Papers › OneFormer: One Transformer to Rule Universal Image Segmentation

OneFormer: One Transformer to Rule Universal Image Segmentation

10 Nov 2022CVPR 2023 1arXiv:2211.06220archive 2025-07-28

Jitesh Jain, Jiachen Li, MangTik Chiu, Ali Hassani, Nikita Orlov, Humphrey Shi

Universal Image Segmentation is not a new concept. Past attempts to unify image segmentation in the last decades include scene parsing, panoptic segmentation, and, more recently, new panoptic architectures. However, such panoptic architectures do not truly unify image segmentation because they need to be trained individually on the semantic, instance, or panoptic segmentation to achieve the best performance. Ideally, a truly universal framework should be trained only once and achieve SOTA performance across all three image segmentation tasks. To that end, we propose OneFormer, a universal image segmentation framework that unifies segmentation with a multi-task train-once design. We first propose a task-conditioned joint training strategy that enables training on ground truths of each domain (semantic, instance, and panoptic segmentation) within a single multi-task training process. Secondly, we introduce a task token to condition our model on the task at hand, making our model task-dynamic to support multi-task training and inference. Thirdly, we propose using a query-text contrastive loss during training to establish better inter-task and inter-class distinctions. Notably, our single OneFormer model outperforms specialized Mask2Former models across all three segmentation tasks on ADE20k, CityScapes, and COCO, despite the latter being trained on each of the three tasks individually with three times the resources. With new ConvNeXt and DiNAT backbones, we observe even more performance improvement. We believe OneFormer is a significant step towards making image segmentation more universal and accessible. To support further research, we open-source our code and models at https://github.com/SHI-Labs/OneFormer

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

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

By repository: official repository: 5 samples from 1 repository, 4 ran (2 with no instrument failure; 2 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

SHI-Labs/OneFormer officialmentioned in papermentioned on GitHubpytorchMITSyntology: 5 samples, 4 ran (2 instrument-failed) · 1 unverified report
huggingface/transformers mentioned on GitHubpytorchSyntology: 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), HuggingFace's Transformers: State-of-the-art Natural Language Processing (arXiv:1910.03771; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified), DeBERTa: Decoding-enhanced BERT with Disentangled Attention (arXiv:2006.03654; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
MindCode-4/code-2 mindsporeApache-2.0Syntology: not harvested report
yangyucheng000/University mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution (arXiv:2409.12191; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 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

5 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 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.

2ran · our draft was wrong
2ran
1unverified

Licence: 0 of the 5 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 SHI-Labs/OneFormer. “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. 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.

SHI-Labs/OneFormer official repository 5 samples, 4 ran (2 instrument-failed) · 1 unverified
batch_dice_loss in 60 papers oneformer/modeling/matcher.py ran · our draft was wrong fingerprinted MIT (permissive) · bc2cb481a75c370d · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float · returned Tensor · level recorded 2026-09-25
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket
oneformer/modeling/criterion.py ran · our draft was wrong fingerprinted MIT (permissive) · 89f75e54ff128be0 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_masks:float/0/float · returned Tensor · level recorded 2026-09-25
linear_sum_assignment_with_nan oneformer/modeling/matcher.py ran fingerprinted MIT (permissive) · 0b93a4545ba92b2d · report fixture: signature cost_matrix:ndarray/2/float · returned tuple · level recorded 2026-09-25
sigmoid_ce_loss in 70 papers
census: 4 implementations from 8 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
oneformer/modeling/criterion.py ran fingerprinted MIT (permissive) · dc4a40c394479bd8 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_masks:float/0/float · returned Tensor · level recorded 2026-09-25
batch_sigmoid_ce_loss in 48 papers oneformer/modeling/matcher.py unverified MIT (permissive) · 1edd24985036b0bf · report

Tasks

Instance SegmentationPanoptic SegmentationScene ParsingSegmentationSemantic SegmentationUniversal Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation ADE20K val OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained) AP 44.2 #1 of 14 Archive leaderboard report
Instance Segmentation ADE20K val OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained) APL 64.3 #1 of 14 Archive leaderboard report
Instance Segmentation ADE20K val OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained) APM 49.9 #1 of 14 Archive leaderboard report
Instance Segmentation ADE20K val OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained) APS 23.7 #1 of 14 Archive leaderboard report
Instance Segmentation ADE20K val OneFormer (DiNAT-L, single-scale, 1280x1280, COCO-pretrain) AP 40.2 #4 of 14 Archive leaderboard report
Instance Segmentation ADE20K val OneFormer (DiNAT-L, single-scale, 1280x1280, COCO-pretrain) APL 59.7 #4 of 14 Archive leaderboard report
Instance Segmentation ADE20K val OneFormer (DiNAT-L, single-scale, 1280x1280, COCO-pretrain) APM 44.4 #4 of 14 Archive leaderboard report
Instance Segmentation ADE20K val OneFormer (DiNAT-L, single-scale, 1280x1280, COCO-pretrain) APS 19.2 #4 of 14 Archive leaderboard report
Instance Segmentation ADE20K val OneFormer (DiNAT-L, single-scale) AP 36.0 #7 of 14 Archive leaderboard report
Instance Segmentation ADE20K val OneFormer (Swin-L, single-scale) AP 35.9 #8 of 14 Archive leaderboard report
Instance Segmentation COCO val (panoptic labels) OneFormer (InternImage-H, emb_dim=1024, single-scale) AP 52.0 #1 of 4 Archive leaderboard report
Instance Segmentation COCO val (panoptic labels) OneFormer (DiNAT-L, single-scale) AP 49.2 #2 of 4 Archive leaderboard report
Instance Segmentation COCO val (panoptic labels) OneFormer (Swin-L, single-scale) AP 49.0 #4 of 4 Archive leaderboard report
Instance Segmentation Cityscapes val OneFormer (ConvNeXt-L, single-scale, Mapillary-Pretrained) mask AP 48.7 #2 of 17 Archive leaderboard report
Instance Segmentation Cityscapes val OneFormer (DiNAT-L, single-scale) mask AP 45.6 #5 of 17 Archive leaderboard report
Instance Segmentation Cityscapes val OneFormer (Swin-L, single-scale) mask AP 45.6 #6 of 17 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (InternImage-H, emb_dim=256, single-scale, 896x896) AP 40.2 #1 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (InternImage-H, emb_dim=256, single-scale, 896x896) PQ 54.5 #1 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (InternImage-H, emb_dim=256, single-scale, 896x896) mIoU 60.4 #1 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (DiNAT-L, single-scale, 1280x1280, COCO-Pretrain) PQ 53.4 #4 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (DiNAT-L, single-scale, 1280x1280, COCO-Pretrain) mIoU 58.9 #4 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (DiNAT-L, single-scale, 1280x1280) AP 37.1 #8 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (DiNAT-L, single-scale, 1280x1280) PQ 51.5 #8 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (DiNAT-L, single-scale, 1280x1280) mIoU 58.3 #8 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (Swin-L, single-scale, 1280x1280) AP 37.8 #9 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (Swin-L, single-scale, 1280x1280) PQ 51.4 #9 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (Swin-L, single-scale, 1280x1280) mIoU 57.0 #9 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (DiNAT-L, single-scale, 640x640) AP 36.0 #11 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (DiNAT-L, single-scale, 640x640) PQ 50.5 #11 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (DiNAT-L, single-scale, 640x640) mIoU 58.3 #11 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (ConvNeXt-XL, single-scale, 640x640) AP 36.3 #12 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (ConvNeXt-XL, single-scale, 640x640) PQ 50.1 #12 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (ConvNeXt-XL, single-scale, 640x640) mIoU 57.4 #12 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (ConvNeXt-L, single-scale, 640x640) AP 36.2 #13 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (ConvNeXt-L, single-scale, 640x640) PQ 50.0 #13 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (ConvNeXt-L, single-scale, 640x640) mIoU 56.6 #13 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (Swin-L, single-scale, 640x640) AP 35.9 #14 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (Swin-L, single-scale, 640x640) PQ 49.8 #14 of 25 Archive leaderboard report
Panoptic Segmentation ADE20K val OneFormer (Swin-L, single-scale, 640x640) mIoU 57.0 #14 of 25 Archive leaderboard report
Panoptic Segmentation COCO minival OneFormer (InternImage-H,single-scale) AP 52.0 #2 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival OneFormer (InternImage-H,single-scale) PQ 60.0 #2 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival OneFormer (InternImage-H,single-scale) PQst 49.2 #2 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival OneFormer (InternImage-H,single-scale) PQth 67.1 #2 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival OneFormer (InternImage-H,single-scale) mIoU 68.8 #2 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival OneFormer (DiNAT-L, single-scale) AP 49.2 #14 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival OneFormer (DiNAT-L, single-scale) PQ 58.0 #14 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival OneFormer (DiNAT-L, single-scale) PQst 48.4 #14 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival OneFormer (DiNAT-L, single-scale) PQth 64.3 #14 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival OneFormer (DiNAT-L, single-scale) mIoU 68.1 #14 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival OneFormer (Swin-L, single-scale) AP 49.0 #16 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival OneFormer (Swin-L, single-scale) PQ 57.9 #16 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival OneFormer (Swin-L, single-scale) PQst 48.0 #16 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival OneFormer (Swin-L, single-scale) PQth 64.4 #16 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival OneFormer (Swin-L, single-scale) mIoU 67.4 #16 of 31 Archive leaderboard report
Panoptic Segmentation Cityscapes test OneFormer (ConvNeXt-L, single-scale, Mapillary Vistas-Pretrained) PQ 68.0 #1 of 10 Archive leaderboard report
Panoptic Segmentation Cityscapes val OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained) AP 48.7 #2 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained) PQ 70.1 #2 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained) PQst 74.1 #2 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained) PQth 64.6 #2 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val OneFormer (ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained) mIoU 84.6 #2 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val OneFormer (ConvNeXt-L, single-scale) AP 46.5 #4 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val OneFormer (ConvNeXt-L, single-scale) PQ 68.51 #4 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val OneFormer (ConvNeXt-L, single-scale) mIoU 83.0 #4 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val OneFormer (ConvNeXt-XL, single-scale) AP 46.7 #7 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val OneFormer (ConvNeXt-XL, single-scale) PQ 68.4 #7 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val OneFormer (ConvNeXt-XL, single-scale) mIoU 83.6 #7 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val OneFormer (DiNAT-L, single-scale) AP 45.6 #10 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val OneFormer (DiNAT-L, single-scale) PQ 67.6 #10 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val OneFormer (DiNAT-L, single-scale) mIoU 83.1 #10 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val OneFormer (Swin-L, single-scale) AP 45.6 #13 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val OneFormer (Swin-L, single-scale) PQ 67.2 #13 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val OneFormer (Swin-L, single-scale) mIoU 83.0 #13 of 37 Archive leaderboard report
Panoptic Segmentation Mapillary val OneFormer (DiNAT-L, single-scale) PQ 46.7 #1 of 13 Archive leaderboard report
Panoptic Segmentation Mapillary val OneFormer (DiNAT-L, single-scale) PQst 54.9 #1 of 13 Archive leaderboard report
Panoptic Segmentation Mapillary val OneFormer (DiNAT-L, single-scale) PQth 40.5 #1 of 13 Archive leaderboard report
Panoptic Segmentation Mapillary val OneFormer (DiNAT-L, single-scale) mIoU 61.7 #1 of 13 Archive leaderboard report
Panoptic Segmentation Mapillary val OneFormer (ConvNeXt-L, single-scale) PQ 46.4 #2 of 13 Archive leaderboard report
Panoptic Segmentation Mapillary val OneFormer (ConvNeXt-L, single-scale) PQst 54.0 #2 of 13 Archive leaderboard report
Panoptic Segmentation Mapillary val OneFormer (ConvNeXt-L, single-scale) PQth 40.6 #2 of 13 Archive leaderboard report
Panoptic Segmentation Mapillary val OneFormer (ConvNeXt-L, single-scale) mIoU 61.6 #2 of 13 Archive leaderboard report
Semantic Segmentation ADE20K val OneFormer (InternImage-H, emb_dim=256, multi-scale, 896x896) mIoU 60.8 #6 of 95 Archive leaderboard report
Semantic Segmentation ADE20K val OneFormer (DiNAT-L, multi-scale, 896x896) mIoU 58.6 #9 of 95 Archive leaderboard report
Semantic Segmentation ADE20K val OneFormer (DiNAT-L, multi-scale, 640x640) mIoU 58.4 #11 of 95 Archive leaderboard report
Semantic Segmentation ADE20K val OneFormer (Swin-L, multi-scale, 896x896) mIoU 58.3 #14 of 95 Archive leaderboard report
Semantic Segmentation ADE20K val OneFormer (Swin-L, multi-scale, 640x640) mIoU 57.7 #19 of 95 Archive leaderboard report
Semantic Segmentation COCO (Common Objects in Context) OneFormer (InternImage-H, emb_dim=1024, single-scale) mIoU 68.8 #3 of 9 Archive leaderboard report
Semantic Segmentation COCO (Common Objects in Context) OneFormer (DiNAT-L, single-scale) mIoU 68.1 #5 of 9 Archive leaderboard report
Semantic Segmentation COCO (Common Objects in Context) OneFormer (Swin-L, single-scale) mIoU 67.4 #6 of 9 Archive leaderboard report
Semantic Segmentation Cityscapes val OneFormer (ConvNeXt-XL, Mapillary, multi-scale) mIoU 85.8 #9 of 99 Archive leaderboard report
Semantic Segmentation Cityscapes val OneFormer (ConvNeXt-XL, multi-scale) mIoU 84.6 #14 of 99 Archive leaderboard report
Semantic Segmentation Cityscapes val OneFormer (Swin-L, multi-scale) mIoU 84.4 #16 of 99 Archive leaderboard report
Semantic Segmentation Mapillary val OneFormer (DiNAT-L, multi-scale) mIoU 64.9 #2 of 8 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 EncodingsAdamAttentionConvNeXtDense ConnectionsDropoutLayer NormalizationLinear LayerMulti-Head AttentionNeighborhood 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