Papers › UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces

UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces

25 Dec 2023arXiv:2312.15715archive 2025-07-28

Jiannan Wu, Yi Jiang, Bin Yan, Huchuan Lu, Zehuan Yuan, Ping Luo

The reference-based object segmentation tasks, namely referring image segmentation (RIS), few-shot image segmentation (FSS), referring video object segmentation (RVOS), and video object segmentation (VOS), aim to segment a specific object by utilizing either language or annotated masks as references. Despite significant progress in each respective field, current methods are task-specifically designed and developed in different directions, which hinders the activation of multi-task capabilities for these tasks. In this work, we end the current fragmented situation and propose UniRef++ to unify the four reference-based object segmentation tasks with a single architecture. At the heart of our approach is the proposed UniFusion module which performs multiway-fusion for handling different tasks with respect to their specified references. And a unified Transformer architecture is then adopted for achieving instance-level segmentation. With the unified designs, UniRef++ can be jointly trained on a broad range of benchmarks and can flexibly complete multiple tasks at run-time by specifying the corresponding references. We evaluate our unified models on various benchmarks. Extensive experimental results indicate that our proposed UniRef++ achieves state-of-the-art performance on RIS and RVOS, and performs competitively on FSS and VOS with a parameter-shared network. Moreover, we showcase that the proposed UniFusion module could be easily incorporated into the current advanced foundation model SAM and obtain satisfactory results with parameter-efficient finetuning. Codes and models are available at \url{https://github.com/FoundationVision/UniRef}.

PaperPDFCodeCode 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="2312.15715")

Code

Syntology Ran 9 of 9 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 2 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

foundationvision/uniref officialmentioned in paperpytorchMIT 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

9 samples harvested; 9 ran; 1 honoured the contract we drafted; 0 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 · honoured contract
1ran · our draft was wrong
2ran · fixture could not drive it
5ran

Licence: 0 of the 9 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 foundationvision/uniref. “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.

aligned_bilinear foundationvision/uniref/projects/UniRef/uniref/models/ddetrs.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 29dbbaafa4be18e1 · report
bounding_box foundationvision/uniref/projects/UniRef/uniref/uniref.py official repository ran MIT (permissive) · 8243ac0c601917dc · report
compute_locations foundationvision/uniref/projects/UniRef/uniref/models/ddetrs.py official repository ran · honoured contract MIT (permissive) · ed1a308adb65f645 · report
compute_mask_iou foundationvision/uniref/projects/UniRef/uniref/models/uniref_sam.py official repository ran fingerprinted MIT (permissive) · 4de0dcaf9f33183b · report
concat_mask_dict_features foundationvision/uniref/projects/UniRef/uniref/uniref.py official repository ran MIT (permissive) · 286983a8483318b8 · report
dice_loss foundationvision/uniref/projects/UniRef/uniref/models/uniref_sam.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · a1c2083ec2eaeb22 · report
parse_dynamic_params foundationvision/uniref/projects/UniRef/uniref/models/ddetrs.py official repository ran MIT (permissive) · 46f34dc9f9a94b67 · report
sigmoid_ce_loss foundationvision/uniref/projects/UniRef/uniref/models/uniref_sam.py official repository ran fingerprinted MIT (permissive) · e28a878991e1e696 · report
unfold_wo_center foundationvision/uniref/projects/UniRef/uniref/uniref.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 6bc62d34967e2917 · report

Tasks

Image SegmentationObjectReferring Expression SegmentationReferring Video Object SegmentationSegmentationSemantic SegmentationVideo Object SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) UniRef++-L F 69.0 #12 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) UniRef++-L J 64.8 #12 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) UniRef++-L J&F 66.9 #12 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.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSAMSoftmaxTransformerVOS

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