{"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/queryinst-parallelly-supervised-mask-query","title":"Instances as Queries","arxiv_id":"2105.01928","date":"2021-05-05","proceeding":"ICCV 2021 10","authors":["Yuxin Fang","Shusheng Yang","Xinggang Wang","Yu Li","Chen Fang","Ying Shan","Bin Feng","Wenyu Liu"],"abstract":"Recently, query based object detection frameworks achieve comparable performance with previous state-of-the-art object detectors. However, how to fully leverage such frameworks to perform instance segmentation remains an open problem. In this paper, we present QueryInst (Instances as Queries), a query based instance segmentation method driven by parallel supervision on dynamic mask heads. The key insight of QueryInst is to leverage the intrinsic one-to-one correspondence in object queries across different stages, as well as one-to-one correspondence between mask RoI features and object queries in the same stage. This approach eliminates the explicit multi-stage mask head connection and the proposal distribution inconsistency issues inherent in non-query based multi-stage instance segmentation methods. We conduct extensive experiments on three challenging benchmarks, i.e., COCO, CityScapes, and YouTube-VIS to evaluate the effectiveness of QueryInst in instance segmentation and video instance segmentation (VIS) task. Specifically, using ResNet-101-FPN backbone, QueryInst obtains 48.1 box AP and 42.8 mask AP on COCO test-dev, which is 2 points higher than HTC in terms of both box AP and mask AP, while runs 2.4 times faster. For video instance segmentation, QueryInst achieves the best performance among all online VIS approaches and strikes a decent speed-accuracy trade-off. Code is available at \\url{https://github.com/hustvl/QueryInst}.","url_abs":"https://arxiv.org/abs/2105.01928v3","url_pdf":"https://arxiv.org/pdf/2105.01928v3.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":"queryinst-parallelly-supervised-mask-query","repo_url":"https://github.com/hustvl/QueryInst","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"queryinst-parallelly-supervised-mask-query","repo_url":"https://github.com/Bo396543018/picodet_repro","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"queryinst-parallelly-supervised-mask-query","repo_url":"https://github.com/flyfly666/mmdetection2.18.1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"queryinst-parallelly-supervised-mask-query","repo_url":"https://github.com/open-mmlab/mmdetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"queryinst-parallelly-supervised-mask-query","repo_url":"https://github.com/sty16/cell_mmdetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"video-instance-segmentation","task_name":"Video Instance Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"cascade-mask-r-cnn","method_name":"Cascade Mask R-CNN"},{"method_slug":"cascade-r-cnn","method_name":"Cascade R-CNN"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"detr","method_name":"Detr"},{"method_slug":"dynamicconv","method_name":"DynamicConv"},{"method_slug":"faster-r-cnn","method_name":"Faster R-CNN"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"roipool","method_name":"RoIPool"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"sparse-r-cnn","method_name":"Sparse R-CNN"},{"method_slug":"transformer","method_name":"Transformer"},{"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":"QueryInst (single scale)","rank_in_archive_order":30,"of":93,"metrics":{"AP50":"74.0","AP75":"53.9","APL":"68.3","APM":"52.6","APS":"30.8","mask AP":"48.9"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"QueryInst (single scale)","rank_in_archive_order":24,"of":112,"metrics":{"AP50":"74.2","AP75":"53.8","APL":"63.2","APM":"51.8","APS":"31.5","mask AP":"49.1"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"QueryInst (single scale)","rank_in_archive_order":45,"of":220,"metrics":{"AP50":"75.8","AP75":"61.7","APL":"71.5","APM":"59.8","APS":"40.2","box AP":"56.1"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"QueryInst (single-scale)","rank_in_archive_order":44,"of":225,"metrics":{"AP50":"75.9","AP75":"61.9","APL":"70.3","APM":"58.9","APS":"37.4","Hardware Burden":"17G","box mAP":"56.1"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-o","task":"Object Detection","dataset":"COCO-O","model":"QueryInst\n(Swin-L)","rank_in_archive_order":13,"of":45,"metrics":{"Average mAP":"33.2","Effective Robustness":"8.26"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.01928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.01928"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/Bo396543018/picodet_repro","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmdetection","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/flyfly666/mmdetection2.18.1","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/hustvl/QueryInst","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sty16/cell_mmdetection","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"listed":{"samples":3,"ran":1,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"893e052530d28946","entry":"process_model_info","repo":"sty16/cell_mmdetection","repo_kind":"listed","path":".dev_scripts/convert_test_benchmark_script.py","file_url":"https://github.com/sty16/cell_mmdetection/blob/HEAD/.dev_scripts/convert_test_benchmark_script.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":true,"mcp_get_code":{"code_sha256":"893e052530d28946"}},{"code_sha256_prefix":"8ff99a6bd2ebf598","entry":"ordered_yaml_dump","repo":"sty16/cell_mmdetection","repo_kind":"listed","path":".dev_scripts/gather_models.py","file_url":"https://github.com/sty16/cell_mmdetection/blob/HEAD/.dev_scripts/gather_models.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":true,"mcp_get_code":{"code_sha256":"8ff99a6bd2ebf598"}},{"code_sha256_prefix":"138e112e22b0314e","entry":"process_checkpoint","repo":"sty16/cell_mmdetection","repo_kind":"listed","path":".dev_scripts/gather_models.py","file_url":"https://github.com/sty16/cell_mmdetection/blob/HEAD/.dev_scripts/gather_models.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":true,"mcp_get_code":{"code_sha256":"138e112e22b0314e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}