Papers › Open-Vocabulary Segmentation with Semantic-Assisted Calibration

Open-Vocabulary Segmentation with Semantic-Assisted Calibration

7 Dec 2023CVPR 2024 1arXiv:2312.04089archive 2025-07-28

Yong liu, Sule Bai, Guanbin Li, Yitong Wang, Yansong Tang

This paper studies open-vocabulary segmentation (OVS) through calibrating in-vocabulary and domain-biased embedding space with generalized contextual prior of CLIP. As the core of open-vocabulary understanding, alignment of visual content with the semantics of unbounded text has become the bottleneck of this field. To address this challenge, recent works propose to utilize CLIP as an additional classifier and aggregate model predictions with CLIP classification results. Despite their remarkable progress, performance of OVS methods in relevant scenarios is still unsatisfactory compared with supervised counterparts. We attribute this to the in-vocabulary embedding and domain-biased CLIP prediction. To this end, we present a Semantic-assisted CAlibration Network (SCAN). In SCAN, we incorporate generalized semantic prior of CLIP into proposal embedding to avoid collapsing on known categories. Besides, a contextual shift strategy is applied to mitigate the lack of global context and unnatural background noise. With above designs, SCAN achieves state-of-the-art performance on all popular open-vocabulary segmentation benchmarks. Furthermore, we also focus on the problem of existing evaluation system that ignores semantic duplication across categories, and propose a new metric called Semantic-Guided IoU (SG-IoU).

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="2312.04089")

Code

Syntology Ran 5 of 10 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 3 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

workforai/scan officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
yongliu20/SCAN officialmentioned on GitHubpytorchNOASSERTION 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

10 samples harvested; 5 ran; 0 honoured the contract we drafted; 5 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 · our draft was wrong
1ran · fixture could not drive it
3ran
5unverified

Licence: 10 of the 10 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 workforai/scan. “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.

crop_with_mask workforai/scan/scan/modeling/clip_adapter/utils.py official repository ran licence not identified · pointer only · 4b40d7fecc852bbe · report
expand_box workforai/scan/scan/modeling/clip_adapter/utils.py official repository ran licence not identified · pointer only · 2fc0075c2a14b806 · report
mask2box workforai/scan/scan/modeling/clip_adapter/utils.py official repository ran licence not identified · pointer only · 50372092a6e364ac · report
window_partition workforai/scan/scan/modeling/backbone/swin.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · f9fd6241d935f07b · report
window_reverse workforai/scan/scan/modeling/backbone/swin.py official repository ran · our draft was wrong no licence file found · pointer only · fb32094c6dbece71 · report
batch_dice_loss workforai/scan/scan/modeling/matcher.py official repository unverified no licence file found · pointer only · bc2cb481a75c370d · report
batch_sigmoid_ce_loss workforai/scan/scan/modeling/matcher.py official repository unverified no licence file found · pointer only · 1edd24985036b0bf · report
calculate_uncertainty workforai/scan/scan/modeling/criterion.py official repository unverified no licence file found · pointer only · 2dcb8123d89bb1ff · report
dice_loss workforai/scan/scan/modeling/criterion.py official repository unverified no licence file found · pointer only · 89f75e54ff128be0 · report
sigmoid_ce_loss workforai/scan/scan/modeling/criterion.py official repository unverified no licence file found · pointer only · d0c61e8dba511aa3 · report

Tasks

AttributeOpen Vocabulary Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open Vocabulary Semantic Segmentation ADE20K-150 SCAN mIoU 33.5 #12 of 23 Archive leaderboard report
Open Vocabulary Semantic Segmentation ADE20K-847 SCAN mIoU 14.0 #10 of 19 Archive leaderboard report
Open Vocabulary Semantic Segmentation PASCAL Context-459 SCAN mIoU 16.7 #11 of 15 Archive leaderboard report
Open Vocabulary Semantic Segmentation PASCAL Context-59 SCAN mIoU 59.3 #11 of 24 Archive leaderboard report
Open Vocabulary Semantic Segmentation PascalVOC-20 SCAN mIoU 97.2 #3 of 20 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

CLIPFocus

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