segment anything model
Segment Anything Model (SAM) refers to advanced models designed to detect and segment objects within images with the flexibility to adapt to various contexts, achieving higher accuracy in object delineation.
- Bringing SAM to new heights: leveraging elevation data for tree crown segmentation from drone imagery
- GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation
- GauSAM: Contour‑Guided 2D Gaussian Fields for Multi‑Scale Medical Image Segmentation with Segment Anything
- OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts
- SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning
- SAM2Flow: Interactive Optical Flow Estimation with Dual Memory for in vivo Microcirculation Analysis
- SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models
- Segment Anything Model Meets Semi-supervised Medical Image Segmentation: A Novel Perspective