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 83 for “"Zero-Shot Learning"”.

  1. Zero-shot Learning for Visual Recognition Problems

    In this thesis we discuss different aspects of zero-shot learning and propose solutions for three challenging visual recognition problems: 1) unknown object recognition from images 2) novel action recognition from videos and 3) unseen object segmentation. In all of these three problems, we have two …

    manitoba Repository record for Zero-shot Learning for Visual Recognition Problems (opens in a new tab)

  2. Generalization and Specialization in Zero-Shot Learning

    … has made remarkable success due to deep learning techniques and vast amounts of labeled data. However, in real-world scenarios, the data distribution is long-tailed, making acquiring sufficient labels difficult, thus hindering the performance of deep models. To overcome these obstacles, …

    unsw Repository record for Generalization and Specialization in Zero-Shot Learning (opens in a new tab)

  3. Generalized Zero-Shot Learning through Similarity Distribution Matching

    Recent advances in supervised learning methods in vision, specifically deep learning frameworks, are primarily built on the abundance of labeled images. However, image labeling is a laborious task, therefore many visual categories are unlabeled or even unavailable. Zero-Shot Learning (ZSL) deals …

    rice Repository record for Generalized Zero-Shot Learning through Similarity Distribution Matching (opens in a new tab)

  4. Optimising image feature zero-shot-learning with EEG

    … not present during training, i.e. we apply zero-shot learning.<br/><br/>To achieve this goal, we first investigate a discriminative feature extraction process for EEG brain data and establish a baseline evaluation of exemplar and category-level decoding. Once competitive decoding rates are …

    qu-belfast Repository record for Optimising image feature zero-shot-learning with EEG (opens in a new tab) Download PDF for Optimising image feature zero-shot-learning with EEG (opens in a new tab)

  5. A TWO-STAGE APPROACH TOWARDS GENERALIZED ZERO-SHOT LEARNING

    Generalized zero-shot learning(GZSL) is a problem setup in which a model is trained to recognize classes it has never seen during training by leveraging auxiliary information, such as textual descriptions or semantic embeddings, about those classes. In the inference phase, samples consist of …

    nus Repository record for A TWO-STAGE APPROACH TOWARDS GENERALIZED ZERO-SHOT LEARNING (opens in a new tab) Download file for A TWO-STAGE APPROACH TOWARDS GENERALIZED ZERO-SHOT LEARNING (opens in a new tab)

  6. Class Representative Projection for Text-based Zero-Shot Learning

    … been significant advances in supervised machine learning and enormous benefits from deep learning for a range of diverse applications. Despite the success of deep learning, in reality, very few works have shown progress in text classification. Transfer learning, known as the zero-shot learning …

    umkc Repository record for Class Representative Projection for Text-based Zero-Shot Learning (opens in a new tab)

  7. Few-Shot and Zero-Shot Learning for Information Extraction

    … extraction in e-commerce, with few labeled (few-shot learning) or even no labeled (zero-shot learning) training data. We explore multi-source auxiliary information and novel learning techniques to integrate semantic auxiliary information with the input text to improve few-shot learning and …

    vt Repository record for Few-Shot and Zero-Shot Learning for Information Extraction (opens in a new tab)

  8. Mid-level representations for action recognition and zero-shot learning

    … and the other two problems in the task of zero-shot learning. For the first problem, we devise a representation suitable for characterising human actions on the basis of a sequence of pose estimates generated by an RGB-D sensor. We show that discriminate sequence of poses typically occur …

    adelaide Repository record for Mid-level representations for action recognition and zero-shot learning (opens in a new tab)

  9. Data Augmentation for Multi-domain and Multi-modal Generalised Zero-shot Learning

    … training and inference for Generalised Zero-Shot Learning (GZSL). GZSL introduces an experimental setup, where the training set contains images and semantic information for a set of seen classes, and semantic information for a set of unseen classes, where there is no overlap between the …

    adelaide Repository record for Data Augmentation for Multi-domain and Multi-modal Generalised Zero-shot Learning (opens in a new tab)

  10. Towards Graph Foundation Models: Few-shot and Zero-shot Learning on Graphs

    … (GNNs) have emerged as powerful tools for learning effective graph representations through iterative message passing, significantly improving performance in tasks such as node classification, link prediction, and graph classification. However, the success of GNNs largely depends on abundant …

    wustl Repository record for Towards Graph Foundation Models: Few-shot and Zero-shot Learning on Graphs (opens in a new tab)

  11. Improving Foreign Accent Conversion with Zero-Shot Learning and Explicit Prosody Modeling

    Pronunciation learning is a significant aspect of second language (L2) acquisition, particularly for older learners who often struggle with acquiring a native-like accent. While vocabulary, grammar, and writing skills can be developed well into adulthood, achieving native-like pronunciation becomes …

    tamu Repository record for Improving Foreign Accent Conversion with Zero-Shot Learning and Explicit Prosody Modeling (opens in a new tab)

  12. Exploring 3D Data and Beyond in a Low Data Regime

    … There have been fewer advances using deep learning methods in the area of point clouds compared to 2D images and videos, partially because the data in a point cloud are typically unordered as opposed to the pixels in a 2D image, which implies standard deep learning architectures are not …

    anu Repository record for Exploring 3D Data and Beyond in a Low Data Regime (opens in a new tab)

  13. GAN you train your network

    Zero-shot classifiers identify unseen classes — classes not seen during training. Specifically, zero-shot models classify attribute information associated with classes (e.g., a zebra has stripes but a lion does not). Lately, the usage of generative adversarial networks (GAN) for zero-shot learning …

    colostate Repository record for GAN you train your network (opens in a new tab)

  14. Learning Transferable Representations for Visual Recognition

    … last half-decade, a new renaissance of machine learning originates from the applications of convolutional neural networks to visual recognition tasks. It is believed that a combination of big curated data and novel deep learning techniques can lead to unprecedented results. However, the …

    ucf Repository record for Learning Transferable Representations for Visual Recognition (opens in a new tab)

  15. 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)

  16. A Retrieval Augmented Approach to Improving Accuracy of Biomedical Term Normalization by Large Language Models

    … research studies indicated that LLMs employing zero-shot learning tend to exhibit low accuracy and are prone to frequent hallucinations. We propose a retrieval augmented generation (RAG) approach to address these limitations and enhance normalization accuracy. We generated synthetic test sets of …

    mo-state Repository record for A Retrieval Augmented Approach to Improving Accuracy of Biomedical Term Normalization by Large Language Models (opens in a new tab)

  17. Combining structured knowledge and data-driven representations for object states classification

    … and generalization capabilities, particularly in zero-shot learning scenarios. Our core contribution is a novel approach to Object-agnostic Zero-Shot State Classification that leverages KGs to encode commonsense knowledge and employs GNNs to learn expressive embeddings capturing rich semantic …

    greece Repository record for Combining structured knowledge and data-driven representations for object states classification (opens in a new tab)

  18. VISUAL AND SEMANTIC KNOWLEDGE TRANSFER FOR NOVEL TASKS

    … is a critical component in a supervised machine learning system. Many successful applications of learning systems on various tasks are based on a large amount of labeled data. For example, deep convolutional neural networks have surpassed human performance on ImageNet classification, which …

    temple Repository record for VISUAL AND SEMANTIC KNOWLEDGE TRANSFER FOR NOVEL TASKS (opens in a new tab)

Page 1 of 5