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 16 of 16 for “"Pseudo labels"”.
-
Domain Adaptation with a Classifier Trained by Robust Pseudo-Labels
… algorithm to infer the robustness of the target pseudo-labels. With the help of target pseudo-labels, I propose two novel types of classifiers: (1) a target-oriented classifier (TO); and (2) a centroid-oriented classifier (CO). Extensive experiments show that these two classifiers exhibit …
-
Self-supervised multi-contrast MRI denoising
… MRI denoising. C2S utilizes self-generated pseudo-labels from noisy data to enhance contrast fusion and Signal-to-Noise Ratio (SNR), providing a robust solution that facilitates shorter scanning times or improved spatial resolution—critical factors in enhancing patient experience and …
-
Self-Training for Natural Language Processing
… practice of training models with real data and pseudo labels, we also explore the possibility of automatically generating synthetic data for better explainability, robustness, and domain adaptation performance. We show the performance improvement achieved by our methods on different natural …
-
An investigation into the use of ConvNext within IICS/IIDS framework for person Re-ID
… Building upon IICS/IIDS framework that generates pseudo labels through intra and inter stages and utilizing techniques such as Adaptive Instance and Batch Normalization (AIBN) and Transform Normalization (TNorm) to minimize intra-camera and inter-camera variations respectively, our work emphasizes …
-
Self-Training and Calibration for Learning with Limited Data
… is to use a trained model to create pseudo-labels for unlabeled data and then select some of those samples to add to the labeled dataset. One way to do this is to pick samples for which the model has high confidence. However, many models are not well-calibrated, which means that the …
-
PASSIVE RADAR TRACK CLUSTERING: HIGHER FIDELITY OF TARGET IDENTIFICATION AND CLASSIFICATION OF UNLABELED TRACKS
… and Gaussian Mixture Models (GMMs) to generate pseudo-labels from limited labeled data for classifier training. The Max Hold Spectrogram performs the best for both SL and USL approaches. GMMs outperform K–Means for all unsupervised clustering implementations. The SSL models are compared against …
-
Weakly supervised aspect extraction for domain-specific texts
… ones. The self-training mechanism provides more pseudo labels in addition to limited supervision. Extensive experiments on real-world datasets demonstrate the superior performance of our proposed framework, as well as the effectiveness of both the attention module and the self-training mechanism. …
-
Inference of the Novel Coronavirus 2019 in Patients fitted with Boston Scientific Medical Hardware
… of patients with clinically established COVID-19 labels, we leverage the power of semi-supervised learning to extract useful signals and characterize the profile of COVID-19 in Boston Scientific Heart Failure patients. Specifically, we utilize constrained K means clustering to understand if there …
-
Unsupervised feature analysis for high dimensional big data
… of traditional feature analysis often relies on labels of the training data examples. However, in the era of big data, label information is often unavailable. In the unsupervised scenario, it is more challenging to do feature analysis. Two important research topics in unsupervised feature …
-
Lightweight edge AI vision models for IoT-based insect monitoring
… both segmentation masks and insect count labels. In addition to its accuracy, it runs entirely on-board MCUs without reliance on a server or cloud support. Quantitatively, SemiY-Net reduced parameters by >75% compared to state-of-the-art models, required <1 MB of storage and RAM, and …
-
Quake-OVUDA: Component-Level AI-Based Post-Earthquake Building Inspections with Vision–Language Guided Unsupervised Domain Adaptation
… dataset, QuakeCity, and is used to generate pseudo-labels for unlabeled real-world images that are used in DAFormer’s self-supervised learning step. To further improve classification performance, particularly of nuanced damage classes, additional refinement and classification of instances …
-
THE CHALLENGE OF DOMAIN SHIFT IN REAL-WORLD ROBOTIC VISION: TOWARD SCALABLE, UNSUPERVISED, AND CLOUD-BASED ADAPTATION
… and the 3D world to enhance the quality of the pseudo-labels, thus enabling self-supervised adaptation. Third, we address adaptation in cloud-based robotic perception, where intensive inference required by neural networks is offloaded to remote servers to deal with the limited hardware …
-
Learning to Adapt Neural Networks Across Visual Domains
… domains. Moreover, to counteract the noisy pseudo-labels we propose to use a co-teaching strategy with a dual classifier head. To enable smoother adaptation, we propose a domain curriculum learning ,when the domain labels are available, that adapts to one target domain at a time, with …
-
Optimal and Safe Semi-supervised Estimation and Inference for High-dimensional Linear Regression
… estimates for the conditional mean function as pseudo-labels for unlabeled data, which attains the lower bound provided that the imputation for the conditional mean function is consistent with a proper rate. To tackle the problem that without any model assumptions for the conditional mean, we …
-
Towards Data Efficiency and Controllable Representations for Deep Learning in Resource-Constrained Domains
… zero-shot annotation to generate high-quality pseudo-labels, which are subsequently used to train a domain-specific model via knowledge distillation. This approach significantly enhances data efficiency, reducing the need for annotated samples several times over in the tested scenario of image …
-
Semi-Supervised Learning for Scalable and Robust Visual Search
… the graph construction process and the initial labels. We propose a new bivariate graph transduction formulation and an efficient solution via an alternating minimization procedure. Based on this bivariate framework, we also develop new methods to filter unreliable and noisy labels. Extensive …