A Survey of Un-, Weakly-, and Semi-Supervised Learning Methods for Noisy, Missing and Partial Labels in Industrial Vision Applications

Simmler, Niclas; Sager, Pascal; Andermatt, Philipp; Chavarriaga, Ricardo; Schilling, F.-P.; Rosenthal, Matthias; Stadelmann, Thilo

doi:10.1109/sds51136.2021.00012

Cited by 10 publications

(4 citation statements)

References 56 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Limited amount of training data and noisy labels of public datasets are other factors contributing to low classification accuracies. One possible way to tackle this limitation is to rely on weakly supervised learning methods to improve the COVID-19 classification accuracy with the methodology summarized in [37].…”

Section: Discussionmentioning

confidence: 99%

PrepNet: A Convolutional Auto-Encoder to Homogenize CT Scans for Cross-Dataset Medical Image Analysis

Amirian

Montoya-Zegarra

Gruss

et al. 2021

2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)

Self Cite

View full text Add to dashboard Cite

With the spread of COVID-19 over the world, the need arose for fast and precise automatic triage mechanisms to decelerate the spread of the disease by reducing human efforts e.g. for image-based diagnosis. Although the literature has shown promising efforts in this direction, reported results do not consider the variability of CT scans acquired under varying circumstances, thus rendering resulting models unfit for use on data acquired using e.g. different scanner technologies. While COVID-19 diagnosis can now be done efficiently using PCR tests, this use case exemplifies the need for a methodology to overcome data variability issues in order to make medical image analysis models more widely applicable. In this paper, we explicitly address the variability issue using the example of COVID-19 diagnosis and propose a novel generative approach that aims at erasing the differences induced by e.g. the imaging technology while simultaneously introducing minimal changes to the CT scans through leveraging the idea of deep autoencoders. The proposed prepossessing architecture (PrepNet) (i) is jointly trained on multiple CT scan datasets and (ii) is capable of extracting improved discriminative features for improved diagnosis. Experimental results on three public datasets (SARS-COVID-2, UCSD COVID-CT, MosMed) show that our model improves cross-dataset generalization by up to 11.84 percentage points despite a minor drop in within dataset performance.

show abstract

Section: Discussionmentioning

confidence: 99%

PrepNet: A Convolutional Auto-Encoder to Homogenize CT Scans for Cross-Dataset Medical Image Analysis

Amirian

Montoya-Zegarra

Gruss

et al. 2021

2021 14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)

Self Cite

View full text Add to dashboard Cite

show abstract

“…To the contrary: First, it reduces the validity of performance result comparisons of the different systems if this occurs in the test dataset. Second, it is detrimental for the learning of MER systems, if it occurs in the training dataset (by teaching the model that the same input has ambiguous output, leading to reduced learning [30]). In order to minimize these meaningless variations in the GT of im2latex-100k, we adopted a data-centric approach to develop a new LaTeX normalization procedure.…”

Section: Detrimental Latex Variationsmentioning

confidence: 99%

MathNet: A Data-Centric Approach for Printed Mathematical Expression Recognition

Schmitt-Koopmann,

Huang,

Hutter

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Printed mathematical expression recognition (MER) models are usually trained and tested using LaTeX-generated mathematical expressions (MEs) as input and the LaTeX source code as ground truth. As the same ME can be generated by various different LaTeX source codes, this leads to unwanted variations in the ground truth data that bias test performance results and hinder efficient learning. In addition, the use of only one font to generate the MEs heavily limits the generalization of the reported results to realistic scenarios. We propose a data-centric approach to overcome this problem, and present convincing experimental results: Our main contribution is an enhanced LaTeX normalization to map any LaTeX ME to a canonical form. Based on this process, we developed an improved version of the benchmark dataset im2latex-100k, featuring 30 fonts instead of one. Second, we introduce the real-world dataset realFormula, with MEs extracted from papers. Third, we developed a MER model, MathNet, based on a convolutional vision transformer, with superior results on all four test sets (im2latex-100k, im2latexv2, realFormula, and InftyMDB-1), outperforming the previous state of the art by up to 88.3%.

show abstract

“…In this paper, we present an approach to identify vertebrae of the spine automatically without the need of excessive labeling of own data (or even no labels at all), thereby heralding a data-centric approach [ 12 ] based on un- or semi-supervised learning [ 13 ]. To this end, our contribution is the development and evaluation of a novel method that requires no labels at all to achieve reliable vertebrae detection and identification and, if given less than 5% of the labels we perform on par with comparable supervised approaches.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Domain Adaptation for Vertebrae Detection and Identification in 3D CT Volumes Using a Domain Sanity Loss

et al. 2022

Self Cite

View full text Add to dashboard Cite

A variety of medical computer vision applications analyze 2D slices of computed tomography (CT) scans, whereas axial slices from the body trunk region are usually identified based on their relative position to the spine. A limitation of such systems is that either the correct slices must be extracted manually or labels of the vertebrae are required for each CT scan to develop an automated extraction system. In this paper, we propose an unsupervised domain adaptation (UDA) approach for vertebrae detection and identification based on a novel Domain Sanity Loss (DSL) function. With UDA the model’s knowledge learned on a publicly available (source) data set can be transferred to the target domain without using target labels, where the target domain is defined by the specific setup (CT modality, study protocols, applied pre- and processing) at the point of use (e.g., a specific clinic with its specific CT study protocols). With our approach, a model is trained on the source and target data set in parallel. The model optimizes a supervised loss for labeled samples from the source domain and the DSL loss function based on domain-specific “sanity checks” for samples from the unlabeled target domain. Without using labels from the target domain, we are able to identify vertebra centroids with an accuracy of 72.8%. By adding only ten target labels during training the accuracy increases to 89.2%, which is on par with the current state-of-the-art for full supervised learning, while using about 20 times less labels. Thus, our model can be used to extract 2D slices from 3D CT scans on arbitrary data sets fully automatically without requiring an extensive labeling effort, contributing to the clinical adoption of medical imaging by hospitals.

show abstract

A Survey of Un-, Weakly-, and Semi-Supervised Learning Methods for Noisy, Missing and Partial Labels in Industrial Vision Applications

Cited by 10 publications

References 56 publications

PrepNet: A Convolutional Auto-Encoder to Homogenize CT Scans for Cross-Dataset Medical Image Analysis

PrepNet: A Convolutional Auto-Encoder to Homogenize CT Scans for Cross-Dataset Medical Image Analysis

MathNet: A Data-Centric Approach for Printed Mathematical Expression Recognition

Unsupervised Domain Adaptation for Vertebrae Detection and Identification in 3D CT Volumes Using a Domain Sanity Loss

Contact Info

Product

Resources

About