Segment Anything Model (SAM) 部分报告汇总

随缘更新，很可能不全
标 [$✓$] 为推荐阅读的文章

---

原始论文：

• [link] [code] [April 5] [SAM]
  Segment Anything

---

• [link] [code] [Apr 9]
  Segment Anything Model (SAM) for Digital Pathology: Assess Zero-shot Segmentation on Whole Slide Imaging
  SAM在WSI图像上的实验

• [link] [code] [Apr 10]
  Can SAM Segment Anything? When SAM Meets Camouflaged Object Detection
  SAM在伪装目标检测上的实验

• [link] [code] [Apr 12]
  SAM Struggles in Concealed Scenes – Empirical Study on “Segment Anything”
  SAM在更多伪装任务以及医学任务(息肉分割，脑肿瘤分割)的实验

• [link] [code] [Apr 12] [$✓$]
  Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications
  SAM在更多现实分割任务(显著/伪装检测，医学分割，工业异常检测，遥感)的实验

• [link] [code] [Apr 13] [$✓$]
  Inpaint Anything: Segment Anything Meets Image Inpainting
  SAM与下游inpainting任务结合

• [link] [code] [Apr 15]
  Can SAM Segment Polyps
  SAM在息肉分割上的实验

• [link] [code] [Apr 17]
  When SAM Meets Medical Images: An Investigation of Segment Anything Model (SAM) on Multi-phase Liver Tumor Segmentation
  SAM在肝分割上的实验

• [link] [code] [Apr 18]
  Accuracy of Segment-Anything Model (SAM) in medical image segmentation tasks
  SAM在一些医学任务上的实验

• [link] [code] [Apr 18] [$✓$]
  SAM Fails to Segment Anything? – SAM-Adapter: Adapting SAM in Underperformed Scenes: Camouflage, Shadow, and More
  如何finetune SAM

• [link] [code] [Apr 21]
  Can SAM Count Anything? An Empirical Study on SAM Counting
  SAM在counting任务上的实验

• [link] [code] [Apr 22] [$✓$]
  Input Augmentation with SAM: Boosting Medical Image Segmentation with Segmentation Foundation Model
  SAM作为数据增强的手段

• [link] [code] [Apr 24] [$✓$]
  Segment Anything in Medical Images
  SAM+Box+Finetune以进行医学分割

• [link] [code] [Apr 25]
  Segment anything, from space?
  SAM在遥感任务上的实验

• [link] [code] [Apr 25]
  Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation
  SAM+Prompt+Lora以进行医学分割

• [link] [code] [Apr 25]
  Generalist Vision Foundation Models for Medical Imaging: A Case Study of Segment Anything Model on Zero-Shot Medical Segmentation
  SAM在一些医学任务上的实验

• [link] [code] [Apr 25]
  Application of Segment Anything Model for Civil Infrastructure Defect Assessment
  SAM在裂缝检测上的实验

• [link] [code] [Apr 25]
  Segment Anything in 3D with NeRFs
  SAM在NeRF上的实验

• [link] [code] [Apr 26] [$✓$]
  Learnable Ophthalmology SAM
  SAM+Prompt在眼底上的实验

• [link] [code] [Apr 26] [$✓$]
  Customized Segment Anything Model for Medical Image Segmentation
  SAM+LoRA在医学上的实验

• [link] [code] [Apr 28]
  SAM Meets Robotic Surgery: An Empirical Study in Robustness Perspective
  SAM在手术器械分割上的实验

• [link] [code] [Apr 28]
  SAM on Medical Images: A Comprehensive Study on Three Prompt Modes
  SAM在不同prompt下的性能比较

• [link] [code] [Apr 28]
  Exploring the Zero-Shot Capabilities of the Segment Anything Model (SAM) in 2D Medical Imaging: A Comprehensive Evaluation and Practical Guideline
  SAM在医学任务上的实验

• [link] [code] [Apr 29]
  Polyp-SAM: Transfer SAM for Polyp Segmentation
  Finetune SAM以获得SOTA性能

• [link] [code] [Apr 29]
  Segment Anything Model (SAM) Meets Glass: Mirror and Transparent Objects Cannot Be Easily Detected
  SAM在透明物体/玻璃上的实验

• [link] [code] [May 1]
  Attack-SAM: Towards Evaluating Adversarial Robustness of Segment Anything Model
  SAM与对抗攻击

• [link] [code] [May 2]
  An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems
  SAM与弱监督语义分割

• [link] [code] [May 3]
  AV-SAM: Segment Anything Model Meets Audio-Visual Localization and Segmentation
  SAM在Audio-Visual Localization上的实验

• [link] [code] [May 4] [$✓$]
  Personalize Segment Anything Model with One Shot
  One Shot SAM

• [link] [code] [May 5] [$✓$]
  How Segment Anything Model (SAM) Boost Medical Image Segmentation?
  SAM在医学领域的综述

• [link] [code] [May 9]
  Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentation
  SAM用于增强弱监督分割

• [link] [code] [May 10]
  An Empirical Study on the Robustness of the Segment Anything Model (SAM)
  SAM对图像扰动的鲁棒性

• [link] [code] [May 11]
  Can SAM Boost Video Super-Resolution?
  SAM与视频超分辨率

• [link] [code] [May 12]
  Knowledge distillation with Segment Anything (SAM) model for Planetary Geological Mapping
  SAM与Planetary Geological Mapping

• [link] [code] [May 12]
  A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering
  SAM综述

• [link] [code] [May 14]
  A Comprehensive Survey on Segment Anything Model for Vision and Beyond
  SAM综述

• [link] [code] [May 16]
  Leaf Only SAM: A Segment Anything Pipeline for Zero-Shot Automated Leaf Segmentation
  SAM用于树叶分割

• [link] [code] [May 17]
  Explain Any Concept: Segment Anything Meets Concept-Based Explanation
  SAM与可解释AI

• [link] [code] [May 21]
  BreastSAM: A Study of Segment Anything Model for Breast Tumor Detection in Ultrasound Images
  SAM与乳腺肿块检测

• [link] [code] [May 21]
  UVOSAM: A Mask-free Paradigm for Unsupervised Video Object Segmentation via Segment Anything Model
  SAM与视频分割

• [link] [code] [May 22]
  Restore Anything Pipeline: Segment Anything Meets Image Restoration
  SAM与图像修复

• [link] [code] [May 22]
  Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
  One shot SAM

• [link] [code] [May 25]
  On the Robustness of Segment Anything
  SAM鲁棒性

• [link] [code] [May 25]
  Interactive Segment Anything NeRF with Feature Imitation
  SAM与NeRF

• [link] [code] [May 26]
  Detect Any Shadow: Segment Anything for Video Shadow Detection
  SAM用于视频分割

• [link] [code] [June 2] [$✓$]
  Segment Anything in High Quality
  改进的高精度分割SAM

• [link] [code] [June 1] [$✓$]
  DeSAM: Decoupling Segment Anything Model for Generalizable Medical Image Segmentation
  修改SAM以供医学分割

• [link] [code] [June 1]
  SAM-helps-Shadow:When Segment Anything Model meet shadow removal
  SAM用于阴影移除

• [link] [code] [June 3]
  Segment Anything Meets Semantic Communication
  SAM与Semantic Communication

• [link] [code] [June 3]
  SAM3D: Zero-Shot 3D Object Detection via Segment Anything Model
  SAM与Zeroshot

• [link] [code] [June 5]
  USD: Unknown Sensitive Detector Empowered by Decoupled Objectness and Segment Anything Model
  SAM与Open World Object Detection

• [link] [code] [June 5]
  Calib-Anything: Zero-training LiDAR-Camera Extrinsic Calibration Method Using Segment Anything
  SAM用于相机校准

• [link] [code] [June 6]
  SAM3D: Segment Anything in 3D Scenes
  SAM用于3D分割

• [link] [code] [June 6]
  Matte Anything: Interactive Natural Image Matting with Segment Anything Models
  SAM用于抠图

• [link] [code] [June 17]
  Robustness of SAM: Segment Anything Under Corruptions and Beyond
  SAM鲁棒性

• [link] [code] [June 17] [$✓$]
  Enlighten Anything: When Segment Anything Model Meets Low-Light Image Enhancement
  SAM用于低光图像增强

• [link] [code] [June 20]
  Segment Anything Model (SAM) for Radiation Oncology
  SAM与医学

• [link] [code] [June 21] [$✓$]
  Fast Segment Anything
  提升SAM推理速度

• [link] [code] [June 21]
  Comparative Analysis of Segment Anything Model and U-Net for Breast Tumor Detection in Ultrasound and Mammography Images
  SAM与乳腺病灶分割

• [link] [code] [June 23]
  Robustness of Segment Anything Model (SAM) for Autonomous Driving in Adverse Weather Conditions
  SAM鲁棒性

• [link] [code] [June 24]
  Utilizing Segment Anything Model For Assessing Localization of GRAD-CAM in Medical Imaging
  SAM与GradCAM

• [link] [code] [June 25] [$✓$]
  Faster Segment Anything: Towards Lightweight SAM for Mobile Applications
  知识蒸馏SAM以轻量化

• [link] [code] [June 26] [$✓$]
  MedLSAM: Localize and Segment Anything Model for 3D Medical Images
  SAM与3D医学分割

• [link] [code] [June 27]
  Let Segment Anything Help Image Dehaze
  SAM与图像去雾

• [link] [code] [June 28]
  The Segment Anything Model (SAM) for Remote Sensing Applications: From Zero to One Shot
  SAM与遥感

• [link] [code] [June 29]
  Detect Any Deepfakes: Segment Anything Meets Face Forgery Detection and Localization
  微调SAM用于伪造监测

• [link] [code] [June 30]
  Topological Data Analysis Guided Segment Anything Model Prompt Optimization for Zero-Shot Segmentation in Biological Imaging
  SAM在医学领域的自动Prompt生成

• [link] [code] [July 3]
  RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation
  SAM与Referring Video Object Segmentation

• [link] [code] [July 3]
  SAMAug: Point Prompt Augmentation for Segment Anything Model
  增强SAM的Prompt

• [link] [code] [July 3]
  Segment Anything Meets Point Tracking
  SAM与Point Tracking

• [link] [code] [July 10] [$✓$]
  SAM-IQA: Can Segment Anything Boost Image Quality Assessment?
  SAM+图像质量评估

• [link] [code] [July 10] [$✓$]
  Semantic-SAM: Segment and Recognize Anything at Any Granularity
  复现SAM

• [link] [code] [July 12] [$✓$]
  SAM-Path: A Segment Anything Model for Semantic Segmentation in Digital Pathology
  引入辅助Encoder来嵌入任务特定信息，以供数字病理图像分割

• [link] [code] [July 15] [$✓$]
  Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments
  SAM与Open Scene Understanding