Segment-anything related awesome extensions/projects/repos.

RobustSAM: Segment Anything Robustly on Degraded Images (CVPR 2024 Highlight)

Collect some resource about Segment Anything (SAM), including the latest papers and demo

LIME-SAM aims to create an Explainable Artificial Intelligence (XAI) framework for image classification using LIME (Local Interpretable Model-agnostic Explanations) as the base algorithm, with the super-pixel method replaced by Segment Anything by Meta (SAM).

Hey! This repository consists of .ipynb fiies for different classifiers trained using google collab, some can be run on local machine and the python files are attached as well, a README is available as well for a more in-depth guide.

This repository is the result of an academic project at Ecole Centrale in Nantes, France, with my classmate @damien-gautier-nantes. The aim of this project was to evaluate the performance of universal segmentation models for segmenting cancerous lesions. The UniverSeg and Segment Anything (SAM) models were tested.

A computer vision Image Segmentation Project done using Segment Anything by Meta.AI & Yolo V8