Papers › CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation
Qihang Yu, Huiyu Wang, Dahun Kim, Siyuan Qiao, Maxwell Collins, Yukun Zhu, Hartwig Adam, Alan Yuille, Liang-Chieh Chen
We propose Clustering Mask Transformer (CMT-DeepLab), a transformer-based framework for panoptic segmentation designed around clustering. It rethinks the existing transformer architectures used in segmentation and detection; CMT-DeepLab considers the object queries as cluster centers, which fill the role of grouping the pixels when applied to segmentation. The clustering is computed with an alternating procedure, by first assigning pixels to the clusters by their feature affinity, and then updating the cluster centers and pixel features. Together, these operations comprise the Clustering Mask Transformer (CMT) layer, which produces cross-attention that is denser and more consistent with the final segmentation task. CMT-DeepLab improves the performance over prior art significantly by 4.4% PQ, achieving a new state-of-the-art of 55.7% PQ on the COCO test-dev set.
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="2206.08948")
Code
Syntology Ran 0 of 8 code samples harvested from 1 repository linked to this paper; 8 have no recorded run.
By repository: community (archive-listed): 8 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
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
8 samples harvested; 0 ran; 0 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.
Licence: 0 of the 8 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 bytedance/kmax-deeplab. “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.
fea9c1c5791db8ef · report
26b60f3c795581f6 · report
f542cee6c2318794 · report
81e3bffc1955dbf8 · report
e41d218074999206 · report
ccfd0fb1e16e8e61 · report
21fe0f39545449df · report
6c0dab27e941b121 · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Panoptic Segmentation | COCO minival | CMT-DeepLab (single-scale) | PQ | 55.3 | #20 of 31 | Archive leaderboard | report |
| Panoptic Segmentation | COCO minival | CMT-DeepLab (single-scale) | PQst | 46.6 | #20 of 31 | Archive leaderboard | report |
| Panoptic Segmentation | COCO minival | CMT-DeepLab (single-scale) | PQth | 61.0 | #20 of 31 | Archive leaderboard | report |
| Panoptic Segmentation | COCO test-dev | CMT-DeepLab (single-scale) | PQ | 55.7 | #6 of 38 | Archive leaderboard | report |
| Panoptic Segmentation | COCO test-dev | CMT-DeepLab (single-scale) | PQst | 46.8 | #6 of 38 | Archive leaderboard | report |
| Panoptic Segmentation | COCO test-dev | CMT-DeepLab (single-scale) | PQth | 61.6 | #6 of 38 | Archive leaderboard | report |
| Panoptic Segmentation | Cityscapes val | CMT-DeepLab (MaX-S, single-scale, IN-1K) | PQ | 64.6 | #17 of 37 | Archive leaderboard | report |
| Panoptic Segmentation | Cityscapes val | CMT-DeepLab (MaX-S, single-scale, IN-1K) | mIoU | 81.4 | #17 of 37 | 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