FrOoDo: Framework for Out-of-Distribution Detection

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Stieber, Jonathan, Fuchs, Moritz, Mukhopadhyay, Anirban
Format: Preprint
Veröffentlicht: 2022
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916125315432448
author Stieber, Jonathan
Fuchs, Moritz
Mukhopadhyay, Anirban
author_facet Stieber, Jonathan
Fuchs, Moritz
Mukhopadhyay, Anirban
contents FrOoDo is an easy-to-use and flexible framework for Out-of-Distribution detection tasks in digital pathology. It can be used with PyTorch classification and segmentation models, and its modular design allows for easy extension. The goal is to automate the task of OoD Evaluation such that research can focus on the main goal of either designing new models, new methods or evaluating a new dataset. The code can be found at https://github.com/MECLabTUDA/FrOoDo.
format Preprint
id arxiv_https___arxiv_org_abs_2208_00963
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle FrOoDo: Framework for Out-of-Distribution Detection
Stieber, Jonathan
Fuchs, Moritz
Mukhopadhyay, Anirban
Computer Vision and Pattern Recognition
FrOoDo is an easy-to-use and flexible framework for Out-of-Distribution detection tasks in digital pathology. It can be used with PyTorch classification and segmentation models, and its modular design allows for easy extension. The goal is to automate the task of OoD Evaluation such that research can focus on the main goal of either designing new models, new methods or evaluating a new dataset. The code can be found at https://github.com/MECLabTUDA/FrOoDo.
title FrOoDo: Framework for Out-of-Distribution Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2208.00963