Browse State-of-the-Art › Zero Shot Segmentation
Zero Shot Segmentation
70 papers with code · 2 benchmarks · 3 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
2 leaderboard tables shown for this task, 2 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 |
|---|---|---|---|---|---|
| Segmentation in the Wild (12 rows) | Grounded HQ-SAM | Segment Anything in High Quality | code | Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 14 unverified | Compare |
| ADE20K training-free zero-shot segmentation (5 rows) | COSMOS ViT-B/16 | COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training | code | — | 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: 134 · with a code link: 70 · where Syntology ran a sample: 20 (19 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 (20 of 134 tagged: 19 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 134, 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.
-
9 Mar 2023 10 repositories listed Syntology official (archive's flag): 1 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 2 samples that ran constructed an object rather than computing a result (of 5 harvested samples)To effectively fuse language and vision modalities, we conceptually divide a closed-set detector into three phases and propose a tight fusion solution, which includes a feature enhancer, a language-guided query…
-
18 Dec 2021 6 repositories 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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)After training on an extended version of the PhraseCut dataset, our system generates a binary segmentation map for an image based on a free-text prompt or on an additional image expressing the query.
-
2 Jun 2023 4 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 14 unverified (of 17 harvested samples) · 8 pointer-only (licence)HQ-SAM is only trained on the introduced detaset of 44k masks, which takes only 4 hours on 8 GPUs.
-
9 Mar 2025 3 repositories listedTraditional methods for reasoning segmentation rely on supervised fine-tuning with categorical labels and simple descriptions, limiting its out-of-domain generalization and lacking explicit reasoning processes.
-
17 May 2023 3 repositories listed Syntology official (archive's flag): 2 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 3 pointer-only (licence)Tested on 14 previously unseen datasets, the One-Prompt Model showcases superior zero-shot segmentation capabilities, outperforming a wide range of related methods.
-
23 Feb 2023 3 repositories listed Syntology official (archive's flag): 1 ran · 7 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; 5 where Syntology's instrument failed) · 2 unverified (of 9 harvested samples)A side network is attached to a frozen CLIP model with two branches: one for predicting mask proposals, and the other for predicting attention bias which is applied in the CLIP model to recognize the class of masks.
-
28 Sep 2024 2 repositories listedRecently, the introduction of foundation models like CLIP and Segment-Anything-Model (SAM), with robust cross-domain representations, has paved the way for interactive and universal image segmentation.
-
30 Sep 2023 2 repositories listed Syntology official (archive's flag): 1 ran · 5 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; 4 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples) · 2 pointer-only (licence)However, in the paper, we reveal that CLIP is insensitive to different mask proposals and tends to produce similar predictions for various mask proposals of the same image.
-
20 Apr 2023 2 repositories listedWe conclude that SAM shows impressive zero-shot segmentation performance for certain medical imaging datasets, but moderate to poor performance for others.
-
12 Apr 2023 2 repositories listedThese phenomena conflict with conventional explainability methods based on the class attention map (CAM), where the raw model can highlight the local foreground regions using global supervision without alignment.
-
14 Mar 2023 2 repositories listedWe present OpenSeeD, a simple Open-vocabulary Segmentation and Detection framework that jointly learns from different segmentation and detection datasets.
-
16 Aug 2020 2 repositories listedIn this paper, we propose a novel context-aware feature generation method for zero-shot segmentation named CaGNet.
-
11 Jul 2025 1 repository listedDue to the excellent performance in yielding high-quality, zero-shot segmentation, Segment Anything Model (SAM) and its variants have been widely applied in diverse scenarios such as healthcare and intelligent…
-
3 Jun 2025 1 repository listedIn this paper, we investigate the efficacy of using a state-of-the-art image segmentation model, Segment Anything Model 2 (SAM2), in a zero-shot manner for individual tree detection and segmentation.
-
13 May 2025 1 repository listedAs AI-generated imagery becomes ubiquitous, invisible watermarks have emerged as a primary line of defense for copyright and provenance.
-
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.
-
9 Jan 2025 1 repository listedDigital Pathology is a cornerstone in the diagnosis and treatment of diseases.
-
6 Dec 2024 1 repository listedIn the context of medical Augmented Reality (AR) applications, object tracking is a key challenge and requires a significant amount of annotation masks.
-
5 Dec 2024 1 repository listedImage segmentation foundation models (SFMs) like Segment Anything Model (SAM) have achieved impressive zero-shot and interactive segmentation across diverse domains.
-
2 Dec 2024 1 repository listedVision-Language Models (VLMs) trained with contrastive loss have achieved significant advancements in various vision and language tasks.
-
6 Nov 2024 1 repository listedWe present 3DGS-CD, the first 3D Gaussian Splatting (3DGS)-based method for detecting physical object rearrangements in 3D scenes.
-
1 Nov 2024 1 repository listedTo address this limitation, we propose a novel zero-shot image matting model, called ZIM, with two key contributions: First, we develop a label converter that transforms segmentation labels into detailed matte labels…
-
3 Oct 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 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; 2 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)We investigate the internal representations of vision-language models (VLMs) to address hallucinations, a persistent challenge despite advances in model size and training.
-
4 Sep 2024 1 repository listedSegment Anything Model (SAM) has demonstrated powerful zero-shot segmentation performance in natural scenes.
-
23 Aug 2024 1 repository listedThe unprecedented developments in segmentation foundational models have become a dominant force in the field of computer vision, introducing a multitude of previously unexplored capabilities in a wide range of natural…
-
19 Aug 2024 1 repository listedWe train SAM-UNet on SA-Med2D-16M, the largest 2-dimensional medical image segmentation dataset to date, yielding a universal pretrained model for medical images.
-
7 Aug 2024 1 repository listedThe framework consists of two main parts: a Single-Shot PCI Estimation Network and a Dense Captioning Network.
-
3 Aug 2024 1 repository listedThe Segment Anything Model 2 (SAM 2) is the latest generation foundation model for image and video segmentation.
-
22 Jul 2024 1 repository listedRapid and accurate diagnosis of pneumothorax, utilizing chest X-ray and computed tomography (CT), is crucial for assisted diagnosis.
-
18 Jul 2024 1 repository listedSpecifically, our model leverages the Segment Anything Model (SAM) model to segment the target regions from images rendered from the 3D shape.
-
17 Jul 2024 1 repository listed
-
3 Jul 2024 1 repository listed
-
13 Jun 2024 1 repository listed Syntology official (archive's flag): 4 ran · 4 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; 3 where Syntology's instrument failed) · 4 unverified (of 8 harvested samples) · 2 pointer-only (licence)
-
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)
-
2 Jun 2024 1 repository listed
-
19 Apr 2024 1 repository listed
-
9 Apr 2024 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: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified (of 12 harvested samples) · 5 pointer-only (licence)
-
29 Mar 2024 1 repository listed
-
5 Mar 2024 1 repository listed
-
24 Feb 2024 1 repository listed
-
11 Jan 2024 1 repository listed
-
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)
-
1 Dec 2023 1 repository listed
-
19 Nov 2023 1 repository listed
-
14 Nov 2023 1 repository listed
-
24 Sep 2023 1 repository listed
-
26 Aug 2023 1 repository listed
-
23 Aug 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
12 Aug 2023 1 repository listed
-
11 Aug 2023 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 10 harvested samples) · 10 pointer-only (licence)
-
3 Jul 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 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; 2 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 2 pointer-only (licence)
-
30 Jun 2023 1 repository listed
-
23 Jun 2023 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples)
-
19 Jun 2023 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified (of 10 harvested samples)
-
14 Jun 2023 1 repository listed
-
30 May 2023 1 repository listed
-
28 Apr 2023 1 repository listed
-
25 Apr 2023 1 repository listed
-
12 Mar 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 2 pointer-only (licence)
-
8 Mar 2023 1 repository listed
-
27 Feb 2023 1 repository listed
-
28 Jan 2023 1 repository listed
-
12 Jan 2023 1 repository listed
-
21 Dec 2022 1 repository listed
-
9 Dec 2022 1 repository listed
-
1 Dec 2022 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 8 harvested samples)
-
10 Jan 2022 1 repository listed Syntology official (archive's flag): 2 ran · 3 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; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 1 pointer-only (licence)
-
2 Dec 2021 1 repository listed
-
11 Nov 2021 1 repository listed
-
25 Apr 2019 1 repository listed
-
Foundation Models for Zero-Shot Segmentation of Scientific Images without AI-Ready Data30 Jun 2025 0 repositories listed
-
MRI-CORE: A Foundation Model for Magnetic Resonance Imaging13 Jun 2025 0 repositories listed
-
Textile Analysis for Recycling Automation using Transfer Learning and Zero-Shot Foundation Models6 Jun 2025 0 repositories listed
-
Adapting a Segmentation Foundation Model for Medical Image Classification9 May 2025 0 repositories listed
-
AI-Driven Segmentation and Analysis of Microbial Cells1 May 2025 0 repositories listed
-
SynthFM: Training Modality-agnostic Foundation Models for Medical Image Segmentation without Real Medical Data11 Apr 2025 0 repositories listed
-
Resilience of Vision Transformers for Domain Generalisation in the Presence of Out-of-Distribution Noisy Images5 Apr 2025 0 repositories listed
-
SmartScan: An AI-based Interactive Framework for Automated Region Extraction from Satellite Images31 Mar 2025 0 repositories listed
-
Eye on the Target: Eye Tracking Meets Rodent Tracking13 Mar 2025 0 repositories listed
-
Visual and Text Prompt Segmentation: A Novel Multi-Model Framework for Remote Sensing10 Mar 2025 0 repositories listed
-
SAQ-SAM: Semantically-Aligned Quantization for Segment Anything Model9 Mar 2025 0 repositories listed
-
Show and Tell: Visually Explainable Deep Neural Nets via Spatially-Aware Concept Bottleneck Models27 Feb 2025 0 repositories listed
-
Few-Shot Adaptation of Training-Free Foundation Model for 3D Medical Image Segmentation15 Jan 2025 0 repositories listed
-
Segment to Recognize Robustly -- Enhancing Recognition by Image Decomposition24 Nov 2024 0 repositories listed
-
Assessing Foundational Medical 'Segment Anything' (Med-SAM1, Med-SAM2) Deep Learning Models for Left Atrial Segmentation in 3D LGE MRI8 Nov 2024 0 repositories listed
-
Zero-Shot Pupil Segmentation with SAM 2: A Case Study of Over 14 Million Images11 Oct 2024 0 repositories listed
-
Prompt-and-Transfer: Dynamic Class-aware Enhancement for Few-shot Segmentation16 Sep 2024 0 repositories listed
-
PaveSAM Segment Anything for Pavement Distress11 Sep 2024 0 repositories listed
-
Image-to-Lidar Relational Distillation for Autonomous Driving Data1 Sep 2024 0 repositories listed
-
SAM-SP: Self-Prompting Makes SAM Great Again22 Aug 2024 0 repositories listed
-
Enforcing View-Consistency in Class-Agnostic 3D Segmentation Fields19 Aug 2024 0 repositories listed
-
SAM 2 in Robotic Surgery: An Empirical Evaluation for Robustness and Generalization in Surgical Video Segmentation8 Aug 2024 0 repositories listed
-
DiNO-Diffusion. Scaling Medical Diffusion via Self-Supervised Pre-Training16 Jul 2024 0 repositories listed
-
PanopticRecon: Leverage Open-vocabulary Instance Segmentation for Zero-shot Panoptic Reconstruction1 Jul 2024 0 repositories listed
-
23 Jun 2024 0 repositories listed Syntology 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
Boosting Medical Image Classification with Segmentation Foundation Model16 Jun 2024 0 repositories listed
-
Interpreting the Second-Order Effects of Neurons in CLIP6 Jun 2024 0 repositories listed
-
Open-Vocabulary SAM3D: Towards Training-free Open-Vocabulary 3D Scene Understanding24 May 2024 0 repositories listed
-
SAM3D: Zero-Shot Semi-Automatic Segmentation in 3D Medical Images with the Segment Anything Model10 May 2024 0 repositories listed
-
Performance Evaluation of Segment Anything Model with Variational Prompting for Application to Non-Visible Spectrum Imagery18 Apr 2024 0 repositories listed
Syntology lines on 20 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