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 19 of 19 for “"Prototypical networks"”.
-
Hierarchy Aligned Commonality Through Prototypical Networks: Discovering Evolutionary Traits over Tree-of-Life
… of Hierarchy aligned Commonality through Prototypical Networks (HComP-Net), which learns common features shared by all descendant species of an internal node and avoids the learning of over-specific prototypes. We empirically show that HComP-Net learns prototypes that are of high accuracy, …
-
ATTENTION-BASED CONVOLUTIONAL NEURAL NETWORK MODEL AND ITS COMBINATION WITH FEW-SHOT LEARNING FOR AUDIO CLASSIFICATION
… learning methods such as convolutional neural networks (CNN), recurrent neural networks (RNN), and their combinations, have achieved great success in such tasks. However, there are still numerous challenges left to be addressed in this domain. For example, in most cases, the sound events of …
-
Mokymosi iš nedaug duomenų metodų tyrimas ir jų taikymas marketingo vaizdams vertinti /
… learning techniques, such as transfer learning, prototypical networks, and MAML, can be effective under datascarce con ditions. The study utilizes pretrained architectures (ResNet18, ResNet50, EfficientNetV2, DeiT) with frozen layers and partial finetuning. Experiments showed that standard …
-
Mokymosi iš nedaug duomenų metodų tyrimas ir jų taikymas marketingo vaizdams vertinti /
… learning techniques, such as transfer learning, prototypical networks, and MAML, can be effective under data-scarce conditions. The study utilizes pretrained architectures (ResNet18, ResNet50, EfficientNetV2, DeiT) with frozen layers and partial finetuning. Experiments showed that standard …
-
Digital image forensics via meta-learning and few-shot learning
… identify image forgeries. Convolutional Neural Networks(CNN) are a frequent machine learning approach. A standard CNN model could distinguish between original and manipulated images. In this dissertation, two CNN models are introduced to recognize seam carving and Gaussian …
-
Fechtavimo judesių klasifikavimas pagal kūno ir špagos taškų sekas taikant mokymąsi iš keleto pavyzdžių /
… Graph Convolutional Network combined with Prototypical Networks and Relation Networks architectures, enabling classification of movement classes and additional attributes, arm position and target zone, using only standard camera footage. A dataset of 130 annotated video clips from …
-
Few-shot learning for dermatological disease diagnosis
… intra-class variability effectively, we propose Prototypical Clustering Networks (PCN), an extension to Prototypical Networks that learns a mixture of "prototypes" for each class. Prototypes are initialized for each class via clustering and refined via an online update scheme. Classification is …
-
Data augmentation as an engine: a multidimensional few-shot analysis
… We evaluate four FSL paradigms (Linear Probe, Prototypical Networks, SetFit, and LoRA) across five benchmarks and demonstrate that DA can yield over 70% relative performance gains in extreme low-data regimes, though it is limited by a trade-off between lexical innovation and semantic fidelity. …
-
UTILIZING FEDERATED LEARNING AND META LEARNING FOR FEW-SHOT LEARNING ON EDGE DEVICES
… and the server. In particular, we utilize the Prototypical Networks to perform meta-learning on all devices to learn multiple independent few-shot learning models and to combine the models in a centralized data distributed architecture using federated learning which can be reused by the clients …
-
Multicultural representation learning for music signal analysis
… the dissertation introduces Label-Combination Prototypical Networks (LC-Protonets), a novel multi-label few-shot learning approach that creates prototypes for label combinations rather than individual labels. The work evaluates state-of-the-art foundation models across diverse musical corpora …
-
Embodied Interaction in Virtual Meetings: From Static Gesture Recognition to Few-Shot Gesture Adaptation
… contains 27 gesture classes. Experiments with Prototypical Networks, using both convolutional neural network (CNN) and spatio-temporal graph convolutional network (ST-GCN) backbones, achieved approximately 75% accuracy in 5-way 5-shot settings. These results demonstrate the potential to expand …
-
Embodied Interaction in Virtual Meetings: From Static Gesture Recognition to Few-Shot Gesture Adaptation
… contains 27 gesture classes. Experiments with Prototypical Networks, using both convolutional neural network (CNN) and spatio-temporal graph convolutional network (ST-GCN) backbones, achieved approximately 75% accuracy in 5-way 5-shot settings. These results demonstrate the potential to expand …
-
Embodied Interaction in Virtual Meetings: From Static Gesture Recognition to Few-Shot Gesture Adaptation
… contains 27 gesture classes. Experiments with Prototypical Networks, using both convolutional neural network (CNN) and spatio-temporal graph convolutional network (ST-GCN) backbones, achieved approximately 75% accuracy in 5-way 5-shot settings. These results demonstrate the potential to expand …
-
Embodied Interaction in Virtual Meetings: From Static Gesture Recognition to Few-Shot Gesture Adaptation
… contains 27 gesture classes. Experiments with Prototypical Networks, using both convolutional neural network (CNN) and spatio-temporal graph convolutional network (ST-GCN) backbones, achieved approximately 75% accuracy in 5-way 5-shot settings. These results demonstrate the potential to expand …
-
Learning vector and functional Bregman divergences for machine learning applications
… for learning embeddings of the data using neural networks and Bregman divergence learning approaches for extending learning Euclidean distances to more general divergence measures such as divergences over distributions. Our proposed framework, Deep divergence networks, unifies and extends these …
-
Few-Shot and Zero-Shot Learning for Information Extraction
… (label) and category description based on the prototypical networks, where the hybrid attention helps alleviate ambiguity and capture more informative semantics by calculating both the label-relevant and query-related weights. A dynamic threshold is learned by integrating the semantic …
-
IMPROVING PERFORMANCE OF INTRUSION DETECTION SYSTEMS FOR SOFTWARE-DEFINED NETWORKS
The proliferation of Software-Defined Networks (SDNs) has revolutionized network management by decoupling the control and data planes, thereby introducing unparalleled flexibility and programmability. However, this architectural shift also exposes SDNs to a wide range of security threats, making …
-
Accessible Card Presentation in Board Games: Developing an Application for Individuals with Visual Impairment
Board games are a popular form of entertainment played in many cultures and countries in similar and different forms around the world. However, board games usually present barriers to people with visual impairments. One of these barriers is the card element in board games since these cards can be a …
-
Mathematical Modeling and Experimental Verification of Resonance Energy Transfer Networks: Applications in Cryptography and Biological Sensing
… However, the properties of larger fluorophore networks are poorly understood and their application space has not yet been fully explored. This dissertation introduces DNA self-assembled FÖrster Resonance Energy Transfer (FRET) networks that provide a unique optical output when probed by a …