We propose a framework for descriptively analyzing sets of partial orders based on the concept of depth functions. Despite intensive studies of depth functions in linear and metric spaces, there is very little discussion on depth functions for non-standard data types such as partial orders. We introduce an adaptation of the well-known simplicial depth to the set of all partial orders, the union-free generic (ufg) depth. Moreover, we utilize our ufg depth for a comparison of machine learning algorithms based on multidimensional performance measures. Concretely, we analyze the distribution of different classifier performances over a sample of standard benchmark data sets. Our results promisingly demonstrate that our approach differs substantially from existing benchmarking approaches and, therefore, adds a new perspective to the vivid debate on the comparison of classifiers.

We explore the use of uncertainty estimation in the maritime domain, showing the efficacy on toy datasets (CIFAR10) and proving it on an in-house dataset, SHIPS. We present a method joining the intra-class uncertainty achieved using Monte Carlo Dropout, with recent discoveries in the field of outlier detection, to gain more holistic uncertainty measures. We explore the relationship between the introduced uncertainty measures and examine how well they work on CIFAR10 and in a real-life setting. Our work improves the FPR95 by 8% compared to the current highest-performing work when the models are trained without out-of-distribution data. We increase the performance by 77% compared to a vanilla implementation of the Wide ResNet. We release the SHIPS dataset and show the effectiveness of our method by improving the FPR95 by 44.2% with respect to the baseline. Our approach is model agnostic, easy to implement, and often does not require model retraining.

As radio telescopes increase in sensitivity and flexibility, so do their complexity and data-rates. For this reason automated system health management approaches are becoming increasingly critical to ensure nominal telescope operations. We propose a new machine learning anomaly detection framework for classifying both commonly occurring anomalies in radio telescopes as well as detecting unknown rare anomalies that the system has potentially not yet seen. To evaluate our method, we present a dataset consisting of 7050 autocorrelation-based spectrograms from the Low Frequency Array (LOFAR) telescope and assign 10 different labels relating to the system-wide anomalies from the perspective of telescope operators. This includes electronic failures, miscalibration, solar storms, network and compute hardware errors among many more. We demonstrate how a novel Self Supervised Learning (SSL) paradigm, that utilises both context prediction and reconstruction losses, is effective in learning normal behaviour of the LOFAR telescope. We present the Radio Observatory Anomaly Detector (ROAD), a framework that combines both SSL-based anomaly detection and a supervised classification, thereby enabling both classification of both commonly occurring anomalies and detection of unseen anomalies. We demonstrate that our system is real-time in the context of the LOFAR data processing pipeline, requiring <1ms to process a single spectrogram. Furthermore, ROAD obtains an anomaly detection F-2 score of 0.92 while maintaining a false positive rate of ~2\%, as well as a mean per-class classification F-2 score 0.89, outperforming other related works.

This study aims to develop a new computational pathology approach that automates the identification and quantification of myocardial inflammatory infiltration in digital HE-stained images to provide a quantitative histological diagnosis of myocarditis.898 HE-stained whole slide images (WSIs) of myocardium from 154 heart transplant patients diagnosed with myocarditis or dilated cardiomyopathy (DCM) were included in this study. An automated DL-based computational pathology approach was developed to identify nuclei and detect myocardial inflammatory infiltration, enabling the quantification of the lymphocyte nuclear density (LND) on myocardial WSIs. A cutoff value based on the quantification of LND was proposed to determine if the myocardial inflammatory infiltration was present. The performance of our approach was evaluated with a five-fold cross-validation experiment, tested with an internal test set from the myocarditis group, and confirmed by an external test from a double-blind trial group. An LND of 1.02/mm2 could distinguish WSIs with myocarditis from those without. The accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) in the five-fold cross-validation experiment were 0.899 plus or minus 0.035, 0.971 plus or minus 0.017, 0.728 plus or minus 0.073 and 0.849 plus or minus 0.044, respectively. For the internal test set, the accuracy, sensitivity, specificity, and AUC were 0.887, 0.971, 0.737, and 0.854, respectively. The accuracy, sensitivity, specificity, and AUC for the external test set reached 0.853, 0.846, 0.858, and 0.852, respectively. Our new approach provides accurate and reliable quantification of the LND of myocardial WSIs, facilitating automated quantitative diagnosis of myocarditis with HE-stained images.

The successful analysis of argumentative techniques from user-generated text is central to many downstream tasks such as political and market analysis. Recent argument mining tools use state-of-the-art deep learning methods to extract and annotate argumentative techniques from various online text corpora, however each task is treated as separate and different bespoke models are fine-tuned for each dataset. We show that different argument mining tasks share common semantic and logical structure by implementing a multi-task approach to argument mining that achieves better performance than state-of-the-art methods for the same problems. Our model builds a shared representation of the input text that is common to all tasks and exploits similarities between tasks in order to further boost performance via parameter-sharing. Our results are important for argument mining as they show that different tasks share substantial similarities and suggest a holistic approach to the extraction of argumentative techniques from text.

The computational analysis of poetry is limited by the scarcity of tools to automatically analyze and scan poems. In a multilingual settings, the problem is exacerbated as scansion and rhyme systems only exist for individual languages, making comparative studies very challenging and time consuming. In this work, we present \textsc{Alberti}, the first multilingual pre-trained large language model for poetry. Through domain-specific pre-training (DSP), we further trained multilingual BERT on a corpus of over 12 million verses from 12 languages. We evaluated its performance on two structural poetry tasks: Spanish stanza type classification, and metrical pattern prediction for Spanish, English and German. In both cases, \textsc{Alberti} outperforms multilingual BERT and other transformers-based models of similar sizes, and even achieves state-of-the-art results for German when compared to rule-based systems, demonstrating the feasibility and effectiveness of DSP in the poetry domain.

In this paper, we introduce a novel technique called Tree-Ring Watermarking that robustly fingerprints diffusion model outputs. Unlike existing methods that perform post-hoc modifications to images after sampling, Tree-Ring Watermarking subtly influences the entire sampling process, resulting in a model fingerprint that is invisible to humans. The watermark embeds a pattern into the initial noise vector used for sampling. These patterns are structured in Fourier space so that they are invariant to convolutions, crops, dilations, flips, and rotations. After image generation, the watermark signal is detected by inverting the diffusion process to retrieve the noise vector, which is then checked for the embedded signal. We demonstrate that this technique can be easily applied to arbitrary diffusion models, including text-conditioned Stable Diffusion, as a plug-in with negligible loss in FID. Our watermark is semantically hidden in the image space and is far more robust than watermarking alternatives that are currently deployed.

Automated malaria diagnosis is a difficult but high-value target for machine learning (ML), and effective algorithms could save many thousands of children's lives. However, current ML efforts largely neglect crucial use case constraints and are thus not clinically useful. Two factors in particular are crucial to developing algorithms translatable to clinical field settings: (i) Clear understanding of the clinical needs that ML solutions must accommodate; and (ii) task-relevant metrics for guiding and evaluating ML models. Neglect of these factors has seriously hampered past ML work on malaria, because the resulting algorithms do not align with clinical needs. In this paper we address these two issues in the context of automated malaria diagnosis via microscopy on Giemsa-stained blood films. First, we describe why domain expertise is crucial to effectively apply ML to malaria, and list technical documents and other resources that provide this domain knowledge. Second, we detail performance metrics tailored to the clinical requirements of malaria diagnosis, to guide development of ML models and evaluate model performance through the lens of clinical needs (versus a generic ML lens). We highlight the importance of a patient-level perspective, interpatient variability, false positive rates, limit of detection, and different types of error. We also discuss reasons why ROC curves, AUC, and F1, as commonly used in ML work, are poorly suited to this context. These findings also apply to other diseases involving parasite loads, including neglected tropical diseases (NTDs) such as schistosomiasis.

Post-OCR processing has significantly improved over the past few years. However, these have been primarily beneficial for texts consisting of natural, alphabetical words, as opposed to documents of numerical nature such as invoices, payslips, medical certificates, etc. To evaluate the OCR post-processing difficulty of these datasets, we propose a method to estimate the denoising complexity of a text and evaluate it on several datasets of varying nature, and show that texts of numerical nature have a significant disadvantage. We evaluate the estimated complexity ranking with respect to the error rates of modern-day denoising approaches to show the validity of our estimator.

Feature attribution methods have become a staple method to disentangle the complex behavior of black box models. Despite their success, some scholars have argued that such methods suffer from a serious flaw: they do not allow a reliable interpretation in terms of human concepts. Simply put, visualizing an array of feature contributions is not enough for humans to conclude something about a model's internal representations, and confirmation bias can trick users into false beliefs about model behavior. We argue that a structured approach is required to test whether our hypotheses on the model are confirmed by the feature attributions. This is what we call the "semantic match" between human concepts and (sub-symbolic) explanations. Building on the conceptual framework put forward in Cin\`a et al. [2023], we propose a structured approach to evaluate semantic match in practice. We showcase the procedure in a suite of experiments spanning tabular and image data, and show how the assessment of semantic match can give insight into both desirable (e.g., focusing on an object relevant for prediction) and undesirable model behaviors (e.g., focusing on a spurious correlation). We couple our experimental results with an analysis on the metrics to measure semantic match, and argue that this approach constitutes the first step towards resolving the issue of confirmation bias in XAI.