Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 34 for “"Visual explanations"”.
-
Human teachable concept highlighter for post-hoc visual explanations
… ability to provide clear and approachable explanations tailored to human learners. Efforts to develop explainable methods for these models have typically been designed for DL-experts rather than learners. In this study, we propose a novel approach that combines high-performance models with …
-
Effective Explainable Artificial Intelligence using Visual Explanations in Images
… simplification, feature relevance, and visual interpretations. After that, we review XAI evaluation metrics, application areas, and tasks. In the end, we discuss XAI challenges and address some concerns, and provide suggestions to improve their performance. This study improves AI systems …
-
Exploring the Effects of Explainable Artificial Intelligence (XAI) Across AI Tools with Different Levels of Decision Complexity
… Complexity Theory, this research examines how visual and textual Explainable Artificial Intelligence (XAI) explanations influence users’ trust and mental model clarity in AI recommendation systems. Using a 2 × 3 mixed factorial experiment, the study compared visual and textual explanations …
-
Explainable deep learning for image understanding
… and a framework for 3D editing informed by visual explanations. These advancements boost model trust across diverse applications.
-
Explainable Interactive Projections for Image Data
… an interactive DR method for images that uses visual features extracted by a deep neural network to project the images into 2D space and provides visual explanations of image features that contributed to the 2D location. In addition, it allows people to directly manipulate the 2D projection …
-
Visual Segmentation with Explanations for Medical Decision Making: A CNN Architecture with a Transformer-Attention Extension
… CNN architecture that generates model-specific visual explanations through spatial attention gates integrated directly into the network. The proposed model achieves a Dice score of 0.8621 on the Kvasir-SEG polyp segmentation dataset, outperforming all evaluated explainable models, while …
-
Enhancing Visual Interpretability in Computer-Assisted Radiological Diagnosis: Deep Learning Approaches for Chest X-Ray Analysis
… influence the robustness and clarity of Grad-CAM visual explanations, providing valuable insights for selecting and designing interpretable deep learning models in medical imaging. Building on the foundational understanding of interpretability, the second study introduces a novel deep learning …
-
Romanticism and film: Franz Liszt and audio-visual explanation
… and aesthetic category and film as an audio-visual medium. A series of selected and interconnected subjects are explored throughout the central chapters in reference to the hypothesis that discourse and representation itself present various kinds of ‘explanations’ about their subjects. The …
-
Visual representation of bug report assignment recommendations
… of the rationale. This work focuses on providing visual explanations for bug report assignment recommendations. We examine the use of a supervised and unsupervised machine learning algorithm for the assignment recommendation from which we can provide recommendation rationale. We explore the use of …
-
Vision and Language: Information Integration and Transformation
… multi-modalities, such as image-text retrieval, visual question answering, visual grounding, and image captioning. In particular, we explore and develop techniques combining image and text information to improve transformation between modalities. First, we exploit the multilingual image …
-
Bridging the gap : enhancing ML transparency with explainable artificial intelligence
… monitoring. The framework combines textual and visual explanations, presenting ML-generated insights in ways that can be more readily understood withoutreducing analytical value.Validation of the framework is carried out using established principles and engineering knowledge to assess the …
-
Transformation-invariance properties of Grad-CAM in Convolutional Neural Networks
… a post-hoc explanation technique that generates visual heatmaps to highlight the class-relevant regions in an input image. However, in real-world scenarios, input images often undergo transformations such as rotation, zoom, and shifts along the horizontal and vertical axis, which may compromise …
-
Interpreting Dimension Reductions through Gradient Visualization
… we use gradients of the projection to generate visual explanations of the DRs. Utilizing these gradients, we show the point-wise sensitivities of the projection with respect to the original data features to explain the reasoning of DR. The combination of the gra- dients with various …
-
Multi-scale local explanation approach for image analysis using model-agnostic explainable artificial intelligence (XAI)
… decisions. Local Interpretable Model-agnostic Explanations (LIME) is an explanation method which produces a coarse heatmap as a visual explanation highlighting the most important superpixels affecting the CNN’s decision. This thesis aims to explore and develop a multi-scale scheme of LIME to …
-
Interpretable Deep Learning Architectures for Mortality Prediction Inside the Intensive Care Unit
… from coalitional game theory to construct visual explanations aimed to show how important these inputs are deemed by the networks. Our results show our models attain state of the art performance while remaining interpretable. Supporting code can be found at …
-
From Shortcut Learning to Explainable Prediction: A Framework for Complex Pulmonary Disease Detection
… hierarchical VAE models, which provide precise visual explanations through gradient-guided latent traversals. These methods outperform traditional deep CNN-based explainability techniques in feature isolation and disease localisation but face challenges with reconstruction quality and predictive …
-
Explainable AI and susceptibility to adversarial attacks in classification and segmentation of breast ultrasound images
… (Grad-CAM) and other techniques that provide visual explanations into inner workings of CNNs. In addition to interpretation, these methods provide clinically important information, such as identifying the location for biopsy or treatment. In this work, we analyze how adversarial assaults that …
-
Explainable improved ensembling for natural language and vision
… Information Extraction, Object Detection, and Visual Question Answering. We also present a variant of SWAF for combining systems that do not have training data in an unsupervised ensemble with systems that do have training data. Our combined approach obtains a new state-of-the-art, beating our …
-
Identifying classifier-relevant regions in images through weightless learning
… been proposed thus far to produce humanlegible explanations to the decision processes of classifiers, each solving a small piece of this enormous puzzle. One part of this, are the visual explanations, which seeks to produce images which can highlight what is the relevant content to the …
Page 1 of 2