-L (single-scale) PQ 43.4 #29 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Axial-DeepLab-L (single-scale) PQst 35.6 #29 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Axial-DeepLab-L (single-scale) PQth 48.5 #29 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Axial-DeepLab-L(multi-scale) PQst 36.8 #30 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Axial-DeepLab-L(multi-scale) PQth 48.6 #30 of 31 Archive leaderboard report
Panoptic Segmentation COCO test-dev Axial-DeepLab-L (multi-scale) PQ 44.2 #28 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev Axial-DeepLab-L (multi-scale) PQst 36.8 #28 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev Axial-DeepLab-L (multi-scale) PQth 49.2 #28 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev Axial-DeepLab-L PQ 43.6 #29 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev Axial-DeepLab-L PQst 35.6 #29 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev Axial-DeepLab-L PQth 48.9 #29 of 38 Archive leaderboard report
Panoptic Segmentation Cityscapes test Axial-DeepLab-XL (Mapillary Vistas, multi-scale) PQ 66.6 #4 of 10 Archive leaderboard report
Panoptic Segmentation Cityscapes val Axial-DeepLab-XL (Mapillary Vistas, multi-scale) AP 44.2 #5 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val Axial-DeepLab-XL (Mapillary Vistas, multi-scale) PQ 68.5 #5 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val Axial-DeepLab-XL (Mapillary Vistas, multi-scale) mIoU 84.6 #5 of 37 Archive leaderboard report
Panoptic Segmentation Mapillary val Axial-DeepLab-L (multi-scale) PQ 41.1 #6 of 13 Archive leaderboard report
Panoptic Segmentation Mapillary val Axial-DeepLab-L (multi-scale) PQst 51.3 #6 of 13 Archive leaderboard report
Panoptic Segmentation Mapillary val Axial-DeepLab-L (multi-scale) PQth 33.4 #6 of 13 Archive leaderboard report
Panoptic Segmentation Mapillary val Axial-DeepLab-L (multi-scale) mIoU 58.4 #6 of 13 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.

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