Papers › YOLACT++: Better Real-time Instance Segmentation

YOLACT++: Better Real-time Instance Segmentation

3 Dec 2019arXiv:1912.06218archive 2025-07-28

Daniel Bolya, Chong Zhou, Fanyi Xiao, Yong Jae Lee

We present a simple, fully-convolutional model for real-time (>30 fps) instance segmentation that achieves competitive results on MS COCO evaluated on a single Titan Xp, which is significantly faster than any previous state-of-the-art approach. Moreover, we obtain this result after training on only one GPU. We accomplish this by breaking instance segmentation into two parallel subtasks: (1) generating a set of prototype masks and (2) predicting per-instance mask coefficients. Then we produce instance masks by linearly combining the prototypes with the mask coefficients. We find that because this process doesn't depend on repooling, this approach produces very high-quality masks and exhibits temporal stability for free. Furthermore, we analyze the emergent behavior of our prototypes and show they learn to localize instances on their own in a translation variant manner, despite being fully-convolutional. We also propose Fast NMS, a drop-in 12 ms faster replacement for standard NMS that only has a marginal performance penalty. Finally, by incorporating deformable convolutions into the backbone network, optimizing the prediction head with better anchor scales and aspect ratios, and adding a novel fast mask re-scoring branch, our YOLACT++ model can achieve 34.1 mAP on MS COCO at 33.5 fps, which is fairly close to the state-of-the-art approaches while still running at real-time.

PaperPDFCodeCode 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="1912.06218")

Code

Syntology Ran 11 of 43 code samples harvested from 10 repositories linked to this paper; 32 have no recorded run. Of those that ran: 2 ran · honoured contract; 2 ran · violated contract; 2 ran · our draft was wrong; 2 ran · fixture could not drive it; 3 ran with no contract checked.

By repository: official repository: 6 samples from 1 repository, 0 ran; community (archive-listed): 37 samples from 9 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.

36 repositories listed; official and paper-mentioned ones first.

dbolya/yolact officialmentioned in papermentioned on GitHubpytorchMIT report
DataXujing/yolact_pytorch mentioned on GitHubpytorchMIT report
DivaniMandi/myCustomDataset_yolact mentioned on GitHubpytorch report
Jittor/InstanceSegmentation-jittor mentioned on GitHubpytorch report
KHKHG/yolact mentioned on GitHubpytorchMIT report
KevinJia1212/yolact_cityscapes_550 mentioned on GitHubpytorchMIT report
Mind23-2/MindCode-92 mentioned on GitHubmindsporeMIT report
SpaceView/Yolact_EfficientNet mentioned on GitHubpytorchMIT report
Yahya1547/FaceMask mentioned on GitHubpytorchMIT report
YeshengSu/Yolact mentioned on GitHubpytorchMIT report
adityarc19/yolact-plus mentioned on GitHubpytorch report
anshkumar/yolact mentioned on GitHubtf report
bihanli/yolactBH mentioned on GitHubpytorchMIT report
divyachandana/yolact mentioned on GitHubpytorchMIT report
eddy4112/Yolact mentioned on GitHubpytorchMIT report
hampen2929/yolact mentioned on GitHubpytorchMIT report
hyunahOh/instance_segmentation mentioned on GitHubpytorchMIT report
jiajunhua/dbolya-yolact mentioned on GitHubpytorchMIT report
kaylode/Clothes-Segmentation mentioned on GitHubpytorchMIT report
kaylode/Trash-Segmentation mentioned on GitHubpytorchMIT report
lasithaya/yolact mentioned on GitHubpytorchMIT report
leenajyotishi/objectdetectionstuff mentioned on GitHubpytorchMIT report
lucasfporto/yolactTest mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-ready report
skritik098/new_yolact mentioned on GitHubpytorchMIT report
skritik098/new_yolact_2 mentioned on GitHubpytorchMIT report
songjmcn/yolact mentioned on GitHubpytorchMIT report
zhaozhongch/yolact_ros mentioned on GitHubpytorchMIT report
zhengzhe97/yolactpaddle mentioned on GitHubpaddleApache-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

43 samples harvested; 11 ran; 2 honoured the contract we drafted; 32 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.

2ran · honoured contract
2ran · violated contract
2ran · our draft was wrong
2ran · fixture could not drive it
3ran
32unverified

Licence: 0 of the 43 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 10 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.

center_size dbolya/yolact/layers/box_utils.py official repository unverified MIT (permissive) · 0118ac3b2ad5818b · report
construct_backbone dbolya/yolact/backbone.py official repository unverified MIT (permissive) · 87523070b15ff05c · report
darknetconvlayer dbolya/yolact/backbone.py official repository unverified MIT (permissive) · 901e174e8a74774c · report
do_nothing dbolya/yolact/utils/augmentations.py official repository unverified MIT (permissive) · 4b9f446ea18137b2 · report
intersect dbolya/yolact/layers/box_utils.py official repository unverified MIT (permissive) · 2b050648fe0422de · report
point_form dbolya/yolact/layers/box_utils.py official repository unverified MIT (permissive) · 27dbfe70566c2e97 · report
drop_connect SpaceView/Yolact_EfficientNet/efficientnet/utils.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · 2dd5dfa94542911e · report
drop_connect kaylode/Clothes-Segmentation/efficient_utils.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · 1667bcdf49534735 · report
dump_value zhengzhe97/yolactpaddle/ppdet/core/workspace.py community (archive-listed) ran Apache-2.0 (permissive) · 891281774f8942bd · report
intersect DataXujing/yolact_pytorch/utils/augmentations.py community (archive-listed) ran fingerprinted MIT (permissive) · 6ec11ee890696819 · report
jaccard_numpy DataXujing/yolact_pytorch/utils/augmentations.py community (archive-listed) ran fingerprinted MIT (permissive) · 13675bf1f3f88001 · report
round_filters SpaceView/Yolact_EfficientNet/efficientnet/utils.py community (archive-listed) ran · honoured contract MIT (permissive) · 826e2e91d6a9ec09 · report
round_filters kaylode/Clothes-Segmentation/efficient_utils.py community (archive-listed) ran · our draft was wrong MIT (permissive) · f15a49337e69e937 · report
round_repeats SpaceView/Yolact_EfficientNet/efficientnet/utils.py community (archive-listed) ran · honoured contract MIT (permissive) · 4d8e794b593d34a0 · report
round_repeats kaylode/Clothes-Segmentation/efficient_utils.py community (archive-listed) ran · our draft was wrong MIT (permissive) · dbc0ca08d119a5a0 · report
str2bool hyunahOh/instance_segmentation/train_hyperopts.py community (archive-listed) ran · violated contract MIT (permissive) · 25c7475539e39da4 · report
str2bool SpaceView/Yolact_EfficientNet/eval_org.py community (archive-listed) ran · violated contract MIT (permissive) · f017532fc389cbfe · report
birdeye skritik098/new_yolact/perspective_utils.py community (archive-listed) unverified MIT (permissive) · fd0efb0b6fbe5e15 · report
calibrate_camera skritik098/new_yolact/calibration_utils.py community (archive-listed) unverified MIT (permissive) · 96082ce9fcb1d9b2 · report
construct_backbone Mind23-2/MindCode-92/src/yolact/layers/backbone_dcnV2.py community (archive-listed) unverified MIT (permissive) · 1111c4bc0e81c97e · report
construct_backbone SpaceView/Yolact_EfficientNet/backbone.py community (archive-listed) unverified MIT (permissive) · 43483f82535041a9 · report
construct_backbone kaylode/Clothes-Segmentation/backbone.py community (archive-listed) unverified MIT (permissive) · 53f37e71ab4bc260 · report
dict_merge zhengzhe97/yolactpaddle/ppdet/core/workspace.py community (archive-listed) unverified Apache-2.0 (permissive) · e5e03cc255676dfc · report
draw_back_onto_the_road skritik098/new_yolact/line_utils.py community (archive-listed) unverified MIT (permissive) · 56fe969f55be8b2a · report
dynamic_lr Mind23-2/MindCode-92/src/lr_schedule.py community (archive-listed) unverified MIT (permissive) · 749a4203e5655443 · report
extract_schema zhengzhe97/yolactpaddle/ppdet/core/config/schema.py community (archive-listed) unverified Apache-2.0 (permissive) · 609837b2d9cef8e0 · report
filter KevinJia1212/yolact_cityscapes_550/log2pic.py community (archive-listed) unverified MIT (permissive) · 5deaafb309a80f98 · report
get_binary_from_equalized_grayscale skritik098/new_yolact/binarization_utils.py community (archive-listed) unverified MIT (permissive) · 13181bb2b714be6a · report
get_coco_cat SpaceView/Yolact_EfficientNet/eval_org.py community (archive-listed) unverified MIT (permissive) · 77562d48931fca67 · report
gradinator hyunahOh/instance_segmentation/train_hyperopts.py community (archive-listed) unverified MIT (permissive) · a05a5fcb70df7164 · report
intersect DataXujing/yolact_pytorch/layers/box_utils.py community (archive-listed) unverified MIT (permissive) · 3e474dde8eaf6a0d · report
key_transformation SpaceView/Yolact_EfficientNet/match_and_rename_efficientnet_dict_keys.py community (archive-listed) unverified MIT (permissive) · 3dbc17aa8a00e166 · report
lazy_calibration skritik098/new_yolact/calibration_utils.py community (archive-listed) unverified MIT (permissive) · 10cb133a150ecbaf · report
load_config zhengzhe97/yolactpaddle/ppdet/core/workspace.py community (archive-listed) unverified Apache-2.0 (permissive) · aa4e831671619d64 · report
nms kaylode/Clothes-Segmentation/efficientdet/model.py community (archive-listed) unverified MIT (permissive) · f35355d03c1b823d · report
prepare_data kaylode/Clothes-Segmentation/loss_compute.py community (archive-listed) unverified MIT (permissive) · 4ba7706686242902 · report
serializable zhengzhe97/yolactpaddle/ppdet/core/config/yaml_helpers.py community (archive-listed) unverified Apache-2.0 (permissive) · 5120596287afa4cc · report
summarize bihanli/yolactBH/run_coco_eval.py community (archive-listed) unverified MIT (permissive) · 2f9a6d5ca1bc906a · report
thresh_frame_in_HSV skritik098/new_yolact/binarization_utils.py community (archive-listed) unverified MIT (permissive) · b88c68259bd7d3b5 · report
thresh_frame_sobel skritik098/new_yolact/binarization_utils.py community (archive-listed) unverified MIT (permissive) · 346c2a237c446a04 · report
toPercentCoords Mind23-2/MindCode-92/src/dataset.py community (archive-listed) unverified MIT (permissive) · 19bacdba13e30f6a · report
transpose_column Mind23-2/MindCode-92/src/dataset.py community (archive-listed) unverified MIT (permissive) · 3bd610e36b49c89d · report
undistort skritik098/new_yolact/calibration_utils.py community (archive-listed) unverified MIT (permissive) · 18692bc814c6db2d · report

Tasks

Instance SegmentationReal-time Instance SegmentationSegmentationSemantic Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Real-time Instance Segmentation MSCOCO YOLACT-550++ (ResNet-101-FPN) AP50 53.8 #14 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT-550++ (ResNet-101-FPN) AP75 36.9 #14 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT-550++ (ResNet-101-FPN) APL 55.1 #14 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT-550++ (ResNet-101-FPN) APM 36.8 #14 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT-550++ (ResNet-101-FPN) APS 11.9 #14 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT-550++ (ResNet-101-FPN) Frame (fps) 27.3 (Titan Xp) #14 of 22 Archive leaderboard report
Real-time Instance Segmentation MSCOCO YOLACT-550++ (ResNet-101-FPN) mask AP 34.6 #14 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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