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 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="2203.16527")

Code

Syntology Ran 1 of 4 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: community (archive-listed): 4 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ViTAE-Transformer/ViTDet mentioned on GitHubpytorchApache-2.0 report
hula-ai/DAMA mentioned on GitHubpytorch report
kdexd/coco-rem mentioned on GitHubpytorch report
vitae-transformer/qformer mentioned on GitHubpytorch report
pwc-1/Paper-9 mindspore 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

4 samples harvested; 1 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran
3unverified

Licence: 0 of the 4 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 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. “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.

process_model_info ViTAE-Transformer/ViTDet/.dev_scripts/convert_test_benchmark_script.py community (archive-listed) ran Apache-2.0 (permissive) · 893e052530d28946 · report
get_num_layer_for_vit ViTAE-Transformer/ViTDet/mmcv_custom/layer_decay_optimizer_constructor.py community (archive-listed) unverified Apache-2.0 (permissive) · 3ccf2a44831e8069 · report
ordered_yaml_dump ViTAE-Transformer/ViTDet/.dev_scripts/gather_models.py community (archive-listed) unverified Apache-2.0 (permissive) · 8ff99a6bd2ebf598 · report
process_checkpoint ViTAE-Transformer/ViTDet/.dev_scripts/gather_models.py community (archive-listed) unverified Apache-2.0 (permissive) · 138e112e22b0314e · 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