Physics-informed machine learning in prognostics and health management: State of the art and challenges
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 …
entire life health service. It has long benefited from intensive research into physics modeling …
Multi-stage image denoising with the wavelet transform
Deep convolutional neural networks (CNNs) are used for image denoising via automatically
mining accurate structure information. However, most of existing CNNs depend on enlarging …
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 …
measurements and corresponding RGB images. Currently, spatial propagation networks …
Lightweight salient object detection in optical remote-sensing images via semantic matching and edge alignment
Recently, relying on convolutional neural networks (CNNs), many methods for salient object
detection in optical remote-sensing images (ORSI-SOD) are proposed. However, most …
detection in optical remote-sensing images (ORSI-SOD) are proposed. However, most …
Decoupled dynamic filter networks
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 …
use, standard convolution has two main shortcomings: Content-agnostic and Computation …
LAGConv: Local-context adaptive convolution kernels with global harmonic bias for pansharpening
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 …
resolution image by fusing a multispectral (MS) image and a panchromatic (PAN) image …
Pointconvformer: Revenge of the point-based convolution
We introduce PointConvFormer, a novel building block for point cloud based deep network
architectures. Inspired by generalization theory, PointConvFormer combines ideas from …
architectures. Inspired by generalization theory, PointConvFormer combines ideas from …
Group R-CNN for weakly semi-supervised object detection with points
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 …
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
Recently, the performance of single image super-resolution (SR) has been significantly
improved with powerful networks. However, these networks are developed for image SR …
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
Fine-grained image classification is a challenging computer vision task where various
species share similar visual appearances, resulting in misclassification if merely based on …
species share similar visual appearances, resulting in misclassification if merely based on …