Papers › Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation

Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation

6 Jun 2022CVPR 2023 1arXiv:2206.02777archive 2025-07-28

Feng Li, Hao Zhang, Huaizhe xu, Shilong Liu, Lei Zhang, Lionel M. Ni, Heung-Yeung Shum

In this paper we present Mask DINO, a unified object detection and segmentation framework. Mask DINO extends DINO (DETR with Improved Denoising Anchor Boxes) by adding a mask prediction branch which supports all image segmentation tasks (instance, panoptic, and semantic). It makes use of the query embeddings from DINO to dot-product a high-resolution pixel embedding map to predict a set of binary masks. Some key components in DINO are extended for segmentation through a shared architecture and training process. Mask DINO is simple, efficient, and scalable, and it can benefit from joint large-scale detection and segmentation datasets. Our experiments show that Mask DINO significantly outperforms all existing specialized segmentation methods, both on a ResNet-50 backbone and a pre-trained model with SwinL backbone. Notably, Mask DINO establishes the best results to date on instance segmentation (54.5 AP on COCO), panoptic segmentation (59.4 PQ on COCO), and semantic segmentation (60.8 mIoU on ADE20K) among models under one billion parameters. Code is available at \url{https://github.com/IDEACVR/MaskDINO}.

PaperPDFConference PDFCodeCode 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="2206.02777")

Code

Syntology Ran 11 of 13 code samples harvested from 2 repositories linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · violated contract; 3 ran · our draft was wrong; 5 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: community (archive-listed): 13 samples from 2 repositories, 11 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

idea-research/maskdino officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
Expedit-LargeScale-Vision-Transformer/Expedit-DINO mentioned on GitHubpytorchApache-2.0 report
IDEA-opensource/DAB-DETR mentioned on GitHubpytorch report
IDEA-opensource/DN-DETR mentioned on GitHubpytorchApache-2.0 report
IDEACVR/DINO mentioned on GitHubpytorchApache-2.0 report
idea-research/dab-detr mentioned on GitHubpytorchApache-2.0 report
idea-research/dn-detr mentioned on GitHubpytorch report
isbrycee/gem mentioned on GitHubpytorch report
isbrycee/gem-glass-segmentor mentioned on GitHubpytorch 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

13 samples harvested; 11 ran; 0 honoured the contract we drafted; 2 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 · violated contract
3ran · our draft was wrong
5ran · fixture could not drive it
2ran
2unverified

Licence: 13 of the 13 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

window_partition IDEA-opensource/DN-DETR/models/DN_DAB_DETR/swin_transformer.py community (archive-listed) ran · fixture could not drive it fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 144d10b49baeb8a6 · report
dice_loss IDEA-opensource/DN-DETR/models/DN_DAB_DETR/segmentation.py community (archive-listed) ran · violated contract fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · ac8fe530cdad4d8c · report
dn_post_process IDEA-opensource/DN-DETR/models/DN_DAB_DETR/dn_components.py community (archive-listed) ran · fixture could not drive it Apache-2.0 recorded; this copy not marked cleared · pointer only · 9db6a2fdc3039d38 · report
dn_post_process IDEACVR/DINO/models/dino/dn_components.py community (archive-listed) ran Apache-2.0 recorded; this copy not marked cleared · pointer only · dc279ea790da466f · report
gen_encoder_output_proposals IDEACVR/DINO/models/dino/utils.py community (archive-listed) ran Apache-2.0 recorded; this copy not marked cleared · pointer only · e3b2768e6a9c1cb5 · report
gen_sineembed_for_position IDEACVR/DINO/models/dino/utils.py community (archive-listed) ran · fixture could not drive it fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 4c82654ae6131ecc · report
gen_sineembed_for_position IDEA-opensource/DN-DETR/models/DN_DAB_DETR/transformer.py community (archive-listed) ran · fixture could not drive it fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 1455637eb5d8b21d · report
sigmoid_focal_loss IDEA-opensource/DN-DETR/models/DN_DAB_DETR/DABDETR.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 5c0711aada67957e · report
window_partition IDEACVR/DINO/models/dino/swin_transformer.py community (archive-listed) ran · fixture could not drive it fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · f9fd6241d935f07b · report
window_reverse IDEA-opensource/DN-DETR/models/DN_DAB_DETR/swin_transformer.py community (archive-listed) ran · our draft was wrong Apache-2.0 recorded; this copy not marked cleared · pointer only · 61bf152e6a42a184 · report
window_reverse IDEACVR/DINO/models/dino/swin_transformer.py community (archive-listed) ran · our draft was wrong Apache-2.0 recorded; this copy not marked cleared · pointer only · fb32094c6dbece71 · report
build_swin_transformer IDEA-opensource/DN-DETR/models/DN_DAB_DETR/swin_transformer.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · ddbe621fd9f33a35 · report
multi_head_attention_forward IDEA-opensource/DN-DETR/models/DN_DAB_DETR/attention.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · a82091666b9db8cf · report

Tasks

Image SegmentationInstance SegmentationObject DetectionPanoptic SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO minival MasK DINO (SwinL, multi-scale) mask AP 54.5 #6 of 93 Archive leaderboard report
Instance Segmentation COCO minival Mask DINO (SwinL) mask AP 52.6 #12 of 93 Archive leaderboard report
Instance Segmentation COCO test-dev MasK DINO (SwinL, multi-scale) mask AP 54.7 #7 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev Mask DINO (SwinL, single -scale) mask AP 52.8 #14 of 112 Archive leaderboard report
Panoptic Segmentation COCO minival MasK DINO (SwinL,single-scale) AP 50.9 #5 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival MasK DINO (SwinL,single-scale) PQ 59.4 #5 of 31 Archive leaderboard report
Panoptic Segmentation COCO test-dev Mask DINO (single scale) PQ 59.5 #1 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev Mask DINO (single scale) PQst - #1 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev Mask DINO (single scale) PQth - #1 of 38 Archive leaderboard report
Semantic Segmentation ADE20K MasK DINO (SwinL, multi-scale) Params (M) 223 #11 of 235 Archive leaderboard report
Semantic Segmentation ADE20K MasK DINO (SwinL, multi-scale) Validation mIoU 60.8 #11 of 235 Archive leaderboard report
Semantic Segmentation ADE20K val MaskDINO-SwinL mIoU 60.8 #5 of 95 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

AttentionDense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision 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