Methods › Computer Vision › Image Segmentation Models › SAM
Segment Anything Model
SAM
Introduced by Alexander Kirillov et al. in Segment Anything
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The archive carries no description for this method.
In Syntology about another paper, arXiv:2308.09949: no code under this exact name (no_code; paper_only). About another paper: this answer is about arXiv:2308.09949, while the archive credits arXiv:2304.02643, so it does not say whether this method has code.
From the lookup's note on this name: The same name also belongs to “Sharpness-Aware Minimization (SAM)”, a method in the paper “Sharpness-Aware Minimization for Efficiently Improving Generalization” (arXiv:2010.01412, 2,067 citations), which the lookup finds cited far more than the paper this answer is about (10 citations), so this answer may be about a different sense of the name. For arXiv:2010.01412: its page on this site · ask the lookup about it.
Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.
- Sparse SAM (SSAM) · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Sparse SAM (SSAM)')
Origin paper of this answer, arXiv:2308.09949 (its page on Syntology).
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 905 · with a code link: 454 · where Syntology ran a sample: 146 (123 with a run with no instrument failure, 23 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (146 of 905 tagged: 123 with a run with no instrument failure, 23 where every run was a failure of Syntology's instrument)
Page 1 of 10: papers 1 to 100 of 905, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “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. It is per sample and not a correctness claim. 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; “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.
-
SAMST: A Transformer framework based on SAM pseudo label filtering for remote sensing semi-supervised semantic segmentation 16 Jul 2025 · 0 repositories · arXiv:2507.11994
-
Are Vision Foundation Models Ready for Out-of-the-Box Medical Image Registration? 15 Jul 2025 · 1 repository · arXiv:2507.11569
-
DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation 14 Jul 2025 · 1 repository · arXiv:2507.10118
-
Test-Time Canonicalization by Foundation Models for Robust Perception 14 Jul 2025 · 1 repository · arXiv:2507.10375Syntology official (archive's flag): 5 ran · 5 ran (of which 1 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) · 0 unverified (of 5 harvested samples)
-
Landmark Detection for Medical Images using a General-purpose Segmentation Model 13 Jul 2025 · 0 repositories · arXiv:2507.11551
-
Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges 13 Jul 2025 · 0 repositories · arXiv:2507.09562
-
Calibrated and Robust Foundation Models for Vision-Language and Medical Image Tasks Under Distribution Shift 12 Jul 2025 · 0 repositories · arXiv:2507.09222
-
Compress Any Segment Anything Model (SAM) 11 Jul 2025 · 1 repository · arXiv:2507.08765
-
SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation 10 Jul 2025 · 1 repository · arXiv:2507.07883Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
Seg-Wild: Interactive Segmentation based on 3D Gaussian Splatting for Unconstrained Image Collections 10 Jul 2025 · 1 repository · arXiv:2507.07395
-
Rethinking Layered Graphic Design Generation with a Top-Down Approach 8 Jul 2025 · 0 repositories · arXiv:2507.05601
-
RSRefSeg 2: Decoupling Referring Remote Sensing Image Segmentation with Foundation Models 8 Jul 2025 · 1 repository · arXiv:2507.06231
-
ViRefSAM: Visual Reference-Guided Segment Anything Model for Remote Sensing Segmentation 3 Jul 2025 · 0 repositories · arXiv:2507.02294
-
DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation 29 Jun 2025 · 0 repositories · arXiv:2506.23104Syntology 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)
-
Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval 28 Jun 2025 · 0 repositories · arXiv:2506.22864
-
Selecting and Merging: Towards Adaptable and Scalable Named Entity Recognition with Large Language Models 28 Jun 2025 · 1 repository · arXiv:2506.22813
-
ProSAM: Enhancing the Robustness of SAM-based Visual Reference Segmentation with Probabilistic Prompts 27 Jun 2025 · 0 repositories · arXiv:2506.21835
-
TASeg: Text-aware RGB-T Semantic Segmentation based on Fine-tuning Vision Foundation Models 27 Jun 2025 · 0 repositories · arXiv:2506.21975
-
Detection of Breast Cancer Lumpectomy Margin with SAM-incorporated Forward-Forward Contrastive Learning 26 Jun 2025 · 1 repository · arXiv:2506.21006
-
AI-Driven MRI-based Brain Tumour Segmentation Benchmarking 25 Jun 2025 · 0 repositories · arXiv:2506.20786
-
Open-Vocabulary Camouflaged Object Segmentation with Cascaded Vision Language Models 24 Jun 2025 · 1 repository · arXiv:2506.19300
-
MedSeg-R: Medical Image Segmentation with Clinical Reasoning 23 Jun 2025 · 0 repositories · arXiv:2506.18669
-
SafeClick: Error-Tolerant Interactive Segmentation of Any Medical Volumes via Hierarchical Expert Consensus 23 Jun 2025 · 0 repositories · arXiv:2506.18404
-
Segment Anything for Satellite Imagery: A Strong Baseline and a Regional Dataset for Automatic Field Delineation 19 Jun 2025 · 1 repository · arXiv:2506.16318
-
MorphSAM: Learning the Morphological Prompts from Atlases for Spine Image Segmentation 16 Jun 2025 · 0 repositories · arXiv:2506.13094
-
Sharpness-Aware Machine Unlearning 16 Jun 2025 · 0 repositories · arXiv:2506.13715Syntology 1 ran (of which 1 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) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample)
-
Generalist Models in Medical Image Segmentation: A Survey and Performance Comparison with Task-Specific Approaches 12 Jun 2025 · 0 repositories · arXiv:2506.10825
-
SRPL-SFDA: SAM-Guided Reliable Pseudo-Labels for Source-Free Domain Adaptation in Medical Image Segmentation 11 Jun 2025 · 1 repository · arXiv:2506.09403
-
Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation 7 Jun 2025 · 1 repository · arXiv:2506.06818
-
Bringing SAM to new heights: Leveraging elevation data for tree crown segmentation from drone imagery 5 Jun 2025 · 0 repositories · arXiv:2506.04970
-
Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos 5 Jun 2025 · 1 repository · arXiv:2506.05302Syntology 4 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; 1 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples) · 1 pointer-only (licence)
-
SAM-aware Test-time Adaptation for Universal Medical Image Segmentation 5 Jun 2025 · 0 repositories · arXiv:2506.05221
-
GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation 3 Jun 2025 · 0 repositories · arXiv:2506.02882
-
Hierarchical Self-Prompting SAM: A Prompt-Free Medical Image Segmentation Framework 3 Jun 2025 · 0 repositories · arXiv:2506.02854
-
SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost 2 Jun 2025 · 1 repository · arXiv:2506.01304Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples)
-
Leadership Assessment in Pediatric Intensive Care Unit Team Training 30 May 2025 · 0 repositories · arXiv:2505.24389
-
LightSAM: Parameter-Agnostic Sharpness-Aware Minimization 30 May 2025 · 0 repositories · arXiv:2505.24399
-
Towards Understanding The Calibration Benefits of Sharpness-Aware Minimization 29 May 2025 · 0 repositories · arXiv:2505.23866
-
Adapting Segment Anything Model for Power Transmission Corridor Hazard Segmentation 28 May 2025 · 1 repository · arXiv:2505.22105
-
InfoSAM: Fine-Tuning the Segment Anything Model from An Information-Theoretic Perspective 28 May 2025 · 0 repositories · arXiv:2505.21920
-
MIAS-SAM: Medical Image Anomaly Segmentation without thresholding 28 May 2025 · 0 repositories · arXiv:2505.22762
-
Geometric Feature Prompting of Image Segmentation Models 27 May 2025 · 0 repositories · arXiv:2505.21644
-
RoBiS: Robust Binary Segmentation for High-Resolution Industrial Images 27 May 2025 · 1 repository · arXiv:2505.21152
-
Domain and Task-Focused Example Selection for Data-Efficient Contrastive Medical Image Segmentation 25 May 2025 · 1 repository · arXiv:2505.19208
-
FHGS: Feature-Homogenized Gaussian Splatting 25 May 2025 · 0 repositories · arXiv:2505.19154
-
Focus on What Matters: Enhancing Medical Vision-Language Models with Automatic Attention Alignment Tuning 24 May 2025 · 0 repositories · arXiv:2505.18503
-
From Flight to Insight: Semantic 3D Reconstruction for Aerial Inspection via Gaussian Splatting and Language-Guided Segmentation 23 May 2025 · 0 repositories · arXiv:2505.17402
-
Assessing the generalization performance of SAM for ureteroscopy scene understanding 22 May 2025 · 0 repositories · arXiv:2505.17210
-
TextureSAM: Towards a Texture Aware Foundation Model for Segmentation 22 May 2025 · 0 repositories · arXiv:2505.16540
-
gen2seg: Generative Models Enable Generalizable Instance Segmentation 21 May 2025 · 0 repositories · arXiv:2505.15263
-
TAGS: 3D Tumor-Adaptive Guidance for SAM 21 May 2025 · 0 repositories · arXiv:2505.17096
-
UWSAM: Segment Anything Model Guided Underwater Instance Segmentation and A Large-scale Benchmark Dataset 21 May 2025 · 1 repository · arXiv:2505.15581
-
Unlocking the Power of SAM 2 for Few-Shot Segmentation 20 May 2025 · 1 repository · arXiv:2505.14100Syntology official (archive's flag): 1 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) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
Industrial Synthetic Segment Pre-training 19 May 2025 · 0 repositories · arXiv:2505.13099
-
AoP-SAM: Automation of Prompts for Efficient Segmentation 17 May 2025 · 0 repositories · arXiv:2505.11980
-
iSegMan: Interactive Segment-and-Manipulate 3D Gaussians 17 May 2025 · 0 repositories · arXiv:2505.11934
-
Unifying Segment Anything in Microscopy with Multimodal Large Language Model 16 May 2025 · 1 repository · arXiv:2505.10769
-
Promoting SAM for Camouflaged Object Detection via Selective Key Point-based Guidance 14 May 2025 · 0 repositories · arXiv:2505.09123
-
Leveraging Segment Anything Model for Source-Free Domain Adaptation via Dual Feature Guided Auto-Prompting 13 May 2025 · 2 repositories · arXiv:2505.08527
-
SLAG: Scalable Language-Augmented Gaussian Splatting 12 May 2025 · 0 repositories · arXiv:2505.08124
-
Causal Prompt Calibration Guided Segment Anything Model for Open-Vocabulary Multi-Entity Segmentation 10 May 2025 · 1 repository · arXiv:2505.06524
-
Improving Generalization of Medical Image Registration Foundation Model 10 May 2025 · 1 repository · arXiv:2505.06527
-
Adapting a Segmentation Foundation Model for Medical Image Classification 9 May 2025 · 0 repositories · arXiv:2505.06217
-
BrainSegDMlF: A Dynamic Fusion-enhanced SAM for Brain Lesion Segmentation 9 May 2025 · 0 repositories · arXiv:2505.06133
-
Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model 8 May 2025 · 0 repositories · arXiv:2505.04861
-
Pro2SAM: Mask Prompt to SAM with Grid Points for Weakly Supervised Object Localization 8 May 2025 · 0 repositories · arXiv:2505.04905
-
UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model 8 May 2025 · 1 repository · arXiv:2505.05049Syntology 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)
-
Sharpness-Aware Minimization with Z-Score Gradient Filtering for Neural Networks 5 May 2025 · 0 repositories · arXiv:2505.02369
-
Segment Any RGB-Thermal Model with Language-aided Distillation 4 May 2025 · 0 repositories · arXiv:2505.01950
-
Accelerating Volumetric Medical Image Annotation via Short-Long Memory SAM 2 3 May 2025 · 2 repositories · arXiv:2505.01854
-
Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification 3 May 2025 · 0 repositories · arXiv:2505.01660
-
AI-Driven Segmentation and Analysis of Microbial Cells 1 May 2025 · 0 repositories · arXiv:2505.00578
-
LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics 30 Apr 2025 · 1 repository · arXiv:2504.21716Syntology official (archive's flag): 1 ran · 1 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; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
SAM4EM: Efficient memory-based two stage prompt-free segment anything model adapter for complex 3D neuroscience electron microscopy stacks 30 Apr 2025 · 1 repository · arXiv:2504.21544
-
RadSAM: Segmenting 3D radiological images with a 2D promptable model 29 Apr 2025 · 0 repositories · arXiv:2504.20837
-
SAM-Guided Robust Representation Learning for One-Shot 3D Medical Image Segmentation 29 Apr 2025 · 0 repositories · arXiv:2504.20501
-
Prompt-Tuning SAM: From Generalist to Specialist with only 2048 Parameters and 16 Training Images 23 Apr 2025 · 0 repositories · arXiv:2504.16739
-
RGB-D Video Object Segmentation via Enhanced Multi-store Feature Memory 23 Apr 2025 · 0 repositories · arXiv:2504.16471
-
AffordanceSAM: Segment Anything Once More in Affordance Grounding 22 Apr 2025 · 0 repositories · arXiv:2504.15650
-
DINOv2-powered Few-Shot Semantic Segmentation: A Unified Framework via Cross-Model Distillation and 4D Correlation Mining 22 Apr 2025 · 0 repositories · arXiv:2504.15669
-
EmoSEM: Segment and Explain Emotion Stimuli in Visual Art 20 Apr 2025 · 0 repositories · arXiv:2504.14658
-
Contour Field based Elliptical Shape Prior for the Segment Anything Model 17 Apr 2025 · 0 repositories · arXiv:2504.12556
-
Putting the Segment Anything Model to the Test with 3D Knee MRI - A Comparison with State-of-the-Art Performance 17 Apr 2025 · 1 repository · arXiv:2504.13340
-
SAM-Based Building Change Detection with Distribution-Aware Fourier Adaptation and Edge-Constrained Warping 17 Apr 2025 · 0 repositories · arXiv:2504.12619
-
CAGS: Open-Vocabulary 3D Scene Understanding with Context-Aware Gaussian Splatting 16 Apr 2025 · 0 repositories · arXiv:2504.11893
-
DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency 16 Apr 2025 · 1 repository · arXiv:2504.12080
-
Mixture-of-Shape-Experts (MoSE): End-to-End Shape Dictionary Framework to Prompt SAM for Generalizable Medical Segmentation 13 Apr 2025 · 0 repositories · arXiv:2504.09601
-
AerOSeg: Harnessing SAM for Open-Vocabulary Segmentation in Remote Sensing Images 12 Apr 2025 · 0 repositories · arXiv:2504.09203
-
FindAnything: Open-Vocabulary and Object-Centric Mapping for Robot Exploration in Any Environment 11 Apr 2025 · 0 repositories · arXiv:2504.08603
-
SynthFM: Training Modality-agnostic Foundation Models for Medical Image Segmentation without Real Medical Data 11 Apr 2025 · 0 repositories · arXiv:2504.08177
-
ZS-VCOS: Zero-Shot Outperforms Supervised Video Camouflaged Object Segmentation 10 Apr 2025 · 1 repository · arXiv:2505.01431
-
econSG: Efficient and Multi-view Consistent Open-Vocabulary 3D Semantic Gaussians 8 Apr 2025 · 0 repositories · arXiv:2504.06003
-
S^4M: Boosting Semi-Supervised Instance Segmentation with SAM 7 Apr 2025 · 0 repositories · arXiv:2504.05301
-
Performance Analysis of Deep Learning Models for Femur Segmentation in MRI Scan 5 Apr 2025 · 0 repositories · arXiv:2504.04066
-
UCS: A Universal Model for Curvilinear Structure Segmentation 5 Apr 2025 · 0 repositories · arXiv:2504.04034
-
APSeg: Auto-Prompt Model with Acquired and Injected Knowledge for Nuclear Instance Segmentation and Classification 3 Apr 2025 · 0 repositories · arXiv:2504.02222
-
F-ViTA: Foundation Model Guided Visible to Thermal Translation 3 Apr 2025 · 1 repository · arXiv:2504.02801
-
BiSeg-SAM: Weakly-Supervised Post-Processing Framework for Boosting Binary Segmentation in Segment Anything Models 2 Apr 2025 · 0 repositories · arXiv:2504.01452
-
AI-Assisted Colonoscopy: Polyp Detection and Segmentation using Foundation Models 31 Mar 2025 · 1 repository · arXiv:2503.24138
-
SmartScan: An AI-based Interactive Framework for Automated Region Extraction from Satellite Images 31 Mar 2025 · 0 repositories · arXiv:2504.00200
Tasks archive 2025-07-28
20 shown of 438 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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