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 91 for “"Grad-CAM"”.
-
Transformation-invariance properties of Grad-CAM in Convolutional Neural Networks
… interest in interpreting their decisions. Gradient weighted Class Activation Mapping (Grad-CAM) is 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 …
-
Machine Learning Based Medical Ultrasound Image Classification and Grad-Cam Interpretation
… the decision-making process of the model. Using Gradient-weighted Class Activation Mapping, the classification decision of the model is visualized via a heatmap. Being able to interpret the decision-making process gives doctors confidence that the diagnostic classification system is accurate.
-
Visual Interpretability of Multimodal Tissue Perfusion Classification Using Grad-Cam and Saliency Maps
… through the analysis of saliency maps and the Gradient-weighted Class Activation Mapping (Grad-CAM) methods. The purpose of this method is to find out how the convolutional neural networks (CNNs) are able to find discriminative regions in di!erent types of data during the classification of the …
-
Enhancing Interpretability of Convolutional Neural Networks: A Decision Tree Approach Using Grad-CAM and Wavelet Transforms for Multi-Class Classification
… trees. In this work, a technique known as Grad-CAM (Gradient-weighted Class Activation Mapping) is used to obtain heat maps that illustrate regions in the image responsible for the CNN class distinction. To increase the readability of these heatmaps, wavelet transforms are used to denoise …
-
Machine Learning Based Characterization of preictal EEG
… gain a better understanding of these features, Gradient-weighted Class Activation Mapping (Grad-CAM) and augmented Gradient-weighted Class Activation Mapping (augmented Grad-CAM) are applied to the convolutional portion of patient specific neural networks trained to recognize preictal activity. …
-
Manijoko lapų ligų atpažinimas /
… competition. It also implements the Grad-CAM analysis of a chosen model and solves a leaf segmentation task. Computer vision is one of the best solutions to identify plant diseases quickly and conveniently, thus reducing the losses caused by these diseases. A convolutional neural …
-
Explainable Artificial Intelligence for Deep Learing Methods in Chest X-Ray Classification
… ImageNet και η μέθοδος ερμηνευσιμότητας είναι η Grad-Cam. Για την αξιολόγηση της Grad-Cam χρησιμοποιείται η μετρητική Intersection over Union (IoU) και η ανάλυση σημαντικότητας εικονοστοιχείων. Το μοντέλο επιτυγχάνει ένα F1 score 0.81, με την κλάση ‘No-Finding’ να κατέχει την υψηλότερη τιμή. Οι …
-
AI-Enabled Retinal Imaging for Scalable Prediction of Systemic and Ocular Diseases Using an Oculomics Framework
… showed a mean absolute error of 0.58 g/dL. Grad-CAM consistently highlighted the optic disc and vessels, reflecting known vascular changes (P < 0.001). For ICP classification with OCT, VGG16 achieved 91.54% accuracy (AUC 0.9551) and ResNet34 88.78% (AUC 0.9422). Grad-CAM showed localised …
-
Dirbtinių neuroninių tinklų modelių paaiškinamumo ir intepretuojamumo tyrimai /
… a new source of learning. LIME, SHAP, and Grad-CAM are explainable artificial intelligence methods that can help bring transparency to very complex and unclear models, uncover the reasoning behind the model’s decisions, and detect adversarial attacks in which an image is corrupted with …
-
ASSESSING THE QUALITY OF PREDICTIVE UNCERTAINTY ON COASTAL AERIAL IMAGES WITH BAYESIAN TRANSFER LEARNING
… the probabilistic outputs of the VI models with Gradient-Weighted Class Activation Mapping (Grad-CAM). By combining Grad-CAM with the outputs, I present a novel approach for visualizing model uncertainty about image feature importance. Both works advance efforts to support the U.S. Navy’s need …
-
Deep learning methods for classifying disease subtypes in multiple sclerosis based on clinical imaging and non-imaging data
… interpretation using a recognized method called gradient-class activation mapping (Grad- CAM). Results showed that axial images normalized with a Z-score like approach were most feasible. Both the 2D and 3D models achieved >80% accuracy in predicting RRMS and SPMS, where combining both MRI and …
-
Inteligência artificial explicável para detecção de fissuras em concreto armado : uma abordagem pós-hoc combinando técnicas de XAI em eedes neurais convolucionais
… explicabilidade baseados em visualização, como o Grad-CAM, com técnicas de segmentação não supervisionada, a exemplo do algoritmo K-means. A metodo- logia emprega aprendizado por transferência com arquiteturas consagradas (VGG16, VGG19 e ResNet) alcançando acurácia superior a 99% nos conjuntos de …
-
Deep Active Learning for Detecting Asset Degradation
… deformation, and corrosion cause components to degrade, potentially resulting in failure. This research has contributed a novel dataset and new machine learning architectures for maintenance video analysis, aiming to detect signs of degradation and alert users to worsening conditions.This research …
-
Enhancing Visual Interpretability in Computer-Assisted Radiological Diagnosis: Deep Learning Approaches for Chest X-Ray Analysis
… The first study scrutinizes the effectiveness of Gradient-weighted Class Activation Mapping (Grad-CAM) across various deep learning architectures, specifically evaluating its reliability in the context of pneumothorax diagnosis in chest X-ray images. Through a systematic analysis, this research …
-
Interpretable time-series forecasting with multi-model deep learning and natural language processing (NLP) driven explainable artificial intelligence (XAI)
… framework incorporates XAI techniques such as Grad-CAM and SHAP. These methods generate sensor-level explanations by highlighting critical regions in input heatmaps and quantifying feature contributions. For instance, Grad-CAM identifies clinically relevant ECG segments (e.g., prolonged QT …
-
Automatic Assessment of Structural Damage of Masonry Structures by Visual Analysis of Surface Cracks
… to the different parts of the image by utilizing Gradient-weighted Class Activation Mapping (grad-cam) library. Finally, we show how combining two different data types, such as raw images and manually extracted features, into a hybrid convolutional neural network can increase the accuracy of the …
-
Identifikace abnormálních EKG segmentů pomocí metody Multiple-Instance Learning
… instancí v EKG byla implementována metoda Grad-CAM. Hodnocení kvality detekce arytmií proběhlo prostřednictvím výpočtu F1 skóre a výsledky byly na konci práce diskutovány.
-
Raman spectroscopy and deep learning for tumour radiation response evaluation
… objective is to apply a CNN-based technique, Gradient-Weighted Class Activation Mapping (Grad-CAM), to visualize key discriminative RS signatures influencing the CNN predictions. A CNN was trained on a RS data set acquired from three irradiated tumour cell lines. The CNN classified …
-
Deep Learning Classification of Deep Ultraviolet Fluorescence Images for Margin Assessment During Breast Cancer Surgery
… regional importance maps generated through the Grad-CAM++ algorithm. The proposed method- ology involves dividing DUV whole-slide images into smaller patches, converting them to grayscale, and analyzing pixel values to identify valid patches. A pre-trained ResNet50 network and an XGBoost …
Page 1 of 5