Browse State-of-the-Art › Zero-Shot Semantic Segmentation
Zero-Shot Semantic Segmentation
29 papers with code · 4 benchmarks · 3 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
4 leaderboard tables shown for this task, 4 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.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| COCO-Stuff (15 rows) | OTSeg+ | OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation | code | Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified | Compare |
| MESS (13 rows) | CAT-Seg-L | — | — | — | Compare |
| PASCAL VOC (13 rows) | OTSeg+ | OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation | code | Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified | Compare |
| ADE20K-847 (1 row) | MAFT | — | — | — | Compare |
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
3 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 60 · with a code link: 29 · where Syntology ran a sample: 10 (9 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (10 of 60 tagged: 9 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 60 of 60, 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.
-
28 May 2019 144 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified (of 302 harvested samples) · 113 pointer-only (licence)Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available.
-
4 Dec 2024 2 repositories listed Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 9 where Syntology's instrument failed) · 7 unverified (of 20 harvested samples) · 20 pointer-only (licence)CLIP has shown impressive results in aligning images and texts at scale.
-
29 Dec 2021 2 repositories listedHowever, semantic segmentation and the CLIP model perform on different visual granularity, that semantic segmentation processes on pixels while CLIP performs on images.
-
16 Aug 2020 2 repositories listedIn this paper, we propose a novel context-aware feature generation method for zero-shot segmentation named CaGNet.
-
3 Jun 2019 2 repositories listedSemantic segmentation models are limited in their ability to scale to large numbers of object classes.
-
16 Apr 2025 1 repository listedExisting zero-shot 3D point cloud segmentation methods often struggle with limited transferability from seen classes to unseen classes and from semantic to visual space.
-
12 Jun 2024 1 repository listedIn recent years, there has been a surge of interest in open-vocabulary 3D scene reconstruction facilitated by visual language models (VLMs), which showcase remarkable capabilities in open-set retrieval.
-
5 Jun 2024 1 repository listed 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 (of 2 harvested samples)Foundation models have emerged as powerful tools across various domains including language, vision, and multimodal tasks.
-
2 Jun 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 1 pointer-only (licence)Our Cascade-CLIP is flexible and can be easily applied to existing zero-shot semantic segmentation methods.
-
21 Mar 2024 1 repository listed Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified (of 10 harvested samples) · 10 pointer-only (licence)The recent success of CLIP has demonstrated promising results in zero-shot semantic segmentation by transferring muiltimodal knowledge to pixel-level classification.
-
1 Jan 2024 1 repository listedOn the other hand overfitting should be mitigated during the training stage.
-
1 Jan 2024 1 repository listedThe recent advent of pre-trained vision transformers has unveiled a promising property: their inherent capability to group semantically related visual concepts.
-
20 Dec 2023 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)Recently, CLIP has found practical utility in the domain of pixel-level zero-shot segmentation tasks.
-
4 Dec 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples) · 2 pointer-only (licence)Specifically, we replace the traditional self-attention block of CLIP vision encoder's last layer by our CSA module and reuse its pretrained projection matrices of query, key, and value, leading to a training-free…
-
30 Sep 2023 1 repository listedFirst, we built a river ice semantic segmentation dataset IPC_RI_SEG using a fixed camera and covering the entire ice melting process of the river.
-
25 Sep 2023 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 7 pointer-only (licence)The emergence of CLIP has opened the way for open-world image perception.
-
27 Jun 2023 1 repository listed 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) · 2 unverified (of 3 harvested samples)To address this problem, zero-shot semantic segmentation makes use of large self-supervised vision-language models, allowing zero-shot transfer to unseen classes.
-
17 Apr 2023 1 repository listedThanks to the impressive progress of large-scale vision-language pretraining, recent recognition models can classify arbitrary objects in a zero-shot and open-set manner, with a surprisingly high accuracy.
-
3 Apr 2023 1 repository listedRecently, the open-vocabulary semantic segmentation problem has attracted increasing attention and the best performing methods are based on two-stream networks: one stream for proposal mask generation and the other for…
-
28 Jan 2023 1 repository listedIn particular, we introduce a novel Multiple Prompt Optimal Transport Solver (MPOT), which is designed to learn an optimal mapping between multiple text prompts and visual feature maps of the frozen image encoder hidden…
-
1 Jan 2023 1 repository listedGiven only the class-level semantic information for unseen objects, we strive to enhance the correspondence, alignment and consistency between the visual and semantic spaces, to synthesise diverse, generic and…
-
7 Dec 2022 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified (of 9 harvested samples) · 3 pointer-only (licence)Recently, CLIP has been applied to pixel-level zero-shot learning tasks via a two-stage scheme.
-
4 Nov 2022 1 repository listedPretrained vision-language models (VLMs) such as CLIP have shown impressive generalization capability in downstream vision tasks with appropriate text prompts.
-
15 Dec 2021 1 repository listed2) a zero-shot classification task on segments.
-
2 Dec 2021 1 repository listedContrastive Language-Image Pre-training (CLIP) has made a remarkable breakthrough in open-vocabulary zero-shot image recognition.
-
21 Apr 2021 1 repository listedBeing able to segment unseen classes not observed during training is an important technical challenge in deep learning, because of its potential to reduce the expensive annotation required for semantic segmentation.
-
25 Sep 2020 1 repository listedThus, we focus on zero-shot semantic segmentation, which aims to segment unseen objects with only category-level semantic representations provided for unseen categories.
-
1 Jul 2020 1 repository listedOur method assumes that both the source images with full pixel-level labels and unlabeled target images are available during training.
-
1 Jun 2019 1 repository listedIn this paper we take this one step further and focus on the challenging task of zero- and few-shot learning of semantic segmentation.
-
Split Matching for Inductive Zero-shot Semantic Segmentation8 May 2025 0 repositories listedZero-shot Semantic Segmentation (ZSS) aims to segment categories that are not annotated during training.
-
Bridge the Gap Between Visual and Linguistic Comprehension for Generalized Zero-shot Semantic Segmentation31 Mar 2025 0 repositories listed
-
Disentangling CLIP for Multi-Object Perception5 Feb 2025 0 repositories listed
-
Open-RGBT: Open-vocabulary RGB-T Zero-shot Semantic Segmentation in Open-world Environments9 Oct 2024 0 repositories listed
-
Segment Anything Model for automated image data annotation: empirical studies using text prompts from Grounding DINO27 Jun 2024 0 repositories listed
-
AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation8 Apr 2024 0 repositories listed
-
Semantics from Space: Satellite-Guided Thermal Semantic Segmentation Annotation for Aerial Field Robots21 Mar 2024 0 repositories listed
-
Annotation Free Semantic Segmentation with Vision Foundation Models14 Mar 2024 0 repositories listed
-
Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation13 Mar 2024 0 repositories listed
-
Learning Segmented 3D Gaussians via Efficient Feature Unprojection for Zero-shot Neural Scene Segmentation11 Jan 2024 0 repositories listed
-
CSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseen9 Dec 2023 0 repositories listed
-
SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding23 Oct 2023 0 repositories listed
-
CLIP Is Also a Good Teacher: A New Learning Framework for Inductive Zero-shot Semantic Segmentation3 Oct 2023 0 repositories listed
-
Masked Momentum Contrastive Learning for Zero-shot Semantic Understanding22 Aug 2023 0 repositories listed
-
MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic Segmentation9 Aug 2023 0 repositories listed
-
Exploring Open-Vocabulary Semantic Segmentation without Human Labels1 Jun 2023 0 repositories listed
-
Interactive Segment Anything NeRF with Feature Imitation25 May 2023 0 repositories listed
-
14 Apr 2023 0 repositories listed
-
[CLS] Token is All You Need for Zero-Shot Semantic Segmentation13 Apr 2023 0 repositories listed
-
SATR: Zero-Shot Semantic Segmentation of 3D Shapes11 Apr 2023 0 repositories listed
-
Class Enhancement Losses with Pseudo Labels for Zero-shot Semantic Segmentation18 Jan 2023 0 repositories listed
-
Exploring Open-Vocabulary Semantic Segmentation from CLIP Vision Encoder Distillation Only1 Jan 2023 0 repositories listed
-
27 Sep 2022 0 repositories listed
-
Zero-Shot Semantic Segmentation via Spatial and Multi-Scale Aware Visual Class Embedding30 Nov 2021 0 repositories listed
-
27 Aug 2021 0 repositories listed
-
Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation14 Aug 2021 0 repositories listed
-
Conterfactual Generative Zero-Shot Semantic Segmentation11 Jun 2021 0 repositories listed
-
Recursive Training for Zero-Shot Semantic Segmentation26 Feb 2021 0 repositories listed
-
Prototypical Matching and Open Set Rejection for Zero-Shot Semantic Segmentation1 Jan 2021 0 repositories listed
-
Consistent Structural Relation Learning for Zero-Shot Segmentation1 Dec 2020 0 repositories listed
-
Uncertainty-Aware Learning for Zero-Shot Semantic Segmentation1 Dec 2020 0 repositories listed
Syntology lines on 10 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