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 224 for “"Few-Shot Learning"”.

  1. Transductive few-shot learning

    Deep learning models have achieved unprecedented success, approaching human-level performances when trained on large-scale labeled data. However, the generalization of such models might be seriously challenged when dealing with new (unseen) classes, with only a few labeled instances per class. …

    ets-quebec Download PDF for Transductive few-shot learning (opens in a new tab)

  2. Few-shot Learning for Object Detection

    … developments in neural networks have made deep learning a powerful tool that significantly advances the performance of various computer vision tasks. However, most most deep learning models rely on the large-scale annotated training data, and the performance turns to be low when the size of …

    anu Repository record for Few-shot Learning for Object Detection (opens in a new tab)

  3. Few-shot Learning for NER using MAML

    This thesis investigates the application of Few-Shot Learning (FSL) using Model-Agnostic Meta-Learning (MAML) to enhance Named Entity Recognition (NER) within the domain of Natural Language Processing (NLP), specifically focusing on chemical datasets. The primary challenge addressed is the …

    vcu Repository record for Few-shot Learning for NER using MAML (opens in a new tab)

  4. Few-shot learning for dermatological disease diagnosis

    … the first issue, we formulate the problem as low-shot learning, where once deployed, a base classifier can rapidly generalize to diagnose novel conditions given very few labeled examples. To model intra-class variability effectively, we propose Prototypical Clustering Networks (PCN), an extension …

    gatech Repository record for Few-shot learning for dermatological disease diagnosis (opens in a new tab)

  5. Few-shot Learning for Medical Image Classification

    … datasets. It hinders the application of deep learning methods in medical image field. Few-shot Learning (FSL) is a type of machine learning problem that has only a limited number of training examples with supervised information. It aims to reduce data gathering effort and computational cost. …

    unsw Repository record for Few-shot Learning for Medical Image Classification (opens in a new tab)

  6. Few-Shot learning for image-based anomaly detection /

    … samples. The aim of this work is to develop a Few-Shot Learning (FSL) extension for the PatchCore model by introducing the proposed DualPatchCore architecture, which incorporates an additional memory bank for storing anomalous feature embeddings. The proposed model is implemented, trained, and …

    vilnius Repository record for Few-Shot learning for image-based anomaly detection / (opens in a new tab)

  7. Investigation of Few-Shot Learning for Fall Detection

    … health and safety of aging seniors. Current deep learning-based fall detection methods perform well when a large amount of training data is available. As obtaining fall data from seniors is extremely difficult, training deep learning models is a challenge, and therefore, a few-shot Siamese network …

    carleton Repository record for Investigation of Few-Shot Learning for Fall Detection (opens in a new tab)

  8. Out-of-domain few-shot learning for image classification

    Deep learning models have consistently produced state-of-the-art results on large, labelled datasets for image classification. Although these models are highly accurate when trained on significant amounts of labeled data, generalization notably suffers when using relatively small datasets or …

    ubc Repository record for Out-of-domain few-shot learning for image classification (opens in a new tab) Download PDF for Out-of-domain few-shot learning for image classification (opens in a new tab)

  9. Deep Zero- and Few-shot Learning in Computer Vision

    … number of samples is not consistent with human's learning abilities, as humans have the ability to understand novel concepts from limited examples. Transfer learning is a machine learning topic that addresses the above limitations in current deep models, and it studies how to make machines exploit …

    anu Repository record for Deep Zero- and Few-shot Learning in Computer Vision (opens in a new tab)

  10. Feature extractor stacking for cross-domain few-shot learning

    Cross-domain few-shot learning (CDFSL) addresses learning problems where knowledge needs to be transferred from one or more source domains into an instance-scarce target domain with an explicitly different distribution. Recently published CDFSL methods generally construct a universal model that …

    waikato-masters Repository record for Feature extractor stacking for cross-domain few-shot learning (opens in a new tab) Download file for Feature extractor stacking for cross-domain few-shot learning (opens in a new tab)

  11. Passive IoT Device-Type Identification Using Few-Shot Learning

    … identification methods use traditional machine learning or deep learning techniques, which require a large amount of labeled data to generate the device fingerprints. Moreover, these techniques require building a new model whenever a new device is introduced. To address these limitations, we …

    concordia Download PDF for Passive IoT Device-Type Identification Using Few-Shot Learning (opens in a new tab)

  12. Digital image forensics via meta-learning and few-shot learning

    … the past several years, machine learning techniques have been effectively used to 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 …

    njit Repository record for Digital image forensics via meta-learning and few-shot learning (opens in a new tab)

  13. Flexible and scalable models for clustering and few-shot learning

    Unsupervised learning methods are difficult to design, and often lead to challenging optimization problems, due to the lack of prior knowledge. In particular, clustering algorithms have been studied extensively in machine learning, as a tool to analyze data through extracting similar patterns, in …

    ets-quebec Download PDF for Flexible and scalable models for clustering and few-shot learning (opens in a new tab)

  14. Few-shot learning with language models: Learning from instructions and contexts

    … do not achieve satisfactory performance in few-shot settings, where only a limited number of examples is available. This is an important issue not only because the need to annotate thousands of examples is a barrier to the more widespread application of such models, but also because few-shot …

    lmu-germany Repository record for Few-shot learning with language models: Learning from instructions and contexts (opens in a new tab)

  15. Annotation Efficient Visual Recognition: from Semi-Supervised to Few-Shot Learning

    In recent years, supervised deep learning has achieved remarkable success in solving a wide range of visual recognition problems. Large-scale labeled datasets have been crucial for this success and the progress has primarily been limited to controlled environments. In this dissertation, we present …

    ucf Repository record for Annotation Efficient Visual Recognition: from Semi-Supervised to Few-Shot Learning (opens in a new tab)

  16. A few-shot learning method for single-object visual anomaly detection

    We propose a few-shot learning method for visually inspecting single objects in an industrial setting. The proposed method is able to identify whether or not an object is defective by comparing its visual appearance with a small set of images of the “working” object, i.e., the object that passes …

    uoit Repository record for A few-shot learning method for single-object visual anomaly detection (opens in a new tab)

  17. Privacy-Preserving and Resource-Aware Intrusion Detection Using Federated Few-Shot Learning

    … limitations of centralized processing. Federated Learning (FL) offers a promising alternative by enabling decentralized model training across distributed devices without the need to share data. However, FL alone often struggles due to the limited availability of labeled intrusion data in …

    concordia Download PDF for Privacy-Preserving and Resource-Aware Intrusion Detection Using Federated Few-Shot Learning (opens in a new tab)

Page 1 of 12