Papers › GSVA: Generalized Segmentation via Multimodal Large Language Models

GSVA: Generalized Segmentation via Multimodal Large Language Models

15 Dec 2023CVPR 2024 1arXiv:2312.10103archive 2025-07-28

Zhuofan Xia, Dongchen Han, Yizeng Han, Xuran Pan, Shiji Song, Gao Huang

Generalized Referring Expression Segmentation (GRES) extends the scope of classic RES to refer to multiple objects in one expression or identify the empty targets absent in the image. GRES poses challenges in modeling the complex spatial relationships of the instances in the image and identifying non-existing referents. Multimodal Large Language Models (MLLMs) have recently shown tremendous progress in these complicated vision-language tasks. Connecting Large Language Models (LLMs) and vision models, MLLMs are proficient in understanding contexts with visual inputs. Among them, LISA, as a representative, adopts a special [SEG] token to prompt a segmentation mask decoder, e.g., SAM, to enable MLLMs in the RES task. However, existing solutions to GRES remain unsatisfactory since current segmentation MLLMs cannot correctly handle the cases where users might reference multiple subjects in a singular prompt or provide descriptions incongruent with any image target. In this paper, we propose Generalized Segmentation Vision Assistant (GSVA) to address this gap. Specifically, GSVA reuses the [SEG] token to prompt the segmentation model towards supporting multiple mask references simultaneously and innovatively learns to generate a [REJ] token to reject the null targets explicitly. Experiments validate GSVA's efficacy in resolving the GRES issue, marking a notable enhancement and setting a new record on the GRES benchmark gRefCOCO dataset. GSVA also proves effective across various classic referring segmentation and comprehension tasks.

PaperPDFConference PDFCodeCode 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 10 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 6 ran (3 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

leaplabthu/gsva officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 10 samples, 6 ran (3 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

10 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 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.

1ran · honoured contract
3ran · our draft was wrong
2ran
4unverified

Licence: 1 of the 10 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 leaplabthu/gsva. “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.

leaplabthu/gsva official repository 10 samples, 6 ran (3 instrument-failed) · 4 unverified
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket
model/losses.py ran · our draft was wrong Apache-2.0 (permissive) · 6ec47ecac3fe27fc · report fixture: signature inputs:Tensor/3/float, targets:Tensor/3/float, num_masks:float/0/float, scale:int/0/int, eps:float/0/float · returned Tensor · level recorded 2026-09-25
get_logger in 383 papers utils/logger.py ran Apache-2.0 (permissive) · 7e11d9ec27335f5b · report fixture: signature output_dir:str/0/str, dist_rank:int/0/int, name:str/0/str · returned Logger · level recorded 2026-09-24
iou_loss in 17 papers model/losses.py ran fingerprinted Apache-2.0 (permissive) · af6fc3d42a9de09a · report fixture: signature pred_iou:Tensor/2/float, pred_mask:Tensor/2/float, target_mask:Tensor/2/float, num_masks:float/0/float · returned Tensor · level recorded 2026-09-25
load_image_from_base64 in 87 papers model/llava/mm_utils.py ran · honoured contract Apache-2.0 (permissive) here; the stored copy is pointer only · 0dde2e782959c0bd · report fixture: signature image:str/0/str · returned PngImageFile · level recorded 2026-09-25
process_images in 79 papers model/llava/mm_utils.py ran · our draft was wrong Apache-2.0 (permissive) · 1df990c375318896 · report fixture: signature images:list/1/Tensor, image_processor:callable/0/?, model_cfg:dict/0/? · returned Tensor · level recorded 2026-09-24
sigmoid_ce_loss in 70 papers
census: 4 implementations from 8 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
model/losses.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 13c0bb91f8009d9c · report fixture: signature inputs:Tensor/3/float, targets:Tensor/3/float, num_masks:float/0/float · returned Tensor · level recorded 2026-09-25
build_sam_vit_b in 53 papers model/segment_anything/build_sam.py unverified Apache-2.0 (permissive) · e11c7f60d91192ce · report
build_sam_vit_h in 54 papers model/segment_anything/build_sam.py unverified Apache-2.0 (permissive) · 06cfc37f79036a2c · report
build_sam_vit_l in 53 papers model/segment_anything/build_sam.py unverified Apache-2.0 (permissive) · 7cea226e4ef7b90d · report
init_vision_seg_for_model model/prepare_model_tokenizer.py unverified Apache-2.0 (permissive) · 0a8545604f9b15d8 · report

Tasks

DecoderGeneralized Referring Expression SegmentationReferring ExpressionReferring Expression SegmentationSegmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Generalized Referring Expression Segmentation gRefCOCO GSVA-Llama2-13B cIoU 66.38 #2 of 13 Archive leaderboard report
Generalized Referring Expression Segmentation gRefCOCO GSVA-Llama2-13B gIoU 70.04 #2 of 13 Archive leaderboard report
Generalized Referring Expression Segmentation gRefCOCO GSVA-Vicuna-13B-v1.1 cIoU 64.05 #5 of 13 Archive leaderboard report
Generalized Referring Expression Segmentation gRefCOCO GSVA-Vicuna-13B-v1.1 gIoU 68.01 #5 of 13 Archive leaderboard report
Generalized Referring Expression Segmentation gRefCOCO GSVA-Vicuna-7B-v1.1 cIoU 63.29 #7 of 13 Archive leaderboard report
Generalized Referring Expression Segmentation gRefCOCO GSVA-Vicuna-7B-v1.1 gIoU 66.47 #7 of 13 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

SAM

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