Segment Anything Model

Follow this topic Ask about this topic

Recent momentum

-57%

3 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

1 new paper

A weekly snapshot of new work published in Segment Anything Model.

70 papers

Latest in Segment Anything Model

Browse all topics →

PSMP-CLIP: Patch-Prompt SAM and Multi-Semantic Prompting for CLIP-Based Zero-Shot Anomaly Detection
Sep 15, 2026Xuezhi Xiang, Guanghao Wu, Heqi Xiang +4Zero-Shot Anomaly Detection Few-Shot Segmentation
Spectral Adapters for Segment Anything Model-based Segmentation of Colorectal Liver Metastases in Computed Tomography
Sep 11, 2026Ramtin Mojtahedi, Mohammad Hamghalam, Jacob J. Peoples +6Lesion Segmentation Segment Anything Model
Zero-Shot 3D Plant Organ Segmentation with SAM3 and Semantic NeRFs
Sep 7, 2026Andreas Gilson, Laura Hennig, Peter Pietrzyk3D Semantic Segmentation 3D Plant Phenotyping
VOS-Agent: The 1st Place Solution for the 8th LSVOS Challenge (MOSEv2 Track)
Aug 13, 2026Canyang Wu, Jinrong Zhang, Xusheng He +3Video Object Segmentation Multi-Object Tracking
Toward Mask Annotation-Free Surgical Instrument Segmentation from Endoscopic Images Using Text-Prompted Segment Anything Model 3 (SAM3)
Aug 9, 2026Nakul Poudel, Richard Simon, Cristian A. LinteSegment Anything Model Medical Image Segmentation
Universal Concept Disruption for SAM3 Image Segmentation
Aug 6, 2026Hao Wang, Yuxuan Zhang, Wei YangSegment Anything Model
EOVSAM: Efficient Open-Vocabulary Segmentation with SAM 3 in One Pass
Aug 3, 2026Haomin Peng, Yongkang Li, Zhaoxiang Liu +4Open-Vocabulary Segment Anything Model
Models as Tools: An Agentic Coordination Framework for Unified Multimodal Visual Tracking
Aug 1, 2026Wenrui Cai, Yuzhe Li, Qingjie Liu +1Multi-Object Tracking Adversarial Motion Priors
SAM+D: Parameter-Efficient Dimensional Lifting of SAM-Family Models via Depth-Routed LoRA and Depth Shifting
Jul 31, 2026Yu Song, Hao Sun, Shiyu Teng +2Segment Anything Model 3D Semantic Segmentation
ZMIS-SAM: Segment Anything Model Enhanced with Wavelet Transform for Zooplankton Microscopy Image Instance Segmentation
Jul 30, 2026Dekun Yuan, Zhongwei Li, Zheng Qiao +1In-Situ Plankton Classifiers Segment Anything Model
Parameter-Efficient Adaptation of SAM3 for Prompt-Driven Surgical Concept Segmentation
Jul 26, 2026Changjing Liu, Yiming Huang, Beilei Cui +5Segment Anything Model Few-Shot Medical Image Segmentation
Farmland Extent and Visible Boundary Mapping from 1 m NAIP Imagery Using Residual U-Net and Text-Prompted SAM 3 Refinement
Jul 24, 2026Mohammadreza Narimani, Vikram Anand, Parastoo FarajpoorU-Net Red-Green-Blue
Lean-SAM2: Target-Anchored Memory and Encoder Acceleration for SAM2
Jul 22, 2026Xudong Ouyang, Wenlun Zhang, Yimin Xu +2Segment Anything Model Cross-Attention
SAMRI-3D: Adapting SAM2 for 3D MRI Segmentation with Global Volume Tokens
Jul 20, 2026Zhao Wang, Wei Dai, Hongfu Sun +2Magnetic Resonance Imaging Segment Anything Model
Digital measurement of droplet flame diameter in microgravity combustion images using Segment Anything Model 2 with automatic prompt selection
Jul 18, 2026Minghui Xu, Chaoyi Zhou, Aaron P. Cecil +3Flames Combustion Control
ViPSAM: Visual Prompting Medical Image Segmentation Using Segment Anything Model
Jul 15, 2026San Lee, Nalee Kim, Jeong Il Yu +2Few-Shot Medical Image Segmentation Lesion Segmentation
SARFA: Segment Anything with Radiomic Feature Alignment
Jul 14, 2026Tyler Ward, Abdullah ImranMedical Image Segmentation Radiomics
MobileSAM2: Lightweight Segment Anything for Spatial Intelligence
Jul 14, 2026Kai Jiang, Jiaxing Huang, Jingyi Zhang +5Mobilenetv2 Segment Anything Model
Semantic-Edge Response Decoding of SAM3 for Zero-Shot Crack Segmentation
Jul 14, 2026Shipeng Liu, Zhanping Song, Liang Zhao +1Segment Anything Model Pixel-Level Annotation
Promptable Concept Segmentation from Above: Evaluating SAM 3's Zero-Shot and One-Shot Capabilities in Remote Sensing
Jul 10, 2026Mohammad Dabaja, Turgay CelikFew-Shot Segmentation Segment Anything Model
SAM-MT: Real-Time Interactive Multi-Target Video Segmentation
Jul 9, 2026Ruiqi Shen, Chang Liu, Henghui DingVideo Object Segmentation Multi-Object Tracking
An Edge-aware Prompt-enhanced SAM for Ultrasound Image Segmentation
Jul 8, 2026Wenhao Li, Fangyi Liu, Bo DuUltrasound Segment Anything Model
HPR-SAM: Hierarchical Probabilistic Representation Learning for Prompt-free SAM-based Medical Image Segmentation
Jul 8, 2026Yingzhen Hu, Yiheng Zhong, Keying Zhu +5Few-Shot Medical Image Segmentation Segment Anything Model
G $^2$ TAM: Geometry Grounded Track Anything Model
Jul 4, 2026Chenming Zhu, Peizhou Cao, Jingli Lin +5Video Object Segmentation Spatial Reasoning
Exploring SAM Supervision for Fine-Grained UAV Target Segmentation under Data Scarcity
Jul 4, 2026Le-Anh TranPseudo-Labeling Segment Anything Model
Dual-Adaptive SAM3: Hierarchical Routing over Low-Rank Expert Layers for Parameter-Efficient Medical Image Segmentation
Jun 30, 2026Ying Chen, Jinyue Li, Kun Wang +2Few-Shot Medical Image Segmentation Medical Image Segmentation
Temporal-Emerged Prompting for Segment Anything in Multiframe Infrared Small Target Detection
Jun 26, 2026Yinghui Xing, Donghao Chu, Shizhou Zhang +1Infrared Small Target Detection Feature Pyramid Networks
Mask to Concept: Auto-Promptable SAM3 via Efficient Test-Time Concept Embedding Search for Few-Shot Annotation
Jun 25, 2026Quan Zhou, Shaoqing Zhai, Qiang Hu +3Few-Shot Medical Image Segmentation Segment Anything Model
Concept Alignment Contrast and Long-Short Prompt Memory for Test-Time Adaptation of SAM3 in Medical Image Segmentation
Jun 22, 2026Yubo Zhou, Jianghao Wu, Ping Ye +2Few-Shot Medical Image Segmentation Medical Image Segmentation
Prompt-Calibrated SAM 3 for Open-Vocabulary Remote Sensing Semantic Segmentation
Jun 20, 2026Yanghui Song, Nanqing Liu, Haonan Yin +3Remote Sensing Image Segmentation Remote Sensing
SARIF: Segment Anything for Robust Image Forensics
Jun 19, 2026Dong-Hyun Moon, Ju-Hyeon Nam, Sang-Chul LeeFace Forgery Detection Multimedia Forensics
SAM3 Self-Distillation for Fine-Grained GOOSE 2D Semantic Segmentation
Jun 18, 2026Xuesong WangDense Semantic Segmentation Segment Anything Model
Domain-Guided Prompting of the Segment Anything Model for Seismic Interpretation: The Role of Attributes, Visualization, and Hybrid Prompts
Jun 14, 2026Aniq Ahmad, Heather Bedle, Ahmad MustafaFull Waveform Inversion Few-Shot Segmentation
Parameter-Efficient Adaptation of SAM 3 for Automated ITV Generation from 4DCT Images
Jun 14, 2026Changwoo SongRadiotherapy Segment Anything Model
Don't waste SAM
Jun 9, 2026Nermeen Abou Baker, Uwe HandmannSegment Anything Model Waste
Inside the Latent Flow: Causal Deciphering of Attention Dynamics in Audio Separation Foundation Models
Jun 8, 2026Yuxuan Chen, Haoyuan Yu, Peize HeSpeech Separation Audio
Where Does Texture Evidence Live in SAM? Features, Proposal Masks, and Texture Segmentation
Jun 7, 2026Nadav Orenstein, Aviad Cohen Zada, Shai Avidan +1Segment Anything Model Frozen Representations
SAMatcher: Co-Visibility Modeling with Segment Anything for Robust Feature Matching
Jun 2, 2026Xu Pan, Qiyuan Ma, Mingyue Dong +3Feature Matching Segment Anything Model
SAM for Robust Mitochondria Instance Segmentation in Fluorescence Microscopy
May 29, 2026Suyog Jadhav, Dilip K. Prasad, Krishna AgarwalMicroscopy Segment Anything Model
Turbulence-Robust Dynamic Object Segmentation with Multi-Signal Priors and SAM2 Refinement
May 28, 2026Bolian Peng, Ying Tang, Xu Liu +2Turbulence Segment Anything Model
Zero-Shot Object Re-Identification in Egocentric Kitchen Videos via Multi-Stage SAM3 Feature Fusion
May 25, 2026Dmytro Klepachevskyi, Alexander Wong, Sirisha Rambhatla +1Re-Identification Feature Pyramid Networks
Weakly Supervised Camouflaged Object Detection Based on the SAM Model and Mask Guidance
May 25, 2026Xia Li, Xinran Liu, Lin Qi +1Camouflaged Object Detection Object Detection
BED-SAM2: Boundary-Enhanced-Depth SAM2 via Monocular Geometric Priors
May 24, 2026Tyler Rust, Dara McNally, Kyle O'Donnell +2Camouflaged Object Detection Feature Pyramid Networks
CLIP-Guided SAM: Parameter-Efficient Semantic Conditioning for Promptable Segmentation
May 24, 2026Shayan Jalilian, Abdul BaisSegment Anything Model Visual In-Context Learning
Segment Anything with Motion, Geometry, and Semantic Adaptation for Complex Nonlinear Visual Object Tracking
May 21, 2026Deyi Zhu, Yuji Wang, Yong Liu +4Multi-Object Tracking Video Object Segmentation
Lighting-aware Unified Model for Instance Segmentation
May 19, 2026Qisai Liu, Alloy Das, Zhanhong Jiang +4Illumination Segment Anything Model
Learning Lifted Action Models from Traces with Minimal Information About Actions and States
May 18, 2026Jonas Gösgens, Niklas Jansen, Hector GeffnerPartial Observability Action Space
TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model
May 18, 2026Zhaoyuan Ding, Yijing Yang, Han Shu +1Video Object Segmentation Segment Anything Model
SparseSAM: Structured Sparsification of Activations in Segment Anything Models
May 17, 2026Hoai-Chau Tran, Chi H. Nguyen, Duy M. H. Nguyen +3Segment Anything Model Token Compression
CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything Model
May 16, 2026Houji Wen, Jiangyong Yu, Jun Li +1Weight-Only Quantization Quantization
Robust Prior-Guided Segmentation for Editable 3D Gaussian Splatting
May 15, 2026Raushan Joshi, Jean-Yves Guillemaut3D Semantic Segmentation 3D Gaussian Splats
Segment Anything with Robust Uncertainty-Accuracy Correlation
May 11, 2026Hongyou Zhou, Marc Toussaint, Ling Shao +1Few-Shot Segmentation Pixel-Level Prediction
Frequency Adapter with SAM for Generalized Medical Image Segmentation
May 11, 2026Phuoc-Nguyen Bui, Van-Nguyen Pham, Duc-Tai Le +2Medical Image Segmentation Multimodal Domain Generalization
Prompt-Free and Efficient SAM2 Adaptation for Biomedical Semantic Segmentation via Dual Adapters
May 7, 2026Hinako Mitsuoka, Kazuhiro HottaFew-Shot Medical Image Segmentation Medical Image Segmentation
Example-Based Object Detection
May 6, 2026ZhiXin SunOpen-Vocabulary Object Detection Object Detection
SIAM: Head and Brain MRI Segmentation from Few High-Quality Templates via Synthetic Training
May 4, 2026Romain Valabregue, Ines Khemir, Eric Badinet +3Segment Anything Model Synthetic Training Data
Remote SAMsing: From Segment Anything to Segment Everything
Apr 30, 2026Osmar Luiz Ferreira de Carvalho, Osmar Abílio de Carvalho Júnior, Anesmar Olino de Albuquerque +1Remote Sensing Image Segmentation Few-Shot Segmentation
Lightweight Distillation of SAM 3 and DINOv3 for Edge-Deployable Individual-Level Livestock Monitoring and Longitudinal Visual Analytics
Apr 29, 2026Haiyu Yang, Miel HostensDinov3 Df-Wild Dataset
SAMamba3D: adapting Segment Anything for generalizable 3D segmentation of multiphase pore-scale images
Apr 29, 2026Rui Zhang, Xianzhi Song, Linqi Zhu +33D Semantic Segmentation Segment Anything Model
Robustness Evaluation of a Foundation Segmentation Model Under Simulated Domain Shifts in Abdominal CT: Implications for Health Digital Twin Deployment
Apr 28, 2026Sanghati BasuMedical Imaging Segment Anything Model

Sep 15, 2026 · cs.CVJ/K move · Enter open · S save

PSMP-CLIP: Patch-Prompt SAM and Multi-Semantic Prompting for CLIP-Based Zero-Shot Anomaly Detection

Xuezhi Xiang, Guanghao Wu, Heqi Xiang, Jiayao Liu+3

Information and Communication Engineering, Harbin Engineering University, Harbin, China · Key Laboratory of Advanced Marine Communication and Information Technology, Harbin, China · Department of Computer Science, University of Toronto, Toronto, ON M5S 2E4, Canada · The Department of Computer Science, Kanagawa University, Kanagawa, 221-8686, Japan

Zero-shot anomaly detection aims to localize anomalies without target-domain samples. Existing CLIP-based methods suffer from coarse anomaly maps and limited semantic prompts. We propose PSMP-CLIP, integrating patch-prompt SAM2 segmentation (PPSS) and multi-semantic guided prompt regularization (MSGPR). PPSS samples prompts directly from intermediate patch features, avoiding threshold drift and guiding SAM2 to produce precise masks. MSGPR uses multiple learnable prompts constrained by semantic anchors to preserve generalization. Experiments on 14 datasets show highly competitive performance, achieving the best pixel-level AUROC on MVTec AD, BTAD, DTD-Synthetic, CVC-ClinicDB, TN3K, Endo, and Kvasir.

Zero-Shot Anomaly Detection Few-Shot Segmentation Segment Anything Model Regularization Techniques

Open paper Ask about it PDF