Sequential Hard Mining: a data-centric approach for Mitosis Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lafarge, Maxime W., Koelzer, Viktor H.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916930272624640
author Lafarge, Maxime W.
Koelzer, Viktor H.
author_facet Lafarge, Maxime W.
Koelzer, Viktor H.
contents With a continuously growing availability of annotated datasets of mitotic figures in histology images, finding the best way to optimally use with this unprecedented amount of data to optimally train deep learning models has become a new challenge. Here, we build upon previously proposed approaches with a focus on efficient sampling of training data inspired by boosting techniques and present our candidate solutions for the two tracks of the MIDOG 2025 challenge.
format Preprint
id arxiv_https___arxiv_org_abs_2509_02588
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sequential Hard Mining: a data-centric approach for Mitosis Detection
Lafarge, Maxime W.
Koelzer, Viktor H.
Image and Video Processing
Computer Vision and Pattern Recognition
With a continuously growing availability of annotated datasets of mitotic figures in histology images, finding the best way to optimally use with this unprecedented amount of data to optimally train deep learning models has become a new challenge. Here, we build upon previously proposed approaches with a focus on efficient sampling of training data inspired by boosting techniques and present our candidate solutions for the two tracks of the MIDOG 2025 challenge.
title Sequential Hard Mining: a data-centric approach for Mitosis Detection
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.02588