IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Oct 21, 2022
Transferable adversarial attacks against Deep neural networks (DNNs) have received broad attention in recent years. An adversarial example can be crafted by a surrogate model and then attack the unknown target model successfully, which brings a sever...
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Oct 21, 2022
Unsupervised domain adaptation (UDA) enables a learning machine to adapt from a labeled source domain to an unlabeled target domain under the distribution shift. Thanks to the strong representation ability of deep neural networks, recent remarkable a...
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Sep 14, 2022
Accurate image segmentation plays a crucial role in medical image analysis, yet it faces great challenges caused by various shapes, diverse sizes, and blurry boundaries. To address these difficulties, square kernel-based encoder-decoder architectures...
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Sep 8, 2022
Although deep neural networks (DNNs) have been shown to be susceptible to image-agnostic adversarial attacks on natural image classification problems, the effects of such attacks on DNN-based texture recognition have yet to be explored. As part of ou...
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Aug 2, 2022
Although 3D hand pose estimation has made significant progress in recent years with the development of the deep neural network, most learning-based methods require a large amount of labeled data that is time-consuming to collect. In this paper, we pr...
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Jul 14, 2022
Different people age in different ways. Learning a personalized age estimator for each person is a promising direction for age estimation given that it better models the personalization of aging processes. However, most existing personalized methods ...
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Jul 12, 2022
Most existing studies on unsupervised domain adaptation (UDA) assume that each domain's training samples come with domain labels (e.g., painting, photo). Samples from each domain are assumed to follow the same distribution and the domain labels are e...
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Jul 12, 2022
In this paper, we address the Online Unsupervised Domain Adaptation (OUDA) problem and propose a novel multi-stage framework to solve real-world situations when the target data are unlabeled and arriving online sequentially in batches. Most of the tr...
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Jul 4, 2022
Most existing methods of human parsing still face a challenge: how to extract the accurate foreground from similar or cluttered scenes effectively. In this paper, we propose a Grammar-induced Wavelet Network (GWNet), to deal with the challenge. GWNet...
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Jun 29, 2022
Real-world datasets commonly have noisy labels, which negatively affects the performance of deep neural networks (DNNs). In order to address this problem, we propose a label noise robust learning algorithm, in which the base classifier is trained on ...