Papers › MSeg: A Composite Dataset for Multi-domain Semantic Segmentation
MSeg: A Composite Dataset for Multi-domain Semantic Segmentation
John Lambert, Zhuang Liu, Ozan Sener, James Hays, Vladlen Koltun
We present MSeg, a composite dataset that unifies semantic segmentation datasets from different domains. A naive merge of the constituent datasets yields poor performance due to inconsistent taxonomies and annotation practices. We reconcile the taxonomies and bring the pixel-level annotations into alignment by relabeling more than 220,000 object masks in more than 80,000 images, requiring more than 1.34 years of collective annotator effort. The resulting composite dataset enables training a single semantic segmentation model that functions effectively across domains and generalizes to datasets that were not seen during training. We adopt zero-shot cross-dataset transfer as a benchmark to systematically evaluate a model's robustness and show that MSeg training yields substantially more robust models in comparison to training on individual datasets or naive mixing of datasets without the presented contributions. A model trained on MSeg ranks first on the WildDash-v1 leaderboard for robust semantic segmentation, with no exposure to WildDash data during training. We evaluate our models in the 2020 Robust Vision Challenge (RVC) as an extreme generalization experiment. MSeg training sets include only three of the seven datasets in the RVC; more importantly, the evaluation taxonomy of RVC is different and more detailed. Surprisingly, our model shows competitive performance and ranks second. To evaluate how close we are to the grand aim of robust, efficient, and complete scene understanding, we go beyond semantic segmentation by training instance segmentation and panoptic segmentation models using our dataset. Moreover, we also evaluate various engineering design decisions and metrics, including resolution and computational efficiency. Although our models are far from this grand aim, our comprehensive evaluation is crucial for progress. We share all the models and code with the community.
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="2112.13762")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2112.13762", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2112.13762")
Code
Syntology 16 code samples harvested from 2 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.
By repository: official repository: 13 samples from 1 repository, 11 ran (10 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 3 samples from 1 repository, 3 ran (0 with no instrument failure; 3 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.
Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 14 samples that ran has no recorded date.
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
16 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 4 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 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 2 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.
fac5364e2f53c6db · report
fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded 1934d9a8c4ffcd55 · report
fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-24 2f5a2c01a9a77336 · report
fixture: signature target_img:ndarray/2/int, to_universal_transform:callable/0/? · returned ndarray · level recorded 2026-09-24 41d449ba30de8f98 · report
fixture: signature h:int/0/int, w:int/0/int, crop_sz:int/0/int · returned int · level recorded 2026-09-24 40602ff1d1820790 · report
fixture: signature pred_rel:ndarray/2/int, target_img:ndarray/2/int, target_img_relabeled:ndarray/2/int, orig_to_u_transform:callable/0/?, relabeled_to_u_transform:callable/0/?, ignore_idx:int/0/int, verbose:bool/0/bool · returned tuple · level recorded 2026-09-24 a4e6c6b440fcad66 · report
fixture: signature pred:ndarray/2/int, target:ndarray/2/int · returned float64 · level recorded 2026-09-24 1101e190c222d8ec · report
fixture: signature img_fpath:str/0/str · returned ndarray · level recorded 2026-09-24 fd92a32f74219b0a · report
fixture: signature image:ndarray/3/int, crop_h:int/0/int, crop_w:int/0/int, mean:tuple/1/float · returned tuple · level recorded 2026-09-24 d58d1438c5b1c419 · report
fixture: signature batch:Tensor/4/float, crop_h:int/0/int, crop_w:int/0/int, mean:float/0/float, std:float/0/float · returned tuple · level recorded 2026-09-24 6ace685db42a1fe2 · report
fixture: signature image:ndarray/3/int, base_size:int/0/int, scale:float/0/float · returned ndarray · level recorded 2026-09-24 ac842f97bea3acce · report
fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-24 0bde1125893e0d96 · report
90a3231eeed46b30 · report
fixture: signature entry:str/0/str · returned list · level recorded 2026-09-22 1dbbfb8d6f7cad26 · report
fixture: signature test_entry:str/0/str · returned str · level recorded 2026-09-22 5dcde850240a1d55 · report
fixture: signature uentry:str/0/str · returned str · level recorded 2026-09-22 Tasks
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Semantic Segmentation | ScanNetV2 | MSeg1080_RVC | Mean IoU | 48.5% | #8 of 12 | 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.
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