Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Ngo, Thi Phuong Nhung"'
Autor:
Nguyen, Duc Tam, Mummadi, Chaithanya Kumar, Ngo, Thi Phuong Nhung, Nguyen, Thi Hoai Phuong, Beggel, Laura, Brox, Thomas
Deep neural networks (DNNs) have been shown to over-fit a dataset when being trained with noisy labels for a long enough time. To overcome this problem, we present a simple and effective method self-ensemble label filtering (SELF) to progressively fi
Externí odkaz:
http://arxiv.org/abs/1910.01842
Autor:
Nguyen, Duc Tam, Dax, Maximilian, Mummadi, Chaithanya Kumar, Ngo, Thi Phuong Nhung, Nguyen, Thi Hoai Phuong, Lou, Zhongyu, Brox, Thomas
Deep neural network (DNN) based salient object detection in images based on high-quality labels is expensive. Alternative unsupervised approaches rely on careful selection of multiple handcrafted saliency methods to generate noisy pseudo-ground-truth
Externí odkaz:
http://arxiv.org/abs/1909.13055
Autor:
Nguyen, Duc Tam, Ngo, Thi-Phuong-Nhung, Lou, Zhongyu, Klar, Michael, Beggel, Laura, Brox, Thomas
We consider the problem of training a model under the presence of label noise. Current approaches identify samples with potentially incorrect labels and reduce their influence on the learning process by either assigning lower weights to them or compl
Externí odkaz:
http://arxiv.org/abs/1906.00216