Papers › Instances as Queries

Instances as Queries

5 May 2021ICCV 2021 10arXiv:2105.01928archive 2025-07-28

Yuxin Fang, Shusheng Yang, Xinggang Wang, Yu Li, Chen Fang, Ying Shan, Bin Feng, Wenyu Liu

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}.

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="2105.01928")

Code

Syntology Ran 1 of 3 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: community (archive-listed): 3 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.

hustvl/QueryInst officialmentioned in papermentioned on GitHubpytorchMIT report
Bo396543018/picodet_repro mentioned on GitHubpytorchApache-2.0 report
flyfly666/mmdetection2.18.1 mentioned on GitHubpytorchApache-2.0 report
open-mmlab/mmdetection mentioned on GitHubpytorchApache-2.0 report
sty16/cell_mmdetection mentioned on GitHubpytorchApache-2.0 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

3 samples harvested; 1 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
2unverified

Licence: 0 of the 3 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 sty16/cell_mmdetection. “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 sty16/cell_mmdetection/.dev_scripts/convert_test_benchmark_script.py community (archive-listed) ran Apache-2.0 (permissive) · 893e052530d28946 · report
ordered_yaml_dump sty16/cell_mmdetection/.dev_scripts/gather_models.py community (archive-listed) unverified Apache-2.0 (permissive) · 8ff99a6bd2ebf598 · report
process_checkpoint sty16/cell_mmdetection/.dev_scripts/gather_models.py community (archive-listed) unverified Apache-2.0 (permissive) · 138e112e22b0314e · report

Tasks

Instance SegmentationObjectObject DetectionSegmentationVideo Instance Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO minival QueryInst (single scale) AP50 74.0 #30 of 93 Archive leaderboard report
Instance Segmentation COCO minival QueryInst (single scale) AP75 53.9 #30 of 93 Archive leaderboard report
Instance Segmentation COCO minival QueryInst (single scale) APL 68.3 #30 of 93 Archive leaderboard report
Instance Segmentation COCO minival QueryInst (single scale) APM 52.6 #30 of 93 Archive leaderboard report
Instance Segmentation COCO minival QueryInst (single scale) APS 30.8 #30 of 93 Archive leaderboard report
Instance Segmentation COCO minival QueryInst (single scale) mask AP 48.9 #30 of 93 Archive leaderboard report
Instance Segmentation COCO test-dev QueryInst (single scale) AP50 74.2 #24 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev QueryInst (single scale) AP75 53.8 #24 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev QueryInst (single scale) APL 63.2 #24 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev QueryInst (single scale) APM 51.8 #24 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev QueryInst (single scale) APS 31.5 #24 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev QueryInst (single scale) mask AP 49.1 #24 of 112 Archive leaderboard report
Object Detection COCO minival QueryInst (single scale) AP50 75.8 #45 of 220 Archive leaderboard report
Object Detection COCO minival QueryInst (single scale) AP75 61.7 #45 of 220 Archive leaderboard report
Object Detection COCO minival QueryInst (single scale) APL 71.5 #45 of 220 Archive leaderboard report
Object Detection COCO minival QueryInst (single scale) APM 59.8 #45 of 220 Archive leaderboard report
Object Detection COCO minival QueryInst (single scale) APS 40.2 #45 of 220 Archive leaderboard report
Object Detection COCO minival QueryInst (single scale) box AP 56.1 #45 of 220 Archive leaderboard report
Object Detection COCO test-dev QueryInst (single-scale) AP50 75.9 #44 of 225 Archive leaderboard report
Object Detection COCO test-dev QueryInst (single-scale) AP75 61.9 #44 of 225 Archive leaderboard report
Object Detection COCO test-dev QueryInst (single-scale) APL 70.3 #44 of 225 Archive leaderboard report
Object Detection COCO test-dev QueryInst (single-scale) APM 58.9 #44 of 225 Archive leaderboard report
Object Detection COCO test-dev QueryInst (single-scale) APS 37.4 #44 of 225 Archive leaderboard report
Object Detection COCO test-dev QueryInst (single-scale) Hardware Burden 17G #44 of 225 Archive leaderboard report
Object Detection COCO test-dev QueryInst (single-scale) box mAP 56.1 #44 of 225 Archive leaderboard report
Object Detection COCO-O QueryInst (Swin-L) Average mAP 33.2 #13 of 45 Archive leaderboard report
Object Detection COCO-O QueryInst (Swin-L) Effective Robustness 8.26 #13 of 45 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

Absolute Position EncodingsAttentionCascade Mask R-CNNCascade R-CNNConvolutionDense ConnectionsDetrDynamicConvFaster R-CNNFeedforward NetworkLayer NormalizationLinear LayerMask R-CNNMulti-Head AttentionPosition-Wise Feed-Forward LayerRPNRoIAlignRoIPoolSoftmaxSparse R-CNNTransformerVision 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