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 13 of 13 for “"label noise"”.
-
Noisy with a Chance of Mislabels: A Local and Training Dynamics Perspective on Detecting Label Noise in Deep Classification
Noisy labels are a pervasive challenge in modern supervised learning, especially in highstakes domains such as healthcare, where model reliability is critical. Detecting and mitigating the influence of mislabeled data is essential to improving both performance and interpretability. Building on …
-
Understanding Deep Learning with Noisy Labels
… datasets. However, collecting high-quality labels for large-scale datasets is expensive and time-consuming or even infeasible in practice. Approaches to addressing this issue include: acquiring labels from non-expert labelers, crowdsourcing-like platforms or other unreliable resources, where …
-
TOWARDS RELIABLE AI UNDER DISTRIBUTION SHIFTS: A DATA-CENTRIC PERSPECTIVE
… when training with empirical risk minimization, label noise exacerbates the effect of spurious correlations in the training data. Second, we introduce two data-centric strategies to diagnose and improve quality of data. To detect mislabeled data, we propose an efficient approximation for the …
-
Dealing with Inaccurate and Incomplete Labels in Industrial Streaming Data
… desired task in industrial environments with few labelled data samples and drifting data features poses a severe challenge. In this thesis, we will address two main technical challenges in the field of analyzing industrial streaming data: (1) how to efficiently train models with only partially …
-
Classification of Faults in Railway Ties Using Computer Vision and Machine Learning
… performance of all approaches. The problem of label noise is also analyzed. The techniques proposed in this work will help in reducing the time, cost and dependency on experts involved in traditional railway tie inspections and will facilitate efficient documentation and planning for …
-
Investigation on ImageNet Remaining Errors with TRAK
… reassessing Imagenet, a nontrivial amount of label error and noise is found and effort had been made to fix this label noise in the test set, mainly through manual review. However, not many studies have dived into fixing labels for the training set, largely due to its large scale. The proposed …
-
Robust Deep Learning Methodologies for Weakly Supervised Remote Sensing Image Classification
… DL is often hindered by scarce and imperfect labeled data. This limits the effectiveness of DL in RS, requiring the development of DL techniques that exploit different kinds of imperfect and weak annotations. This thesis addresses this critical challenge by developing a suite of novel …
-
Towards AI Safety via Interpretability and Oversight
… including data scarcity, class imbalance, label noise, and covariate shift. While SAEs occasionally outperform baseline methods, they fail to consistently enhance task performance, underscoring a potentially critical limitation of SAEs. Lastly, we introduce a quantitative framework to …
-
Confident Learning for Machines and Humans
… ability to deal with the uncertainty in the labels upon which it is trained. To this end, we introduce confident learning whereby a machine (like humans) must learn with noisy-labeled data, directly quantify and identify label noise, and unlearn misconceptions by re-learning with confidence …
-
Multi-server federated learning in vehicular edge computing
… Dirichlet-based non-IID splits with client-level label noise and mobility-induced dropouts, as well as additional experiments with ResNet-18 on GTSRB, T-BIDS converges faster and achieves higher, more stable accuracy and lower loss than baseline selectors. Second, we design an edge-based …
-
Example weighting for deep representation learning
… cases: (1) in-distribution anomalies, e.g., label noise; (2) out-of-distribution anomalies, e.g., input with no object of interest; (3) sample imbalance.
-
Information extraction with weak supervision
… these tasks, aiming to reduce reliance on manual labeling while maintaining high performance. The first part of the dissertation presents a novel framework, Confidence-Based Multi-Class Positive and Unlabeled (Conf-MPU) learning, designed to enhance the performance of distantly supervised NER. By …
-
Towards a Reliable Deep Learning Framework for Prostate Cancer Diagnosis using Ultrasound
… models for PCa detection is hindered by noisy labels and cancer heterogeneity. The purpose of this work is to develop a clinically applicable framework for DL-based detection of PCa from ultrasound that is robust to noise and uncertainty inherent to ultrasound images and their associated gold …