arXiv subjects

Yubao Sun

Publications and source records attributed to Yubao Sun.

6 recordsLinked to original sources

arXiv2024

ROA-BEV: 2D Region-Oriented Attention for BEV-based 3D Object Detection

Vision-based Bird's-Eye-View (BEV) 3D object detection has recently become popular in autonomous driving. However, objects with a high similarity to the background from a camera perspective cannot be detected well by existing methods. In this paper, we propose a BEV-based 3D Object Detection Network with 2D Region-Oriented Attention (ROA-BEV), which enables the backbone to focus more on feature learning of the regions where objects exist. Moreover, our method further enhances the information feature learning ability of ROA through multi-scale structures. Each block of ROA utilizes a large kernel to ensure that the receptive field is large enough to catch information about large objects. Experiments on nuScenes show that ROA-BEV improves the performance based on BEVDepth. The source codes of this work will be available at https://github.com/DFLyan/ROA-BEV.

cs.CV↗

arXiv2021

Unsupervised Spatial-spectral Network Learning for Hyperspectral Compressive Snapshot Reconstruction

Hyperspectral compressive imaging takes advantage of compressive sensing theory to achieve coded aperture snapshot measurement without temporal scanning, and the entire three-dimensional spatial-spectral data is captured by a two-dimensional projection during a single integration period. Its core issue is how to reconstruct the underlying hyperspectral image using compressive sensing reconstruction algorithms. Due to the diversity in the spectral response characteristics and wavelength range of different spectral imaging devices, previous works are often inadequate to capture complex spectral variations or lack the adaptive capacity to new hyperspectral imagers. In order to address these issues, we propose an unsupervised spatial-spectral network to reconstruct hyperspectral images only from the compressive snapshot measurement. The proposed network acts as a conditional generative model conditioned on the snapshot measurement, and it exploits the spatial-spectral attention module to capture the joint spatial-spectral correlation of hyperspectral images. The network parameters are optimized to make sure that the network output can closely match the given snapshot measurement according to the imaging model, thus the proposed network can adapt to different imaging settings, which can inherently enhance the applicability of the network. Extensive experiments upon multiple datasets demonstrate that our network can achieve better reconstruction results than the state-of-the-art methods.

eess.IV↗

arXiv2016

Graph Regularized Low Rank Representation for Aerosol Optical Depth Retrieval

In this paper, we propose a novel data-driven regression model for aerosol optical depth (AOD) retrieval. First, we adopt a low rank representation (LRR) model to learn a powerful representation of the spectral response. Then, graph regularization is incorporated into the LRR model to capture the local structure information and the nonlinear property of the remote-sensing data. Since it is easy to acquire the rich satellite-retrieval results, we use them as a baseline to construct the graph. Finally, the learned feature representation is feeded into support vector machine (SVM) to retrieve AOD. Experiments are conducted on two widely used data sets acquired by different sensors, and the experimental results show that the proposed method can achieve superior performance compared to the physical models and other state-of-the-art empirical models.

cs.LG↗

arXiv2016

Elastic Net Hypergraph Learning for Image Clustering and Semi-supervised Classification

Graph model is emerging as a very effective tool for learning the complex structures and relationships hidden in data. Generally, the critical purpose of graph-oriented learning algorithms is to construct an informative graph for image clustering and classification tasks. In addition to the classical $K$-nearest-neighbor and $r$-neighborhood methods for graph construction, $l_1$-graph and its variants are emerging methods for finding the neighboring samples of a center datum, where the corresponding ingoing edge weights are simultaneously derived by the sparse reconstruction coefficients of the remaining samples. However, the pair-wise links of $l_1$-graph are not capable of capturing the high order relationships between the center datum and its prominent data in sparse reconstruction. Meanwhile, from the perspective of variable selection, the $l_1$ norm sparse constraint, regarded as a LASSO model, tends to select only one datum from a group of data that are highly correlated and ignore the others. To simultaneously cope with these drawbacks, we propose a new elastic net hypergraph learning model, which consists of two steps. In the first step, the Robust Matrix Elastic Net model is constructed to find the canonically related samples in a somewhat greedy way, achieving the grouping effect by adding the $l_2$ penalty to the $l_1$ constraint. In the second step, hypergraph is used to represent the high order relationships between each datum and its prominent samples by regarding them as a hyperedge. Subsequently, hypergraph Laplacian matrix is constructed for further analysis. New hypergraph learning algorithms, including unsupervised clustering and multi-class semi-supervised classification, are then derived. Extensive experiments on face and handwriting databases demonstrate the effectiveness of the proposed method.

cs.CV↗

arXiv2010

Interaction of a nonlinear spin wave and magnetic soliton in a uniaxial anisotropic ferromagnet

We study the interaction of a nonlinear spin-wave and magnetic soliton in a uniaxial anisotropic ferromagnet. By means of a reasonable assumption and a straightforward Darboux transformation one- and two-soliton solutions in a nonlinear spin-wave background are obtained analytically, and their properties are discussed in detail. In the background of a nonlinear spin wave the amplitude of the envelope soliton has the spatial and temporal period, and soliton can be trapped only in space. The amplitude and wave number of spin wave have the different contribution to the width, velocity, and the amplitude of soliton solutions, respectively. The envelope of solution hold the shape of soliton, and the amplitude of each envelope soliton keeps invariability before and after collision which shows the elastic collision of two envelope soliton in the background of a nonlinear spin wave.

cond-mat.other↗

arXiv2006

Twist angle effects on the dynamic response of in-plane-switching liquid crystal displays

Twist angle effect on the response time of in-plane-switching liquid crystal displays are analyzed. We propose a device configuration whose top and bottom boundary liquid crystal layers are symmetric to each other with respect to the electric field direction. The analytical results of this device configuration indicate that the response time is improved at least 4X faster than that of a conventional in-plane-switching twisted-nematic mode and normal in-plane-switching mode.

cond-mat.soft↗