Papers › Unsupervised Universal Image Segmentation

Unsupervised Universal Image Segmentation

28 Dec 2023CVPR 2024 1arXiv:2312.17243archive 2025-07-28

Dantong Niu, Xudong Wang, Xinyang Han, Long Lian, Roei Herzig, Trevor Darrell

Several unsupervised image segmentation approaches have been proposed which eliminate the need for dense manually-annotated segmentation masks; current models separately handle either semantic segmentation (e.g., STEGO) or class-agnostic instance segmentation (e.g., CutLER), but not both (i.e., panoptic segmentation). We propose an Unsupervised Universal Segmentation model (U2Seg) adept at performing various image segmentation tasks -- instance, semantic and panoptic -- using a novel unified framework. U2Seg generates pseudo semantic labels for these segmentation tasks via leveraging self-supervised models followed by clustering; each cluster represents different semantic and/or instance membership of pixels. We then self-train the model on these pseudo semantic labels, yielding substantial performance gains over specialized methods tailored to each task: a +2.6 APᵇᵒˣ boost vs. CutLER in unsupervised instance segmentation on COCO and a +7.0 PixelAcc increase (vs. STEGO) in unsupervised semantic segmentation on COCOStuff. Moreover, our method sets up a new baseline for unsupervised panoptic segmentation, which has not been previously explored. U2Seg is also a strong pretrained model for few-shot segmentation, surpassing CutLER by +5.0 APᵐᵃˢᵏ when trained on a low-data regime, e.g., only 1% COCO labels. We hope our simple yet effective method can inspire more research on unsupervised universal image segmentation.

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="2312.17243")

Code

Syntology Ran 13 of 15 code samples harvested from 2 repositories linked to this paper; 2 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 4 ran · fixture could not drive it; 6 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 6 ran; community (archive-listed): 7 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

u2seg/u2seg officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
dantong88/llarva mentioned on GitHubpytorchApache-2.0 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

15 samples harvested; 13 ran; 0 honoured the contract we drafted; 2 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.

3ran · our draft was wrong
4ran · fixture could not drive it
6ran
2unverified

Licence: 0 of the 15 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

conv u2seg/u2seg/u2seg/Instance_Clustering/semisup-simclrv2/resnet.py official repository ran Apache-2.0 (permissive) · fb569f13818701fc · report
drop_path u2seg/u2seg/u2seg/Instance_Clustering/selective_labeling/dino.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 55120f2026b56aa2 · report
evaluate_predictions u2seg/u2seg/u2seg/Instance_Clustering/usl-t_pretraining/usl-t-imagenet-pretrain.py official repository ran Apache-2.0 (permissive) · 23374018ab9941b5 · report
name_to_params u2seg/u2seg/u2seg/Instance_Clustering/semisup-simclrv2/resnet.py official repository ran Apache-2.0 (permissive) · 0e80e018f0e62f7b · report
test_opencv_video_format u2seg/u2seg/demo/u2seg_demo.py official repository ran Apache-2.0 (permissive) · 0f0abfb396e03541 · report
trunc_normal_ u2seg/u2seg/u2seg/Instance_Clustering/selective_labeling/dino.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · 915b71e73a54fc97 · report
get_resnet u2seg/u2seg/u2seg/Instance_Clustering/semisup-simclrv2/resnet.py official repository unverified Apache-2.0 (permissive) · 1f977428f41dd1e0 · report
vit_small u2seg/u2seg/u2seg/Instance_Clustering/selective_labeling/dino.py official repository unverified Apache-2.0 (permissive) · c2eb0fe4668d4549 · report
collate_fn dantong88/llarva/llava/eval/model_vqa_loader.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 20e4f665698a3d18 · report
divide_to_patches dantong88/llarva/llava/mm_utils.py community (archive-listed) ran Apache-2.0 (permissive) · 7e03b180fa317c9a · report
get_chunk dantong88/llarva/llava/eval/model_vqa.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 42a46570620cd9fa · report
resize_and_pad_image dantong88/llarva/llava/mm_utils.py community (archive-listed) ran Apache-2.0 (permissive) · 468eedeba67f1b00 · report
select_best_resolution dantong88/llarva/llava/mm_utils.py community (archive-listed) ran · fixture could not drive it Apache-2.0 (permissive) · 3999ff487573f32c · report
split_list dantong88/llarva/llava/eval/model_vqa.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 076c252c52cbb161 · report
unpad_image dantong88/llarva/llava/model/llava_arch.py community (archive-listed) ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 55c32993da87759b · report

Tasks

Image SegmentationInstance SegmentationPanoptic SegmentationSegmentationSemantic SegmentationUniversal SegmentationUnsupervised Image SegmentationUnsupervised Instance SegmentationUnsupervised Panoptic SegmentationUnsupervised Semantic SegmentationUnsupervised Zero-Shot Instance SegmentationUnsupervised Zero-Shot Panoptic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Panoptic Segmentation BDD100K val U2Seg PQ 15.8 #4 of 4 Archive leaderboard report
Unsupervised Panoptic Segmentation COCO val2017 U2Seg PQ 16.1 #1 of 2 Archive leaderboard report
Unsupervised Panoptic Segmentation COCO val2017 U2Seg RQ 19.9 #1 of 2 Archive leaderboard report
Unsupervised Panoptic Segmentation COCO val2017 U2Seg SQ 71.1 #1 of 2 Archive leaderboard report
Unsupervised Panoptic Segmentation Cityscapes U2Seg (827 pseudo-classes) PQ 18.4 #4 of 5 Archive leaderboard report
Unsupervised Panoptic Segmentation KITTI U2Seg PQ 20.6 #4 of 4 Archive leaderboard report
Unsupervised Panoptic Segmentation MUSES: MUlti-SEnsor Semantic perception dataset U2Seg PQ 20.3 #4 of 4 Archive leaderboard report
Unsupervised Panoptic Segmentation Waymo Open Dataset U2Seg PQ 19.8 #4 of 4 Archive leaderboard report
Unsupervised Semantic Segmentation COCO-Stuff-27 U2Seg Clustering [Accuracy] 63.9 #5 of 29 Archive leaderboard report
Unsupervised Semantic Segmentation COCO-Stuff-27 U2Seg Clustering [mIoU] 30.2 #5 of 29 Archive leaderboard report
Unsupervised Zero-Shot Instance Segmentation COCO val2017 U2Seg AP 6.4 #1 of 2 Archive leaderboard report
Unsupervised Zero-Shot Instance Segmentation COCO val2017 U2Seg AP50 11.2 #1 of 2 Archive leaderboard report
Unsupervised Zero-Shot Instance Segmentation COCO val2017 U2Seg AP75 6.4 #1 of 2 Archive leaderboard report
Unsupervised Zero-Shot Instance Segmentation COCO val2017 U2Seg AR100 18.5 #1 of 2 Archive leaderboard report
Unsupervised Zero-Shot Panoptic Segmentation COCO val2017 U2Seg PQ 11.1 #1 of 1 Archive leaderboard report
Unsupervised Zero-Shot Panoptic Segmentation COCO val2017 U2Seg RQ 13.7 #1 of 1 Archive leaderboard report
Unsupervised Zero-Shot Panoptic Segmentation COCO val2017 U2Seg SQ 60.1 #1 of 1 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