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 537 for “"Zero-Shot"”.
-
Zero-shot Image Classification
… based on the textual descriptions. To this end, Zero-Shot Image Classification (ZIC) is proposed, which aims to make machines that can learn to classify unseen images like humans. The problem can be viewed from two different levels. Low-level technical issues are concerned by the general …
-
Vision Language Model Guided Zero-shot Classification
… tasks, with a particular emphasis on zero-shot settings in both 2D and 3D scenarios. We provide a comprehensive overview of Vision-Language Models, focusing on their pretraining datasets, architectural components, learning strategies, and representative models. By comparing with …
-
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 …
-
Representations in zero-shot meta-reinforcement learning
<p>A long-standing goal in the field of Artificial Intelligence (AI) is to create autonomous agents capable of making a sequence of decisions to interact with the world. When interacting with its environment, an agent will encounter new situations that it has not previously encountered and for …
-
Speaker Encoding for Zero-Shot Speech Synthesis
… only ten to thirty seconds of data is called zero-shot. However, there are currently no zero-shot speech synthesis methods able to produce human-like speech or replicate a speaker with a high degree of similarity. In this thesis, I propose a novel speaker encoder model to make zero-shot speech …
-
Multimodal Contrastive Models Through Zero-Shot Training
In today’s world, data exists in multiple modalities, primarily because human interaction with machines happens through varied sensory inputs. The three key modalities that have been extensively digitized are vision, text, and audio. We upload and interpret images, interact with computers using …
-
ZERO-SHOT DOMAIN ADAPTATION FOR SKETCH RECOGNITION
… παρούσα εργασία αντιμετωπίζουμε το πρόβλημα του “zero-shot domain adaptation” μεταξύ των πεδίων των εικόνων και σκίτσων. Τον όρο "zero-shot" τον εννοούμε ως προς τα σκίτσα. Ο όρος "domain adaptation" υπονοεί ότι πρόκειται να μάθουμε χρησιμοποιώντας εικόνες ως παραδείγματα και θα χρησιμοποιήσουμε …
-
Generalization and Specialization in Zero-Shot Learning
… of deep models. To overcome these obstacles, Zero-Shot Learning (ZSL) is proposed. ZSL aims to transfer classification ability from seen to unseen classes with semantic side information as the bridge. The success of ZSL requires two crucial abilities, i.e., the generalization ability to …
-
Concept Vectors for Zero-Shot Video Generation
Zero-shot video generation involves generating videos of concepts (action classes) that are not seen in the training phase. Even though the research community has explored conditional video generation for long high-resolution videos, zero-shot video remains a fairly unexplored and challenging task. …
-
General Keypoint Detection: Few-Shot and Zero-Shot
… works as follows: Firstly, inspired by few-shot learning, we introduce a new task called few-shot keypoint detection (FSKD) whose goal is to detect the corresponding keypoints in a query image given one or a few support images with keypoint annotations. Moreover, we propose a versatile FSKD …
-
Generalized Zero-Shot Learning through Similarity Distribution Matching
… categories are unlabeled or even unavailable. Zero-Shot Learning (ZSL) deals with classifying unseen visual categories that have no samples during training phase. In particular, ZSL is a classification task where some classes referred to as unseen classes have no training images. Instead, we …
-
Zero-Shot Robotic Grasping from Local Surface Geometry
… generalization. This thesis presents RCVGrasp, a zero-shot grasp prediction framework grounded solely in local surface geometry. Instead of modelling global object shape or identity, a parallel-jaw grasp is represented as a pair of local three-dimensional surface patches corresponding to the …
-
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 …
-
Prompting LLMs for Zero-Shot Next-Item Recommendation
… In particular, they have exhibited remarkable zero-shot performance in numerous natural language processing (NLP) tasks, showcasing their capacity to recommend without extensive training data. This thesis explores the untapped potential of integrating LLMs into sequential recommendations to …
-
Zero-shot human attribute classification using pretrained VLMs
… (CLIP) is a Vision-Language Model with promising zero-shot performance in several downstream tasks, without the need for fine-tuning or retraining, allowing end-users to simply input an image and ask for its characteristics. However, given the nature of the data used to train these models and the …
-
Commonsense for Zero-Shot Natural Language Video Localization
Zero-shot Natural Language-Video Localization (NLVL) has shown promising results in training NLVL models solely with raw video data through dynamic video segment proposal generation and pseudo-query annotations. However, existing pseudo-queries lack grounding in the source video and suffer from a …
-
Zero-Shot Scene Graph Relationship Prediction using VLMs
… recent surge of interest in open-vocabulary and zero-shot SGG, most approaches still require some form of training or adaptation on the target dataset, even when using Vision-Language Models (VLMs). In this work, we propose a training-free framework for the VLMs to predict scene graph …
-
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 …
-
Zero-shot Denoising and Debleeding Applied to Microscopic Imaging
… addresses these limitations by developing novel zero-shot image restoration techniques to enhance the quality and interpretability of biological images. In Chapter 2, I propose Noise2Fast, a method for rapid zero-shot image denoising specifically designed for automated live cell imaging under …
-
Foundational Local Features for Zero-Shot 6D Pose Estimation
… to The Feature Pose (B2TFPose), a training-free zero-shot method for 6DoF pose estimation of unseen objects from RGB images, with an extension to RGB-D. Using a single frozen DINOv3 vision transformer as its only pretrained component within the pose estimation pipeline, B2TFPose extracts dense …
Page 1 of 27