Browse State-of-the-Art › Open Vocabulary Semantic Segmentation

Open Vocabulary Semantic Segmentation

71 papers with code · 14 benchmarks · 6 datasets archive 2025-07-28

Computer Vision

Open-vocabulary semantic segmentation models aim to accurately assign a semantic label to each pixel in an image from a set of arbitrary open-vocabulary texts.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

15 leaderboard tables shown for this task, 14 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 15 until expanded.

Syntology 5 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 1 placed): PASCAL Context-59 (1 judged, 1 placed), ADE20K-150 (2 judged, 0 placed), ADE20K-847 (1 judged, 0 placed), iSAID (2 judged, 0 placed), FAST (1 judged, 0 placed), SIOR (1 judged, 0 placed), SOTA (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
PASCAL Context-59 (24 rows) HyperSeg HyperSeg: Towards Universal Visual Segmentation with Large Language Model code Syntology official (archive's flag): 13 ran · 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 Compare
ADE20K-150 (23 rows) Mask-Adapter Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation code — Compare
PascalVOC-20 (20 rows) UMG-CLIP-L/14 UMG-CLIP: A Unified Multi-Granularity Vision Generalist for... code — Compare
ADE20K-847 (19 rows) UMG-CLIP-E/14 UMG-CLIP: A Unified Multi-Granularity Vision Generalist for... code — Compare
PASCAL Context-459 (15 rows) SILC SILC: Improving Vision Language Pretraining with Self-Distillation — — Compare
COCO-Stuff-171 (7 rows) POMP Prompt Pre-Training with Twenty-Thousand Classes for... code Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified Compare
Cityscapes (5 rows) FC-CLIP Convolutions Die Hard: Open-Vocabulary Segmentation with Single... code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
PascalVOC-20b (4 rows) UMG-CLIP-E/14 UMG-CLIP: A Unified Multi-Granularity Vision Generalist for... code — Compare
iSAID (2 rows) SkySense-O SkySense: A Multi-Modal Remote Sensing Foundation Model Towards... code — Compare
ISPRS Potsdam (1 row) SkySense-O SkySense: A Multi-Modal Remote Sensing Foundation Model Towards... code — Compare
Cityscape-171 (1 row) PACL Open Vocabulary Semantic Segmentation with Patch Aligned... code — Compare
FAST (1 row) SkySense-O SkySense: A Multi-Modal Remote Sensing Foundation Model Towards... code — Compare
SIOR (1 row) SkySense-O SkySense: A Multi-Modal Remote Sensing Foundation Model Towards... code — Compare
SOTA (1 row) SkySense-O SkySense: A Multi-Modal Remote Sensing Foundation Model Towards... code — Compare
ADE20K-150 (0 rows) no rows in the archive — —

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

6 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 113 · with a code link: 71 · where Syntology ran a sample: 29 (24 with a run with no instrument failure, 5 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (29 of 113 tagged: 24 with a run with no instrument failure, 5 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 113, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 29 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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