{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mask-dino-towards-a-unified-transformer-based-1","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","arxiv_id":"2206.02777","date":"2022-06-06","proceeding":"CVPR 2023 1","authors":["Feng Li","Hao Zhang","Huaizhe xu","Shilong Liu","Lei Zhang","Lionel M. Ni","Heung-Yeung Shum"],"abstract":"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}.","url_abs":"https://arxiv.org/abs/2206.02777v3","url_pdf":"https://arxiv.org/pdf/2206.02777v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mask-dino-towards-a-unified-transformer-based-1","repo_url":"https://github.com/idea-research/maskdino","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"mask-dino-towards-a-unified-transformer-based-1","repo_url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-DINO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"mask-dino-towards-a-unified-transformer-based-1","repo_url":"https://github.com/IDEA-opensource/DAB-DETR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mask-dino-towards-a-unified-transformer-based-1","repo_url":"https://github.com/IDEA-opensource/DN-DETR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"mask-dino-towards-a-unified-transformer-based-1","repo_url":"https://github.com/IDEACVR/DINO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"mask-dino-towards-a-unified-transformer-based-1","repo_url":"https://github.com/idea-research/dab-detr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"mask-dino-towards-a-unified-transformer-based-1","repo_url":"https://github.com/idea-research/dn-detr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mask-dino-towards-a-unified-transformer-based-1","repo_url":"https://github.com/isbrycee/gem","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"mask-dino-towards-a-unified-transformer-based-1","repo_url":"https://github.com/isbrycee/gem-glass-segmentor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"mask-dino-towards-a-unified-transformer-based-1","repo_url":"https://github.com/PaddlePaddle/PaddleDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/instance-segmentation-on-coco-minival","task":"Instance Segmentation","dataset":"COCO minival","model":"MasK DINO (SwinL, multi-scale)","rank_in_archive_order":6,"of":93,"metrics":{"mask AP":"54.5"},"uses_additional_data":true},{"leaderboard":"/sota/instance-segmentation-on-coco-minival","task":"Instance Segmentation","dataset":"COCO minival","model":"Mask DINO (SwinL)","rank_in_archive_order":12,"of":93,"metrics":{"mask AP":"52.6"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"MasK DINO (SwinL, multi-scale)","rank_in_archive_order":7,"of":112,"metrics":{"mask AP":"54.7"},"uses_additional_data":true},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"Mask DINO (SwinL, single -scale)","rank_in_archive_order":14,"of":112,"metrics":{"mask AP":"52.8"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-coco-minival","task":"Panoptic Segmentation","dataset":"COCO minival","model":"MasK DINO (SwinL,single-scale)","rank_in_archive_order":5,"of":31,"metrics":{"AP":"50.9","PQ":"59.4"},"uses_additional_data":true},{"leaderboard":"/sota/panoptic-segmentation-on-coco-test-dev","task":"Panoptic Segmentation","dataset":"COCO test-dev","model":"Mask DINO (single scale)","rank_in_archive_order":1,"of":38,"metrics":{"PQ":"59.5","PQst":"-","PQth":"-"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"MasK DINO (SwinL, multi-scale)","rank_in_archive_order":11,"of":235,"metrics":{"Params (M)":"223","Validation mIoU":"60.8"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-ade20k-val","task":"Semantic Segmentation","dataset":"ADE20K val","model":"MaskDINO-SwinL","rank_in_archive_order":5,"of":95,"metrics":{"mIoU":"60.8"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2206.02777","atlas_url":"https://app.syntology.ai/?focus=2206.02777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.02777"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/idea-research/dab-detr","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/isbrycee/gem","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleDetection","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IDEA-opensource/DAB-DETR","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IDEACVR/DINO","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/idea-research/dn-detr","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/idea-research/maskdino","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/isbrycee/gem-glass-segmentor","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-DINO","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IDEA-opensource/DN-DETR","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":5,"ran_violates":1,"ran":2,"ran_draft_wrong":3,"unverified":2},"by_repo_kind":{"listed":{"samples":13,"ran":11,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":13,"samples":[{"code_sha256_prefix":"144d10b49baeb8a6","entry":"window_partition","repo":"IDEA-opensource/DN-DETR","repo_kind":"listed","path":"models/DN_DAB_DETR/swin_transformer.py","file_url":"https://github.com/IDEA-opensource/DN-DETR/blob/HEAD/models/DN_DAB_DETR/swin_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"144d10b49baeb8a6"}},{"code_sha256_prefix":"ac8fe530cdad4d8c","entry":"dice_loss","repo":"IDEA-opensource/DN-DETR","repo_kind":"listed","path":"models/DN_DAB_DETR/segmentation.py","file_url":"https://github.com/IDEA-opensource/DN-DETR/blob/HEAD/models/DN_DAB_DETR/segmentation.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"ac8fe530cdad4d8c"}},{"code_sha256_prefix":"9db6a2fdc3039d38","entry":"dn_post_process","repo":"IDEA-opensource/DN-DETR","repo_kind":"listed","path":"models/DN_DAB_DETR/dn_components.py","file_url":"https://github.com/IDEA-opensource/DN-DETR/blob/HEAD/models/DN_DAB_DETR/dn_components.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"9db6a2fdc3039d38"}},{"code_sha256_prefix":"dc279ea790da466f","entry":"dn_post_process","repo":"IDEACVR/DINO","repo_kind":"listed","path":"models/dino/dn_components.py","file_url":"https://github.com/IDEACVR/DINO/blob/HEAD/models/dino/dn_components.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"dc279ea790da466f"}},{"code_sha256_prefix":"e3b2768e6a9c1cb5","entry":"gen_encoder_output_proposals","repo":"IDEACVR/DINO","repo_kind":"listed","path":"models/dino/utils.py","file_url":"https://github.com/IDEACVR/DINO/blob/HEAD/models/dino/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e3b2768e6a9c1cb5"}},{"code_sha256_prefix":"4c82654ae6131ecc","entry":"gen_sineembed_for_position","repo":"IDEACVR/DINO","repo_kind":"listed","path":"models/dino/utils.py","file_url":"https://github.com/IDEACVR/DINO/blob/HEAD/models/dino/utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4c82654ae6131ecc"}},{"code_sha256_prefix":"1455637eb5d8b21d","entry":"gen_sineembed_for_position","repo":"IDEA-opensource/DN-DETR","repo_kind":"listed","path":"models/DN_DAB_DETR/transformer.py","file_url":"https://github.com/IDEA-opensource/DN-DETR/blob/HEAD/models/DN_DAB_DETR/transformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"1455637eb5d8b21d"}},{"code_sha256_prefix":"5c0711aada67957e","entry":"sigmoid_focal_loss","repo":"IDEA-opensource/DN-DETR","repo_kind":"listed","path":"models/DN_DAB_DETR/DABDETR.py","file_url":"https://github.com/IDEA-opensource/DN-DETR/blob/HEAD/models/DN_DAB_DETR/DABDETR.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"code_sha256_prefix":"f9fd6241d935f07b","entry":"window_partition","repo":"IDEACVR/DINO","repo_kind":"listed","path":"models/dino/swin_transformer.py","file_url":"https://github.com/IDEACVR/DINO/blob/HEAD/models/dino/swin_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f9fd6241d935f07b"}},{"code_sha256_prefix":"61bf152e6a42a184","entry":"window_reverse","repo":"IDEA-opensource/DN-DETR","repo_kind":"listed","path":"models/DN_DAB_DETR/swin_transformer.py","file_url":"https://github.com/IDEA-opensource/DN-DETR/blob/HEAD/models/DN_DAB_DETR/swin_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"61bf152e6a42a184"}},{"code_sha256_prefix":"fb32094c6dbece71","entry":"window_reverse","repo":"IDEACVR/DINO","repo_kind":"listed","path":"models/dino/swin_transformer.py","file_url":"https://github.com/IDEACVR/DINO/blob/HEAD/models/dino/swin_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"fb32094c6dbece71"}},{"code_sha256_prefix":"ddbe621fd9f33a35","entry":"build_swin_transformer","repo":"IDEA-opensource/DN-DETR","repo_kind":"listed","path":"models/DN_DAB_DETR/swin_transformer.py","file_url":"https://github.com/IDEA-opensource/DN-DETR/blob/HEAD/models/DN_DAB_DETR/swin_transformer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"ddbe621fd9f33a35"}},{"code_sha256_prefix":"a82091666b9db8cf","entry":"multi_head_attention_forward","repo":"IDEA-opensource/DN-DETR","repo_kind":"listed","path":"models/DN_DAB_DETR/attention.py","file_url":"https://github.com/IDEA-opensource/DN-DETR/blob/HEAD/models/DN_DAB_DETR/attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"a82091666b9db8cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}