-
Customized segment anything model for medical image segmentation
The dataset used for medical image segmentation. -
Segment Anything Model (SAM) for Medical Images
Three publicly available medical imaging datasets: Breast Ultrasound Scan Images (BUSI), CVC-ClinicDB, and ISIC-2016. -
USD: Unknown Sensitive Detector Empowered by Decoupled Objectness and Segment...
Open World Object Detection (OWOD) is a novel and challenging computer vision task that enables object detection with the ability to detect unknown objects. -
EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM
EdgeSAM is an accelerated variant of the Segment Anything Model (SAM) optimized for efficient execution on edge devices with minimal compromise in performance. -
Robustness of SAM: Segment Anything under corruptions and beyond
This work investigates the robustness of SAM to corruptions and adversarial attacks. -
Segment Anything Model (SAM)
SAM is a foundation model in computer vision that can segment anything. -
Black-box Targeted Adversarial Attack on Segment Anything (SAM)
This work conducts the first yet comprehensive study on TAA on SAM in a black-box setup, assuming no access to prompt and model. -
Radiation Oncology Segment Anything Model (SAM) Dataset
The dataset used in this study for evaluating the performance of the Segment Anything Model (SAM) in clinical radiotherapy. -
COSMOS 553K
The COSMOS 553K dataset is a large-scale medical image segmentation dataset. -
Masking Hyperspectral Imaging Data with Pretrained Models
The proposed processing pipeline encom- passes two fundamental parts: regions of interest mask generation, followed by the application of hyperspectral data processing... -
Task-Aware Low-Rank Adaptation of Segment Anything Model
The Segment Anything Model (SAM) has been proven to be a powerful foundation model for image segmentation tasks, which is an important task in computer vision. However, the... -
UVOSAM: A Mask-free Paradigm for Unsupervised Video Object Segmentation via S...
Unsupervised video object segmentation has made significant progress in recent years, but the manual annotation of video mask datasets is expensive and limits the diversity of... -
DMControl and Adroit
The dataset used in the paper is a collection of tasks from DMControl and Adroit, with 8 tasks from DMControl and 3 tasks from Adroit. -
Segment Anything Model
The dataset used in this paper is the Meta Research's Segment Anything Model (SAM) dataset, which consists of images.
