Papers › Universal Segmentation at Arbitrary Granularity with Language Instruction

Universal Segmentation at Arbitrary Granularity with Language Instruction

4 Dec 2023CVPR 2024 1arXiv:2312.01623archive 2025-07-28

Yong liu, Cairong Zhang, Yitong Wang, Jiahao Wang, Yujiu Yang, Yansong Tang

This paper aims to achieve universal segmentation of arbitrary semantic level. Despite significant progress in recent years, specialist segmentation approaches are limited to specific tasks and data distribution. Retraining a new model for adaptation to new scenarios or settings takes expensive computation and time cost, which raises the demand for versatile and universal segmentation model that can cater to various granularity. Although some attempts have been made for unifying different segmentation tasks or generalization to various scenarios, limitations in the definition of paradigms and input-output spaces make it difficult for them to achieve accurate understanding of content at arbitrary granularity. To this end, we present UniLSeg, a universal segmentation model that can perform segmentation at any semantic level with the guidance of language instructions. For training UniLSeg, we reorganize a group of tasks from original diverse distributions into a unified data format, where images with texts describing segmentation targets as input and corresponding masks are output. Combined with a automatic annotation engine for utilizing numerous unlabeled data, UniLSeg achieves excellent performance on various tasks and settings, surpassing both specialist and unified segmentation models.

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="2312.01623")

Code

Syntology Ran 13 of 16 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 5 ran · our draft was wrong; 2 ran · fixture could not drive it; 6 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 13 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/UniLSeg officialmentioned in papermentioned on GitHubpytorchMIT report
yongliu20/UniLSeg officialmentioned on GitHubpytorchMIT 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

16 samples harvested; 13 ran; 0 honoured the contract we drafted; 3 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.

5ran · our draft was wrong
2ran · fixture could not drive it
6ran
3unverified

Licence: 0 of the 16 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/UniLSeg. “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.

basic_clean workforai/UniLSeg/utils/simple_tokenizer.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 98f385d847636a3e · report
conv_layer workforai/UniLSeg/model/layers.py official repository ran · our draft was wrong MIT (permissive) · dbfe3357dc25ca5f · report
convert workforai/UniLSeg/general_inference.py official repository ran MIT (permissive) · b58064020006b0a9 · report
drop_path workforai/UniLSeg/model/swin_basic.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 55120f2026b56aa2 · report
getTransformMat workforai/UniLSeg/general_inference.py official repository ran MIT (permissive) · 78c2a76bb782ddcf · report
get_norm workforai/UniLSeg/model/layers.py official repository ran MIT (permissive) · c7bbc28314ec3695 · report
get_pairs workforai/UniLSeg/utils/simple_tokenizer.py official repository ran · our draft was wrong MIT (permissive) · d919ae32e5e4e616 · report
linear_layer workforai/UniLSeg/model/layers.py official repository ran MIT (permissive) · 89f9fd49ddec76ba · report
seq_to_2d workforai/UniLSeg/model/swin_basic.py official repository ran MIT (permissive) · 6bbbed38875c20c9 · report
trunc_normal_ workforai/UniLSeg/model/swin.py official repository ran fingerprinted MIT (permissive) · 6c14f890f804806f · report
whitespace_clean workforai/UniLSeg/utils/simple_tokenizer.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 9542161e9640b858 · report
window_partition workforai/UniLSeg/model/swin.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · f9fd6241d935f07b · report
window_reverse workforai/UniLSeg/model/swin.py official repository ran · our draft was wrong MIT (permissive) · fb32094c6dbece71 · report
build_model workforai/UniLSeg/model/clip.py official repository unverified MIT (permissive) · 6cbac649525d3861 · report
load_cfg_from_cfg_file workforai/UniLSeg/utils/config.py official repository unverified MIT (permissive) · cc23416cff396c39 · report
merge_cfg_from_list workforai/UniLSeg/utils/config.py official repository unverified MIT (permissive) · 022883c7911679b3 · report

Tasks

Referring Expression SegmentationSegmentationUniversal Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Referring Expression Segmentation RefCOCO+ test B UniLSeg-100 Overall IoU 68.15 #6 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ test B UniLSeg-20 Overall IoU 66.99 #7 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ testA UniLSeg-100 Overall IoU 78.29 #6 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ testA UniLSeg-20 Overall IoU 77.02 #8 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ val UniLSeg-100 Overall IoU 73.18 #8 of 33 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ val UniLSeg-20 Overall IoU 72.70 #9 of 33 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-test UniLSeg-100 Overall IoU 80.54 #1 of 18 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-test UniLSeg-20 Overall IoU 79.47 #3 of 18 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-val UniLSeg-100 Overall IoU 79.27 #3 of 23 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-val UniLSeg-20 Overall IoU 78.41 #4 of 23 Archive leaderboard report
Referring Expression Segmentation RefCoCo val UniLSeg-100 Overall IoU 81.74 #8 of 37 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) UniLSeg-100 F 67.0 #18 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) UniLSeg-100 J 62.8 #18 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) UniLSeg-100 J&F 64.9 #18 of 33 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