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 73 for “"Contrastive Learning"”.
-
Contrastive Learning of Auditory Representations
Learning rich visual representations using contrastive self-supervised learning has been extremely successful. However, it is still a major question whether we could use a similar approach to learn more efficient auditory and audio-visual representations. In this thesis, we expand on prior …
-
Adversarial graph contrastive learning with information regularization
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms
-
Dynamics of Gradient Flow with Contrastive Learning
Contrastive learning (CL), in di erent forms, has been shown to learn discriminatory representations for downstream tasks without the need of human labeling. In the representation space learnt via CL, each class collapses to a distinct vertex of a simplex on a hypersphere during training. This …
-
Improving Natural Language Understanding via Contrastive Learning Methods
… Among the previous NLU solutions, representation learning methods have recently become the mainstream, which maps textual data into low-dimensional vector spaces for downstream tasks. With the development of deep neural networks, text representation learning has achieved state-of-the-art …
-
Towards General-purpose Vision via Multiview Contrastive Learning
Representation learning plays a key role in building robust and general-purpose vision learners, and is a long-standing problem. It becomes increasingly interesting with the continuing explosion of data in our era. However, most previous approaches are based on specific designs of strategies that …
-
Uncertainty-Inclusive Contrastive Learning for Leveraging Synthetic Images
… synthesized training data to improve few-shot learning performance. Prevailing approaches treat all generated data as uniformly important, neglecting the fact that the quality of generated images varies across different domains, datasets, and methods of generation. Using poor-quality images can …
-
Scaling contrastive learning batch size by two orders of magnitude
Contrastive learning has emerged as a powerful framework for unsupervised representation learning, allowing models to learn by maximizing agreement between related samples and distinguishing dissimilar ones. However, contrastive learning frameworks are fundamentally limited by the number of …
-
Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis
… a seminal tool in self-supervised representation learning, contrastive learning has gained unprecedented attention in recent years. In essence, contrastive learning aims to leverage pairs of positive and negative samples for representation learning, which relates to exploiting neighborhood …
-
LLM2IR: simple unsupervised contrastive learning makes long-context LLM great retriever
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms
-
Enhancing Breast Cancer Detection Through Combination of Contrastive Learning and Adversarial Domain Adaptation
… and therapies. This study aims to explore deep-learning techniques that can be utilized to implement and train a model to identify breast cancer cases in mammograms. Current deep learning-based diagnostic techniques are hindered by two fundamental issues: the expensive and time-consuming task of …
-
Graph Neural Networks for Health-Aware Food and Multi-Criteria Recommendation Systems
… and the Multiview Graph Dual Attention and Contrastive Learning for Multi-Criteria Recommender Systems (D-MGAC). The first framework, HFRS-DA, addresses the challenge of effectively integrating heterogeneous information and uncovering meaningful relationships among entities in food and …
-
Improving utilization, granularity, and interpretability in visual representation learning
… three works that revolve around improving the learning and usage of deep model features in computer vision. The first work is about improving style transfer, which is a generative artistic method that leverages pretrained deep model features. Style transfer boils down to a distribution matching …
-
Computational Methods for Biomedical Imaging
… by these beams is well-suited for machine learning applications, where 2D images can contain 3D contextual information without the added computational overhead of performing 3D convolutions. We begin with a review of important non-diffracting beams in the existing literature, and proceed to …
-
Detecting Irregular Network Activity with Adversarial Learning and Expert Feedback
… thesis proposes a novel self-supervised deep learning framework CAAD for anomaly detection in wireless communication systems. Specifically, CAAD employs powerful adversarial learning and contrastive learning techniques to learn effective representations of normal and anomalous behavior in …
-
Contrastive representation learning for bioimage quantification
Deep learning has enabled unprecedented progress towards automating the analysis and quantification of large-scale, high-resolution imaging data. However, the majority of current deep learning systems for bioimage analysis is trained with manual annotations, leading to limitations in their …
-
Hybrid ConVIRT - enhancing medical image-text representation learning of vision language models
… advancements in image-text representation learning, as demonstrated by Hybrid-ConVIRT, which builds on contrastive learning frameworks such as ConVIRT and MedCLIP. These medical contrastive learning models trained on domain-specific datasets, have tackled issues related to the costly, …
-
Robust Learning from Uncurated Data
The field of machine learning has witnessed a growing interest in learning from uncurated data, which involves training models from data that has not been carefully curated or labeled. However, this type of data is typically noisy, incomplete, and riddled with errors, making it challenging for …
-
Enhancing Self-Supervised Learning through Transformations in Higher Activation Space
… Augmentation through extensive experiments on contrastive learning tasks in computer vision and NLP domains, where we observe substantial performance gains with ResNets and Transformers as the underlying models. Our experimentation reveals that targeting deeper layers with Deep Augmentation …
-
Classifying and Displaying Brain-waves through Self-supervised Learning
… constructing labeled datasets for supervised learning from EEG signals is expensive and time-consuming. Moreover, the existing datasets use incompatible EEG setups (e.g. different numbers of channels, sampling rates, types of sensors, etc.) that make them hard to fuse to obtain larger …
Page 1 of 4