Papers › HyperSeg: Towards Universal Visual Segmentation with Large Language Model

HyperSeg: Towards Universal Visual Segmentation with Large Language Model

26 Nov 2024arXiv:2411.17606archive 2025-07-28

Cong Wei, Yujie Zhong, Haoxian Tan, Yong liu, Zheng Zhao, Jie Hu, Yujiu Yang

This paper aims to address universal segmentation for image and video perception with the strong reasoning ability empowered by Visual Large Language Models (VLLMs). Despite significant progress in current unified segmentation methods, limitations in adaptation to both image and video scenarios, as well as the complex reasoning segmentation, make it difficult for them to handle various challenging instructions and achieve an accurate understanding of fine-grained vision-language correlations. We propose HyperSeg, the first VLLM-based universal segmentation model for pixel-level image and video perception, encompassing generic segmentation tasks and more complex reasoning perception tasks requiring powerful reasoning abilities and world knowledge. Besides, to fully leverage the recognition capabilities of VLLMs and the fine-grained visual information, HyperSeg incorporates hybrid entity recognition and fine-grained visual perceiver modules for various segmentation tasks. Combined with the temporal adapter, HyperSeg achieves a comprehensive understanding of temporal information. Experimental results validate the effectiveness of our insights in resolving universal image and video segmentation tasks, including the more complex reasoning perception tasks. Our code is available.

PaperPDFCodeCode Syntology ran

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):

Code

Syntology 17 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 13 ran (8 with no instrument failure; 5 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 13 samples that ran have no recorded date.

congvvc/HyperSeg officialmentioned on GitHubpytorchApache-2.0Syntology: 17 samples, 13 ran (5 instrument-failed) · 4 unverified 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

17 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 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.

4ran · honoured contract
2ran · violated contract
4ran · our draft was wrong
1ran; the contract check could not run
2ran
4unverified

Licence: 2 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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 congvvc/HyperSeg. “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.

congvvc/HyperSeg official repository 17 samples, 13 ran (5 instrument-failed) · 4 unverified
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
hyperseg/model/multimodal_encoder/swin_trans.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 144d10b49baeb8a6 · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded, date not recorded
FeedForward in 198 papers hyperseg/model/language_model/perceiver.py ran · our draft was wrong Apache-2.0 (permissive) · 4d75570b4e91d0b4 · report fixture: signature dim:int/0/int, mult:int/0/int · returned Sequential · level recorded 2026-09-22
box_cxcywh_to_xyxy in 60 papers hyperseg/model/tracker/box_ops.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · e0a06ded5d4f6c3c · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
enhance_with_circles hyperseg/model/datasets_mapper/coco_instance_mapper.py ran · honoured contract Apache-2.0 (permissive) · 8bbf355ce170aeb9 · report fixture: signature binary_mask:ndarray/2/int, radius:int/0/int · returned ndarray · level recorded 2026-09-25
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
hyperseg/model/language_model/perceiver.py ran · violated contract Apache-2.0 (permissive) here; the stored copy is pointer only · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded
expand2square in 78 papers hyperseg/model/mipha/mm_utils.py ran · our draft was wrong Apache-2.0 (permissive) · 592b3c1a88f93d7c · report fixture: signature pil_img:Image/0/?, background_color:tuple/1/int · returned Image · level recorded 2026-09-22
filter_empty_instances_soft hyperseg/model/datasets_mapper/coco_instance_mapper.py ran Apache-2.0 (permissive) · ee5e474262386435 · report fixture: signature instances:Instances/0/?, by_box:bool/0/bool, by_mask:bool/0/bool, box_threshold:float/0/float · returned Instances · level recorded 2026-09-25
get_mask_box_from_json hyperseg/model/tracker/box_ops.py ran Apache-2.0 (permissive) · b1aa0c20f4bb79af · report fixture: signature json_path:str/0/str, img:ndarray/3/int · returned tuple · level recorded 2026-09-25
get_mask_from_json in 5 papers hyperseg/model/tracker/box_ops.py ran · our draft was wrong Apache-2.0 (permissive) · 5f4db0dd94dcdfcb · report fixture: signature json_path:str/0/str, img:ndarray/3/int · returned tuple · level recorded 2026-09-25
load_image_from_base64 in 87 papers hyperseg/model/mipha/mm_utils.py ran · honoured contract Apache-2.0 (permissive) · c3ee9d07c900dd55 · report fixture: signature image:str/0/str · returned PngImageFile · level recorded 2026-09-24
process_images in 79 papers hyperseg/model/mipha/mm_utils.py ran · honoured contract Apache-2.0 (permissive) · 344dff4791fd1381 · report fixture: signature images:list/1/Image, image_processor:callable/0/?, model_cfg:MockModelConfig/0/? · returned Tensor · level recorded 2026-09-26
violates_moderation in 59 papers hyperseg/model/mipha/utils.py ran · violated contract Apache-2.0 (permissive) here; the stored copy is pointer only · f9939a84b9a65279 · report fixture: signature text:str/0/str · returned bool · level recorded 2026-09-26
window_reverse in 296 papers hyperseg/model/multimodal_encoder/swin_trans.py ran · our draft was wrong Apache-2.0 (permissive) · 61bf152e6a42a184 · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded, date not recorded
build_logger in 9 papers hyperseg/model/mipha/utils.py unverified Apache-2.0 (permissive) · 40cf72d9c04c7f63 · report
build_swin_t hyperseg/model/multimodal_encoder/swin_trans.py unverified Apache-2.0 (permissive) · 670eda77b277eb8a · report
check_shape hyperseg/model/language_model/einops_exts.py unverified Apache-2.0 (permissive) · bbe128f6633ed802 · report
pretty_print_semaphore in 55 papers hyperseg/model/mipha/utils.py unverified Apache-2.0 (permissive) · 37899f22fb191b37 · report

Tasks

Language ModelingLarge Language ModelOpen Vocabulary Semantic SegmentationPanoptic SegmentationReasoning SegmentationReasoning Video Object SegmentationReferring Expression SegmentationReferring Video Object SegmentationSegmentationSemantic SegmentationUniversal SegmentationVideo Object SegmentationWorld Knowledge

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open Vocabulary Semantic Segmentation PASCAL Context-59 HyperSeg mIoU 64.6 #1 of 24 Archive leaderboard report
Open Vocabulary Semantic Segmentation PascalVOC-20 HyperSeg mIoU 92.1 #12 of 20 Archive leaderboard report
Panoptic Segmentation COCO minival HyperSeg (Swin-B) PQ 61.2 #1 of 31 Archive leaderboard report
Referring Expression Segmentation DAVIS 2017 (val) HyperSeg J&F 1st frame 71.2 #2 of 18 Archive leaderboard report
Referring Expression Segmentation RefCOCO testA HyperSeg Overall IoU 85.7 #2 of 13 Archive leaderboard report
Referring Expression Segmentation RefCOCO testB HyperSeg Overall IoU 83.4 #1 of 13 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ test B HyperSeg Overall IoU 75.2 #2 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ testA HyperSeg Overall IoU 83.5 #1 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ val HyperSeg Overall IoU 79.0 #3 of 33 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-test HyperSeg Overall IoU 78.9 #4 of 18 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-val HyperSeg Overall IoU 79.4 #2 of 23 Archive leaderboard report
Referring Expression Segmentation RefCoCo val HyperSeg Overall IoU 84.8 #2 of 37 Archive leaderboard report
Referring Video Object Segmentation Refer-YouTube-VOS HyperSeg J&F 68.5 #3 of 18 Archive leaderboard report
Semantic Segmentation COCO (Common Objects in Context) HyperSeg mIoU 77.2 #1 of 9 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