Papers › YOLACT++: Better Real-time Instance Segmentation
YOLACT++: Better Real-time Instance Segmentation
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.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="1912.06218")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1912.06218", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1912.06218")
Code
Syntology 43 code samples harvested from 10 repositories linked to this paper: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 6 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 37 samples from 9 repositories, 32 ran (25 with no instrument failure; 7 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:
- mindspore-ai/models, community (archive-listed): harvested for another paper, listed under the repository
Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 37 samples that ran have no recorded date.
36 repositories listed; official and paper-mentioned ones first.
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.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
43 samples harvested: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 5 of the 43 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
0118ac3b2ad5818b · report
fixture: returned Tensor · level recorded 2026-09-25 87523070b15ff05c · report
fixture: signature cfg:BackboneConfig/0/? · returned SimpleBackbone · level recorded 2026-09-25 census: 6 implementations from 9 papers, 1 distinct output on one shared input utils/augmentations.py ran MIT (permissive) ·
4b9f446ea18137b2 · report
fixture: signature img:Tensor/4/float, masks:Tensor/4/int, boxes:Tensor/3/float, labels:Tensor/2/int · returned tuple · level recorded 2026-09-25 2b050648fe0422de · report
fixture: returned Tensor · level recorded 2026-09-25 27dbfe70566c2e97 · report
fixture: returned Tensor · level recorded 2026-09-25 6ec11ee890696819 · report
fixture: signature box_a:ndarray/2/float, box_b:ndarray/1/float · returned ndarray · level recorded 2026-09-24 3e474dde8eaf6a0d · report
fixture: returned Tensor · level recorded 2026-09-24 13675bf1f3f88001 · report
fixture: signature box_a:ndarray/2/float, box_b:ndarray/1/float · returned ndarray · level recorded 2026-09-24 5deaafb309a80f98 · report
fixture: signature x:list/1/int, y:list/1/float, win_size:int/0/int · returned tuple · level recorded 2026-09-24 1111c4bc0e81c97e · report
fixture: signature cfg:dict/0/? · returned SimpleBackbone · level recorded 2026-09-24 749a4203e5655443 · report
fixture: signature cfg:dict/0/?, start_epoch:int/0/int, total_epochs:int/0/int, steps_each_epoch:int/0/int · returned list · level recorded 2026-09-24 19bacdba13e30f6a · report
fixture: signature img:ndarray/3/float, gt_bboxes:ndarray/2/float, gt_label:ndarray/1/int, num_crowds:int/0/int, gt_mask:ndarray/3/float · returned tuple · level recorded 2026-09-24 3bd610e36b49c89d · report
fixture: signature img:ndarray/3/int, gt_bboxes:ndarray/2/float, gt_label:ndarray/1/int, crowd_boxes:ndarray/2/float, gt_mask:ndarray/3/bool · returned tuple · level recorded 2026-09-24 43483f82535041a9 · report
fixture: signature cfg:BackboneConfig/0/? · returned SimpleBackbone · level recorded 2026-09-24 census: 9 implementations from 7 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32 efficientnet/utils.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only ·
2dd5dfa94542911e · report
fixture: signature inputs:Tensor/4/float, p:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22 3dbc17aa8a00e166 · report
fixture: signature key:str/0/str · returned str · level recorded 2026-09-24 826e2e91d6a9ec09 · report
fixture: signature filters:int/0/int, global_params:GlobalParams/0/? · returned int · level recorded 2026-09-22 4d8e794b593d34a0 · report
fixture: signature repeats:int/0/int, global_params:GlobalParams/0/? · returned int · level recorded 2026-09-22 f017532fc389cbfe · report
fixture: signature v:str/0/str · returned bool · level recorded, date not recorded a05a5fcb70df7164 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24 25c7475539e39da4 · report
fixture: signature v:str/0/str · returned bool · level recorded, date not recorded 53f37e71ab4bc260 · report
fixture: signature cfg:BackboneConfig/0/? · returned SimpleBackbone · level recorded 2026-09-24 census: 9 implementations from 7 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32 efficient_utils.py ran; the contract check could not run (RAISES) MIT (permissive) ·
1667bcdf49534735 · report
fixture: signature inputs:Tensor/4/float, p:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22 f35355d03c1b823d · report
fixture: signature dets:Tensor/2/float, thresh:float/0/float · returned Tensor · level recorded 2026-09-24 f15a49337e69e937 · report
fixture: signature filters:int/0/int, global_params:GlobalParams/1/float · returned int · level recorded 2026-09-22 dbc0ca08d119a5a0 · report
fixture: signature repeats:int/0/int, global_params:GlobalParams/1/float · returned int · level recorded 2026-09-22 fd0efb0b6fbe5e15 · report
fixture: signature img:ndarray/3/int, verbose:bool/0/bool · returned tuple · level recorded 2026-09-24 56fe969f55be8b2a · report
fixture: signature img_undistorted:ndarray/3/int, Minv:ndarray/2/float, line_lt:LaneLine/0/?, line_rt:LaneLine/0/?, keep_state:bool/0/bool · returned ndarray · level recorded 2026-09-24 13181bb2b714be6a · report
fixture: signature frame:ndarray/3/int · returned ndarray · level recorded 2026-09-24 10cb133a150ecbaf · report
fixture: signature func:callable/0/? · returned function · level recorded 2026-09-24 b88c68259bd7d3b5 · report
fixture: signature frame:ndarray/3/int, min_values:ndarray/1/int, max_values:ndarray/1/int, verbose:bool/0/bool · returned ndarray · level recorded 2026-09-24 346c2a237c446a04 · report
fixture: signature frame:ndarray/3/int, kernel_size:int/0/int · returned ndarray · level recorded 2026-09-24 18692bc814c6db2d · report
fixture: signature frame:ndarray/3/int, mtx:ndarray/2/float, dist:ndarray/1/float, verbose:bool/0/bool · returned ndarray · level recorded 2026-09-24 891281774f8942bd · report
fixture: signature value:dict/0/? · returned str · level recorded 2026-09-24 609837b2d9cef8e0 · report
fixture: returned SchemaDict · level recorded 2026-09-24 aa4e831671619d64 · report
fixture: signature file_path:str/0/str · returned AttrDict · level recorded 2026-09-24 5120596287afa4cc · report
fixture: signature cls:callable/0/? · returned type · level recorded 2026-09-24 e5e03cc255676dfc · report
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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