Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Ikami, Daiki"'
Rotation is frequently listed as a candidate for data augmentation in contrastive learning but seldom provides satisfactory improvements. We argue that this is because the rotated image is always treated as either positive or negative. The semantics
Externí odkaz:
http://arxiv.org/abs/2210.12681
Many variants of unsupervised domain adaptation (UDA) problems have been proposed and solved individually. Its side effect is that a method that works for one variant is often ineffective for or not even applicable to another, which has prevented pra
Externí odkaz:
http://arxiv.org/abs/2106.01656
Positive-unlabeled learning refers to the process of training a binary classifier using only positive and unlabeled data. Although unlabeled data can contain positive data, all unlabeled data are regarded as negative data in existing positive-unlabel
Externí odkaz:
http://arxiv.org/abs/2103.04685
Publikováno v:
ICPR2020
We propose a new optimization framework for aleatoric uncertainty estimation in regression problems. Existing methods can quantify the error in the target estimation, but they tend to underestimate it. To obtain the predictive uncertainty inherent in
Externí odkaz:
http://arxiv.org/abs/2011.01655
Semi-supervised learning (SSL) has been proposed to leverage unlabeled data for training powerful models when only limited labeled data is available. While existing SSL methods assume that samples in the labeled and unlabeled data share the classes o
Externí odkaz:
http://arxiv.org/abs/2007.11330
Convolutional neural network (CNN) architectures utilize downsampling layers, which restrict the subsequent layers to learn spatially invariant features while reducing computational costs. However, such a downsampling operation makes it impossible to
Externí odkaz:
http://arxiv.org/abs/1803.11370
Publikováno v:
CVPR 2018, pp.5552--5550
Deep neural networks (DNNs) trained on large-scale datasets have exhibited significant performance in image classification. Many large-scale datasets are collected from websites, however they tend to contain inaccurate labels that are termed as noisy
Externí odkaz:
http://arxiv.org/abs/1803.11364
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
The extraction of useful deep features is important for many computer vision tasks. Deep features extracted from classification networks have proved to perform well in those tasks. To obtain features of greater usefulness, end-to-end distance metric
Externí odkaz:
http://arxiv.org/abs/1712.10151
We propose the residual expansion (RE) algorithm: a global (or near-global) optimization method for nonconvex least squares problems. Unlike most existing nonconvex optimization techniques, the RE algorithm is not based on either stochastic or multi-
Externí odkaz:
http://arxiv.org/abs/1705.09549
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.