Saved in:
Bibliographic Details
Main Authors: Das, Kaustav, Rauchs, Gaston, Sykora, Jan, Kucerova, Anna
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.00127
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910035740721152
author Das, Kaustav
Rauchs, Gaston
Sykora, Jan
Kucerova, Anna
author_facet Das, Kaustav
Rauchs, Gaston
Sykora, Jan
Kucerova, Anna
contents This work tests a self-annotation-based unsupervised methodology for training a convolutional neural network (CNN) model for semantic segmentation of X-ray computed tomography (XCT) scans of concretes. Concrete poses a unique challenge for XCT imaging due to similar X-ray attenuation coefficients of aggregates and mortar, resulting in low-contrast between the two phases in the ensuing images. While CNN-based models are a proven technique for semantic segmentation in such challenging cases, they typically require labeled training data, which is often unavailable for new datasets or are costly to obtain. To counter that limitation, a self-annotation technique is used here which leverages superpixel algorithms to identify perceptually similar local regions in an image and relates them to the global context in the image by utilizing the receptive field of a CNN-based model. This enables the model to learn a global-local relationship in the images and enables identification of semantically similar structures. We therefore present the performance of the unsupervised training methodology on our XCT datasets and discuss potential avenues for further improvements.
format Preprint
id arxiv_https___arxiv_org_abs_2603_00127
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Segmenting Low-Contrast XCTs of Concretes: An Unsupervised Approach
Das, Kaustav
Rauchs, Gaston
Sykora, Jan
Kucerova, Anna
Computer Vision and Pattern Recognition
This work tests a self-annotation-based unsupervised methodology for training a convolutional neural network (CNN) model for semantic segmentation of X-ray computed tomography (XCT) scans of concretes. Concrete poses a unique challenge for XCT imaging due to similar X-ray attenuation coefficients of aggregates and mortar, resulting in low-contrast between the two phases in the ensuing images. While CNN-based models are a proven technique for semantic segmentation in such challenging cases, they typically require labeled training data, which is often unavailable for new datasets or are costly to obtain. To counter that limitation, a self-annotation technique is used here which leverages superpixel algorithms to identify perceptually similar local regions in an image and relates them to the global context in the image by utilizing the receptive field of a CNN-based model. This enables the model to learn a global-local relationship in the images and enables identification of semantically similar structures. We therefore present the performance of the unsupervised training methodology on our XCT datasets and discuss potential avenues for further improvements.
title Segmenting Low-Contrast XCTs of Concretes: An Unsupervised Approach
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.00127