Papers › Sparse Instance Activation for Real-Time Instance Segmentation

Sparse Instance Activation for Real-Time Instance Segmentation

24 Mar 2022CVPR 2022 1arXiv:2203.12827archive 2025-07-28

Tianheng Cheng, Xinggang Wang, Shaoyu Chen, Wenqiang Zhang, Qian Zhang, Chang Huang, Zhaoxiang Zhang, Wenyu Liu

In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. Previously, most instance segmentation methods heavily rely on object detection and perform mask prediction based on bounding boxes or dense centers. In contrast, we propose a sparse set of instance activation maps, as a new object representation, to highlight informative regions for each foreground object. Then instance-level features are obtained by aggregating features according to the highlighted regions for recognition and segmentation. Moreover, based on bipartite matching, the instance activation maps can predict objects in a one-to-one style, thus avoiding non-maximum suppression (NMS) in post-processing. Owing to the simple yet effective designs with instance activation maps, SparseInst has extremely fast inference speed and achieves 40 FPS and 37.9 AP on the COCO benchmark, which significantly outperforms the counterparts in terms of speed and accuracy. Code and models are available at https://github.com/hustvl/SparseInst.

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="2203.12827")

Code

Syntology Ran 3 of 11 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 3 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/sparseinst officialmentioned in papermentioned on GitHubpytorchMIT 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

11 samples harvested; 3 ran; 1 honoured the contract we drafted; 8 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 · honoured contract
1ran · our draft was wrong
1ran
8unverified

Licence: 0 of the 11 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 hustvl/sparseinst. “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.

aligned_bilinear hustvl/sparseinst/sparseinst/utils.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 29dbbaafa4be18e1 · report
downsample_conv hustvl/sparseinst/sparseinst/backbones/resnet.py official repository ran MIT (permissive) · eea0376ea397a1c7 · report
get_padding hustvl/sparseinst/sparseinst/backbones/resnet.py official repository ran · honoured contract fingerprinted MIT (permissive) · 9b02c1068795fd5b · report
compute_mask_iou hustvl/sparseinst/sparseinst/loss.py official repository unverified MIT (permissive) · fa8b5ab70cd01b52 · report
create_stem hustvl/sparseinst/sparseinst/backbones/cspnet.py official repository unverified MIT (permissive) · 9419c6922822ae68 · report
dice_loss hustvl/sparseinst/sparseinst/loss.py official repository unverified MIT (permissive) · 2bd30703b07443b2 · report
dice_score hustvl/sparseinst/sparseinst/loss.py official repository unverified MIT (permissive) · a08c2d41f637733e · report
downsample_avg hustvl/sparseinst/sparseinst/backbones/resnet.py official repository unverified MIT (permissive) · bf7559951d6574a4 · report
nested_masks_from_list hustvl/sparseinst/sparseinst/utils.py official repository unverified MIT (permissive) · fc67f83665c787db · report
nested_tensor_from_tensor_list hustvl/sparseinst/sparseinst/utils.py official repository unverified MIT (permissive) · 764b0c92414d2fed · report
rescoring_mask hustvl/sparseinst/sparseinst/sparseinst.py official repository unverified MIT (permissive) · 41822f58ea4816aa · report

Tasks

Instance SegmentationObjectObject DetectionReal-time Instance SegmentationSegmentationSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Real-time Instance Segmentation MSCOCO SparseInst-608 (ResNet-50-vd) AP50 59.2 #7 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO SparseInst-608 (ResNet-50-vd) AP75 40.2 #7 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO SparseInst-608 (ResNet-50-vd) APL 56.9 #7 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO SparseInst-608 (ResNet-50-vd) APM 39.4 #7 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO SparseInst-608 (ResNet-50-vd) APS 15.7 #7 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO SparseInst-608 (ResNet-50-vd) Frame (fps) 40 (2080 Ti) #7 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO SparseInst-608 (ResNet-50-vd) mask AP 37.9 #7 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO SparseInst-448 (ResNet-50-vd) AP50 56.5 #10 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO SparseInst-448 (ResNet-50-vd) AP75 37.7 #10 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO SparseInst-448 (ResNet-50-vd) APL 57.0 #10 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO SparseInst-448 (ResNet-50-vd) APM 37.1 #10 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO SparseInst-448 (ResNet-50-vd) APS 12.3 #10 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO SparseInst-448 (ResNet-50-vd) Frame (fps) 58.5 (2080 Ti) #10 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO SparseInst-448 (ResNet-50-vd) mask AP 35.9 #10 of 22 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

SPEED

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