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 435 for “"ResNet"”.
-
Pruning resnet neural networks block by block
… works focus on neurons or convolutional filters. ResNet is a model architecture composed of many blocks that are linked with residual connections. In our work, we explore pruning larger structures – ResNet blocks, and thoroughly study the feasibility of block by block pruning whilst keeping track …
-
IMPACT OF STOCHASTIC DEPTH ON DETERMINISTIC AND PROBABILISTIC RESNET MODELS FOR WEATHER MODELING
… depth (SD) implementation in residual networks (ResNet), both deterministic and probabilistic, to reduce long training times associated with Bayesian neural networks while maintaining model accuracy. We show that overall, ResNets fail to perform better with the implementation of SD with the …
-
A HYBRID RESNET-50 AND GRAPH RELATIONAL LEARNING APPROACH FOR PROSTHETIC HAND GRASP CLASSIFICATION
… my research proposes a model that uses ResNet-50 as the backbone to extract image features, followed by a Graph Neural Network (GNN) architecture to significantly enhance performance in predicting visual inputs. The proposed ResNet50-Graph model is evaluated on the HandCam dataset for …
-
A BERT-ResNet Cross-Attention Fusion Network and Modality Utilization Assessment for Multimodal Sentiment Classification
… a model using BERT for textual features and ResNet for visual features. A cross-attention fusion module aligns the modalities for joint representation. We conduct experiments on the MVSA-Single and MVSA-Multiple datasets, which contain over 5,000 and 17,000 labeled text-image pairs. Our …
-
Pseudo-Computed Tomography Image Generation from Magnetic Resonance Imaging Using Generative Adversarial Networks for Veterinary Radiation Therapy Planning
… and PatchGAN discriminator, and another with a ResNet U-Net generator and ResNet discriminator are compared. The ResNet U-Net generator and ResNet discriminator produced the most accurate pseudo-CT images with a mean absolute error of 109.54 ± 153.66 HU, a peak-signal-to-noise ratio of 21.15 ± …
-
Pose Estimation and 3D Bounding Box Prediction for Autonomous Vehicles Through Lidar and Monocular Camera Sensor Fusion
… the integration of transfer learning with ResNet-101 and compares its performance with VGG-19 for 3D object detection in autonomous vehicles. ResNet-101 is a deep Convolutional Neural Network with 101 layers and VGG-19 is a one with 19 layers. The research emphasizes the fusion of camera …
-
Comparison of cnn and svm ensemble methods for acoustic drone recognition /
This thesis explores combining SVM and CNN (ResNet) models for acoustic drone detection. When tested on known drones, the hybrid ResNet+SVM ensemble with product rule fusion achieved a perfect F1 of 1.0, outperforming standalone SVM (0.984) and CNN (0.963). On unseen drones, a CNN-only ensemble led …
-
Rare disease classification from facial photographs using deep learning
… convolutional neural network models (AlexNet, ResNet-18, ResNet-34, ResNet-50, VGG-16, VGG-19, DenseNet121, MobileNetV2) are analyzed over two different transfer learning approaches. All the models, except VGG-16, achieved superior results when trained with fine-tuned transfer learning approach …
-
A Dual-Stream Deep Learning Approach for Genuine–Counterfeit Coin Classification
… edge maps. Each stream is realized with a ResNet-101 backbone, and their probabilistic outputs are combined via soft voting to form the final decision. Under 5-fold cross-validation, the proposed model attains mean accuracies of 94.4% on 2 dollars-head, 96.3% on 2 dollars-tail, 92% on 50 …
-
Hluboké neuronové sítě pro analýzu medicínských obrazových dat
… hrudníka. Najlepšie výsledky dosiahli siete ResNet a SEResNet. Pri prvej úlohe dosiahla SEResNet presnosť 99,49%, pri druhej mala najlepšie výsledky ResNet s presnosťou 94,97% a v prípade tretej úlohy dosiahla najlepší výsledok opäť SEResNet, 31,53% s použitím metriky F1 measure.
-
Pre-trained CNN and bi-directional LSTM for no-reference video quality assessment
… we assess three pre-trained CNN, MobileNet, ResNet-50 and Inception-ResNet-V2, as feature extractors and select ResNet-50 since it showed the best performance. In this thesis, we assess the stability of our VQA method and conduct an ablation study to highlight the importance of the …
-
Automated Cataract Grading using Smartphone Images
… ConvNets, including VGG-16, Inception V3, and ResNet-101, were fine-tuned on the target dataset. In the last procedure, to evaluate the classification technique with the standard supervised classifiers, the extracted features by the ResNet-101 pre-trained network were fed into the Support …
-
Hluboké neuronové sítě pro prostředí superpočítače
… zahŕňajú aplikovanie modelov Inception V3 a ResNet. Modely siete sú aplikované na rôzne grafické karty a výpočetný hardvér. Výstupom diplomovej práce je implementovaný model siete Inception V3, ktorý skúma grafické karty a ich výkon, časovú náročnosť výpočtov a ich efektivitu. Model siete …
-
Application of deep convolutional neural networks to automatic feature/object detection in high resolution remote sensing imagery
… the performance of CaffeNet, GoogLeNet, ResNet-50, ResNet-101, on this data set. ResNet-101 achieved a 96.4 percent average accuracy on the world-wide SAM site data set. Finally, we present a China SAM site search and detection case study. First, we compare a visual Broad Area Search …
-
Evaluating Modern Neural Network Architectures for Suicide Prediction
… (MLP) and a selection of its successors, ResNet and MLP with a category embedding layer, at the task of predicting suicidal ideation among high-school students. This research finds ResNet to be the most capable at minimizing false negatives, but with a higher amount of false positives. …
-
A Study on Deepsea Fish Detection Using Convolutional Neural Networks
… using the DeepFish dataset. A pretrained ResNet-50 model attained a validation accuracy of 82.8% for multi-class habitat classification, demonstrating robust performance in most habitats based on 6,517 images, although exhibiting lower recall for visually similar or underrepresented …
-
Lietuvių kalbos teksto atpažinimas /
… convolutional recurrent neural network and ResNet-50. Convolutional recurrent neural network model is adapted to recognize Lithuanian words with the help of a dictionary, and the ResNet-50 model is compared with the fine-tuned version. A photo dataset of Lithuanian alphabet was created to …
-
Kintamumo prognozavimas panaudojant rekurentines diagramas ir giliojo mokymosi metodus /
… data was used to train GARCH, RNN, LSTM and ResNet models. These models were trained to forecast intervals in which stock market volatility should fall after 1, 2, 5, 10 and 21 days. Obtained results showed that RNN models give the best results when forecasting volatility after 1, 2, 5 and 10 …
-
Deep learning-based fine-tuned multi-vehicle tracking with classification correction
… dataset was created from multiple sources. A ResNet classifier was trained, and its knowledge was utilized to build a localization dataset automatically without manual annotations. The dataset consists of videos generated from the MLK testbed. Three different object detection frameworks (SSD, …
-
Robustness of ai-driven histopathology under real-world adversarial examples
… cohort, four representative architectures—ResNet-18, ResNet-50, HIPT-2MLP, and ViT-B/16 —are benchmarked across controlled pixel-level distortions and artifact-like transformations. Adversarial methods include iterative Fast Gradient Sign, Projected Gradient Descent, Salt-and-Pepper noise, …
Page 1 of 22