Are We Ready for Out-of-Distribution Detection in Digital Pathology?

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Oh, Ji-Hun, Falahkheirkhah, Kianoush, Bhargava, Rohit
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909261760561152
author Oh, Ji-Hun
Falahkheirkhah, Kianoush
Bhargava, Rohit
author_facet Oh, Ji-Hun
Falahkheirkhah, Kianoush
Bhargava, Rohit
contents The detection of semantic and covariate out-of-distribution (OOD) examples is a critical yet overlooked challenge in digital pathology (DP). Recently, substantial insight and methods on OOD detection were presented by the ML community, but how do they fare in DP applications? To this end, we establish a benchmark study, our highlights being: 1) the adoption of proper evaluation protocols, 2) the comparison of diverse detectors in both a single and multi-model setting, and 3) the exploration into advanced ML settings like transfer learning (ImageNet vs. DP pre-training) and choice of architecture (CNNs vs. transformers). Through our comprehensive experiments, we contribute new insights and guidelines, paving the way for future research and discussion.
format Preprint
id arxiv_https___arxiv_org_abs_2407_13708
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Are We Ready for Out-of-Distribution Detection in Digital Pathology?
Oh, Ji-Hun
Falahkheirkhah, Kianoush
Bhargava, Rohit
Computer Vision and Pattern Recognition
Machine Learning
The detection of semantic and covariate out-of-distribution (OOD) examples is a critical yet overlooked challenge in digital pathology (DP). Recently, substantial insight and methods on OOD detection were presented by the ML community, but how do they fare in DP applications? To this end, we establish a benchmark study, our highlights being: 1) the adoption of proper evaluation protocols, 2) the comparison of diverse detectors in both a single and multi-model setting, and 3) the exploration into advanced ML settings like transfer learning (ImageNet vs. DP pre-training) and choice of architecture (CNNs vs. transformers). Through our comprehensive experiments, we contribute new insights and guidelines, paving the way for future research and discussion.
title Are We Ready for Out-of-Distribution Detection in Digital Pathology?
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2407.13708