Over the past few years, the computer vision domain has evolved and made a revolutionary transition from human-engineered features to automated features to address challenging …
Y Liu, X Dong, D Zhang, S Xu - Neurocomputing, 2024 - Elsevier
Abstract Deep Supervised Salient Object Detection (SSOD) excessively relies on large- scale annotated pixel-level labels which consume intensive labour acquiring high quality …
Y Liu, D Cheng, D Zhang, S Xu… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Capsule networks (CapsNets) have been known difficult to develop a deeper architecture, which is desirable for high performance in the deep learning era, due to the complex …
X Ma, H Zhong, Y Li, J Ma, Z Cui… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Accurate and reliable traffic forecasting for complicated transportation networks is of vital importance to modern transportation management. The complicated spatial dependencies …
We introduce a new routing algorithm for capsule networks, in which a child capsule is routed to a parent based only on agreement between the parent's state and the child's vote …
Y Guo, G Camporese, W Yang… - Proceedings of the …, 2021 - openaccess.thecvf.com
In open set recognition, a classifier has to detect unknown classes that are not known at training time. In order to recognize new categories, the classifier has to project the input …
Lung and colon cancers are two of the most common causes of death and morbidity in humans. One of the most important aspects of appropriate treatment is the histopathological …
Adversarial examples raise questions about whether neural network models are sensitive to the same visual features as humans. In this paper, we first detect adversarial examples or …
The profound impact of deep learning and particularly of convolutional neural networks (CNNs) in automatic image processing has been decisive for the progress and evolution of …