UEmmanuel5/FirESAM: FirESAM v1.0.0

Zenodo (CERN European Organization for Nuclear Research) 2026 Open access

Read full text
Authors: Emmanuel U. Ugwu, Xinming Zhang, Ezekiel B. Ouedraogo, Aprilica Liemong Caezar Al Fajr N., Aurelia Sukianto, Sicheng Huang
DOI: 10.5281/zenodo.18598905
Cited by: 0

Abstract

Full Changelog: https://github.com/UEmmanuel5/FirESAM/commits/v1.0.0 Initial public release of FireSAM: a promptable fire-segmentation pipeline including teacher–student training scripts, evaluation utilities, interactive prompting/annotation, ONNX export (FP32/FP16) and INT8 quantization tools, plus ONNX video benchmarking and optional detector weights for end-to-end demos. Licensed under Apache-2.0.

Fields of Study & Subjects

Fire Detection and Safety Systems Advanced Neural Network Applications Domain Adaptation and Few-Shot Learning

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
10 February 2026
Language
EN