Papers › Exploring Plain Vision Transformer Backbones for Object Detection

Exploring Plain Vision Transformer Backbones for Object Detection

30 Mar 2022arXiv:2203.16527archive 2025-07-28

Yanghao Li, Hanzi Mao, Ross Girshick, Kaiming He

We explore the plain, non-hierarchical Vision Transformer (ViT) as a backbone network for object detection. This design enables the original ViT architecture to be fine-tuned for object detection without needing to redesign a hierarchical backbone for pre-training. With minimal adaptations for fine-tuning, our plain-backbone detector can achieve competitive results. Surprisingly, we observe: (i) it is sufficient to build a simple feature pyramid from a single-scale feature map (without the common FPN design) and (ii) it is sufficient to use window attention (without shifting) aided with very few cross-window propagation blocks. With plain ViT backbones pre-trained as Masked Autoencoders (MAE), our detector, named ViTDet, can compete with the previous leading methods that were all based on hierarchical backbones, reaching up to 61.3 AP_box on the COCO dataset using only ImageNet-1K pre-training. We hope our study will draw attention to research on plain-backbone detectors. Code for ViTDet is available in Detectron2.

PaperPDFCodeCode 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 (facebookresearch/detectron2) is linked to this paper; the 4 samples below come from 1 community repository. Syntology harvested code from facebookresearch/detectron2 for 2 other papers.

facebookresearch/detectron2: Syntology's graph links these samples to Focal Loss for Dense Object Detection (arXiv:1708.02002; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 0 unverified) and An Extendable, Efficient and Effective Transformer-based Object Detector (arXiv:2204.07962; that paper's own run record: 2 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; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method.

Syntology 4 code samples harvested from 1 repository linked to this paper: 3 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; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 4 samples from 1 repository, 3 ran (2 with no instrument failure; 1 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 7 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

facebookresearch/detectron2 officialpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Focal Loss for Dense Object Detection (arXiv:1708.02002; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 0 unverified) and An Extendable, Efficient and Effective Transformer-based Object Detector (arXiv:2204.07962; that paper's own run record: 2 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; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
ViTAE-Transformer/ViTDet mentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 3 ran (1 instrument-failed) · 1 unverified report
hula-ai/DAMA mentioned on GitHubpytorchSyntology: not harvested report
kdexd/coco-rem mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Benchmarking Object Detectors with COCO: A New Path Forward (arXiv:2403.18819; that paper's own run record: 1 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; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
vitae-transformer/qformer mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to VSA: Learning Varied-Size Window Attention in Vision Transformers (arXiv:2204.08446; that paper's own run record: 3 ran (of which 3 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) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result) and Vision Transformer with Quadrangle Attention (arXiv:2303.15105; that paper's own run record: 2 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; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
MindCode-4/code-1 mindsporeSyntology: not harvested report
MindCode-4/code-5 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ViTamin: Designing Scalable Vision Models in the Vision-Language Era (arXiv:2404.02132; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
PaddlePaddle/PaddleDetection paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PP-YOLOE: An evolved version of YOLO (arXiv:2203.16250; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
alibaba/EasyCV pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to End-to-End Object Detection with Transformers (arXiv:2005.12872; that paper's own run record: 70 ran (of which 45 constructed an object rather than computing a result; 62 with no instrument failure: 2 honoured, 1 violated, 59 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified), Training data-efficient image transformers & distillation through attention (arXiv:2012.12877; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified), Masked Autoencoders Are Scalable Vision Learners (arXiv:2111.06377; that paper's own run record: 86 ran (of which 40 constructed an object rather than computing a result; 68 with no instrument failure: 8 honoured, 0 violated, 60 with no contract checked; 18 where Syntology's instrument failed) · 51 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
pwc-1/Paper-9 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RandAugment: Practical automated data augmentation with a reduced search space (arXiv:1909.13719; that paper's own run record: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
gitlab.com/birder/birder pytorchSyntology: not harvested 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

4 samples harvested: 3 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; 1 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.

1ran · our draft was wrong
2ran
1unverified

Licence: 1 of the 4 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ViTAE-Transformer/ViTDet. “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.

ViTAE-Transformer/ViTDet community (archive-listed) 4 samples, 3 ran (1 instrument-failed) · 1 unverified
get_num_layer_for_vit in 23 papers mmcv_custom/layer_decay_optimizer_constructor.py ran Apache-2.0 (permissive) · 3ccf2a44831e8069 · report fixture: signature var_name:str/0/str, num_max_layer:int/0/int, layer_sep:NoneType/0/? · returned int · level recorded 2026-09-24
process_checkpoint in 87 papers .dev_scripts/gather_models.py ran Apache-2.0 (permissive) · 138e112e22b0314e · report fixture: signature in_file:str/0/str, out_file:str/0/str · returned str · level recorded 2026-09-25
process_model_info in 21 papers .dev_scripts/convert_test_benchmark_script.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 893e052530d28946 · report fixture: signature model_info:dict/0/?, work_dir:str/0/str · returned dict · level recorded 2026-09-24
ordered_yaml_dump in 33 papers .dev_scripts/gather_models.py unverified Apache-2.0 (permissive) · 8ff99a6bd2ebf598 · report

Tasks

Cross-Domain Few-Shot Object DetectionInstance SegmentationObjectObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Domain Few-Shot Object Detection Artaxor ViTDeT-FT mAP 23.4 #9 of 16 Archive leaderboard report
Cross-Domain Few-Shot Object Detection Clipark1k ViTDeT-FT mAP 25.6 #7 of 10 Archive leaderboard report
Cross-Domain Few-Shot Object Detection DIOR ViTDeT-FT mAP 29.4 #5 of 15 Archive leaderboard report
Cross-Domain Few-Shot Object Detection DeepFish ViTDeT-FT mAP 6.5 #8 of 10 Archive leaderboard report
Cross-Domain Few-Shot Object Detection NEU-DET ViTDeT-FT mAP 15.8 #4 of 10 Archive leaderboard report
Cross-Domain Few-Shot Object Detection UODD ViTDeT-FT mAP 15.8 #8 of 16 Archive leaderboard report
Instance Segmentation COCO minival ViTDet, ViT-H Cascade (multiscale) mask AP 53.1 #10 of 93 Archive leaderboard report
Instance Segmentation COCO minival ViTDet, ViT-H Cascade mask AP 52 #16 of 93 Archive leaderboard report
Instance Segmentation LVIS v1.0 val ViTDet-H mask AP 48.1 #5 of 25 Archive leaderboard report
Instance Segmentation LVIS v1.0 val ViTDet-H mask APr 36.9 #5 of 25 Archive leaderboard report
Instance Segmentation LVIS v1.0 val ViTDet-L mask AP 46.0 #6 of 25 Archive leaderboard report
Instance Segmentation LVIS v1.0 val ViTDet-L mask APr 34.3 #6 of 25 Archive leaderboard report
Object Detection COCO minival ViTDet, ViT-H Cascade (multiscale) box AP 61.3 #18 of 220 Archive leaderboard report
Object Detection COCO minival ViTDet, ViT-H Cascade box AP 60.4 #23 of 220 Archive leaderboard report
Object Detection COCO-O ViTDet (ViT-H) Average mAP 34.3 #10 of 45 Archive leaderboard report
Object Detection COCO-O ViTDet (ViT-H) Effective Robustness 7.89 #43 of 45 Archive leaderboard report
Object Detection LVIS v1.0 val ViTDet-H box AP 53.4 #7 of 15 Archive leaderboard report
Object Detection LVIS v1.0 val ViTDet-L box AP 51.2 #10 of 15 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

1x1 ConvolutionAbsolute Position EncodingsAdamAttentionBPEConvolutionDense ConnectionsDropoutFPNLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVision Transformer

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