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 7 of 7 for “"Mislabeled Samples"”.
-
Label Cleaning Multiple Instance Learning: Refining Coarse Annotations on Single Whole-slide Imaging
… of them tackle the refinement problem, where the mislabeled samples need to be explicitly identified and relabeled. In this thesis, we propose a method called Label Cleaning Multiple Instance Learning (LC-MIL) to refine annotations on a single WSI. Patches cropped from a WSI with noisy labels are …
-
Machine Learning for handwriting text recognition in historical documents
… We also contribute an algorithm for purging mislabeled samples that affect the learning of models. Finally, we develop a variational auto encoder method for generating synthetic samples of handwritten text images for data augmentation. Experiments are performed on various historical …
-
Machine learning tecniques applied to hydrate failure detection on production lines
… by real data, it is usual to face a lot of mislabeled data, which can significantly jeopardize the model performance. Therefore, we deploy a technique to reduce the mislabeled samples, which presented an improvement of 7.93%, on average, reaching over 80% of accuracy in all single-class …
-
Deep Learning-Based Medical Image Analysis for Enhanced Diagnosis and Severity Assessment of Viral Pneumonia
… data valuation (Data Shapley) to identify mislabeled samples in chest image training datasets; (ii) Introducing a domain-adaptive strategy guided by model prediction confidence to improve the generalization of DL segmentation models; (iii) Developing robust DL frameworks for precise …
-
Robust Approaches for Learning with Noisy Labels
… method that automatically distinguishes the mislabeled samples and prevents the model from memorizing them; 4) EM-enhanced loss: a family of robust loss functions that not only mitigates the influence of noisy labels, but also avoids underfitting problem; 5) MixNN: a framework that trains the …
-
Robust deep learning for computer vision to counteract data scarcity and label noise
… learning approach is extremely sensitive to mislabeled datasets. Training deep models on such noisy labels often leads to a strong model overfitting.<br><br>To counteract this overfitting effect, we propose a simple but effective method of filtering out wrong labels progressively with …
-
Data debugging for machine learning
… phase, the training dataset may contain mislabeled, anomalous samples, and/or data poisons. During the model deployment phase, adversarial attacks may be crafted or the statistical properties between training and serving data may change, a phenomenon called data drift, affecting their …