Physics-informed machine learning in prognostics and health management: State of the art and challenges

D Weikun, KTP Nguyen, K Medjaher, G Christian… - Applied Mathematical …, 2023 - Elsevier
Prognostics and health management (PHM) plays a constructive role in the equipment's
entire life health service. It has long benefited from intensive research into physics modeling …

Multi-stage image denoising with the wavelet transform

C Tian, M Zheng, W Zuo, B Zhang, Y Zhang, D Zhang - Pattern Recognition, 2023 - Elsevier
Deep convolutional neural networks (CNNs) are used for image denoising via automatically
mining accurate structure information. However, most of existing CNNs depend on enlarging …

Dynamic spatial propagation network for depth completion

Y Lin, T Cheng, Q Zhong, W Zhou… - Proceedings of the aaai …, 2022 - ojs.aaai.org
Image-guided depth completion aims to generate dense depth maps with sparse depth
measurements and corresponding RGB images. Currently, spatial propagation networks …

Lightweight salient object detection in optical remote-sensing images via semantic matching and edge alignment

G Li, Z Liu, X Zhang, W Lin - IEEE Transactions on Geoscience …, 2023 - ieeexplore.ieee.org
Recently, relying on convolutional neural networks (CNNs), many methods for salient object
detection in optical remote-sensing images (ORSI-SOD) are proposed. However, most …

Decoupled dynamic filter networks

J Zhou, V Jampani, Z Pi, Q Liu… - Proceedings of the …, 2021 - openaccess.thecvf.com
Convolution is one of the basic building blocks of CNN architectures. Despite its common
use, standard convolution has two main shortcomings: Content-agnostic and Computation …

LAGConv: Local-context adaptive convolution kernels with global harmonic bias for pansharpening

ZR Jin, TJ Zhang, TX Jiang, G Vivone… - Proceedings of the AAAI …, 2022 - ojs.aaai.org
Pansharpening is a critical yet challenging low-level vision task that aims to obtain a higher-
resolution image by fusing a multispectral (MS) image and a panchromatic (PAN) image …

Pointconvformer: Revenge of the point-based convolution

W Wu, L Fuxin, Q Shan - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
We introduce PointConvFormer, a novel building block for point cloud based deep network
architectures. Inspired by generalization theory, PointConvFormer combines ideas from …

Group R-CNN for weakly semi-supervised object detection with points

S Zhang, Z Yu, L Liu, X Wang… - Proceedings of the …, 2022 - openaccess.thecvf.com
We study the problem of weakly semi-supervised object detection with points (WSSOD-P),
where the training data is combined by a small set of fully annotated images with bounding …

Learning a single network for scale-arbitrary super-resolution

L Wang, Y Wang, Z Lin, J Yang… - Proceedings of the …, 2021 - openaccess.thecvf.com
Recently, the performance of single image super-resolution (SR) has been significantly
improved with powerful networks. However, these networks are developed for image SR …

Dynamic mlp for fine-grained image classification by leveraging geographical and temporal information

L Yang, X Li, R Song, B Zhao, J Tao… - Proceedings of the …, 2022 - openaccess.thecvf.com
Fine-grained image classification is a challenging computer vision task where various
species share similar visual appearances, resulting in misclassification if merely based on …