Related papers: Interpretable Semantic Gradients in SSD: A PCA Swe…

Current methods for the interpretability of discriminative deep neural networks commonly rely on the model's input-gradients, i.e., the gradients of the output logits w.r.t. the inputs. The common assumption is that these input-gradients…

The rise of social networks has not only facilitated communication but also allowed the spread of harmful content. Although significant advances have been made in detecting toxic language in textual data, the exploration of concept-based…

Standard accuracy metrics indicate that reading comprehension systems are making rapid progress, but the extent to which these systems truly understand language remains unclear. To reward systems with real language understanding abilities,…

Dimensionality reduction is a fundamental technique in machine learning and data analysis, enabling efficient representation and visualization of high-dimensional data. This paper explores five key methods: Principal Component Analysis…

Semantic segmentation networks (SSNs) are central to safety-critical applications such as medical imaging and autonomous driving, where robustness under uncertainty is essential. However, existing probabilistic verification methods often…

Interpretable deep learning is a fundamental building block towards safer AI, especially when the deployment possibilities of deep learning-based computer-aided medical diagnostic systems are so eminent. However, without a computational…

Understanding the meaning of words is crucial for many tasks that involve human-machine interaction. This has been tackled by research in Word Sense Disambiguation (WSD) in the Natural Language Processing (NLP) field. Recently, WSD and many…

Scaled dot-product attention (SDPA) is a fundamental component responsible for the success of large-language models and other nonlinear signal processing applications. The rationale for SDPA has been based upon "query, key, value" concepts…

Our work introduces SAVeD (Semantically Aware Version Detection), a contrastive learning-based framework for identifying versions of structured datasets without relying on metadata, labels, or integration-based assumptions. SAVeD addresses…

Deep learning enables the modelling of high-resolution histopathology whole-slide images (WSI). Weakly supervised learning of tile-level data is typically applied for tasks where labels only exist on the patient or WSI level (e.g. patient…

Self-supervised learning (SSL) has recently shown notable success in various visual tasks. However, in terms of discriminability, SSL is still not on par with supervised learning (SL). This paper identifies a key issue, the ``crowding…

Effective suppression of surface-related multiples is essential to prevent imaging artifacts and erroneous structural interpretations. While conventional approaches rely on accurate priors or subsurface model knowledge, and supervised…

Text-based person anomaly search retrieves specific behavioral events from surveillance archives using natural-language queries. Although recent pose-aware methods align geometric structures well, they face a fundamental Pose-Semantic Gap:…

Remote sensing (RS) change detection is essential for interpreting surface dynamics. Semantic change detection (SCD) further enables pixel-level understanding of multi-class transitions, yet remains sensitive to pseudo-changes induced by…

Grading precancerous lesions on whole slide images is a challenging task: the continuous space of morphological phenotypes makes clear-cut decisions between different grades often difficult, leading to low inter- and intra-rater agreements.…

Neurodiverse learners often require reading supports, yet increasing scaffold richness can sometimes overload attention and working memory rather than improve comprehension. Grounded in the Construction-Integration model and a contingent…

Inspired by the recent success of deep neural networks and the recent efforts to develop multi-layer dictionary models, we propose a Deep Analysis dictionary Model (DeepAM) which is optimized to address a specific regression task known as…

Instruction tuning is one of the key steps required for adapting large language models (LLMs) to a broad spectrum of downstream applications. However, this procedure is difficult because real-world datasets are rarely homogeneous; they…

Improving the feature representation ability is the foundation of many whole slide pathological image (WSIs) tasks. Recent works have achieved great success in pathological-specific self-supervised learning (SSL). However, most of them only…

This paper introduces "Semantic Scaling," a novel method for ideal point estimation from text. I leverage large language models to classify documents based on their expressed stances and extract survey-like data. I then use item response…