arXiv subjects

Weimin Wang

Publications and source records attributed to Weimin Wang.

At least 55 records · Page 3Linked to original sources

arXiv2022

Enhancing Local Geometry Learning for 3D Point Cloud via Decoupling Convolution

Modeling the local surface geometry is challenging in 3D point cloud understanding due to the lack of connectivity information. Most prior works model local geometry using various convolution operations. We observe that the convolution can be equivalently decomposed as a weighted combination of a local and a global component. With this observation, we explicitly decouple these two components so that the local one can be enhanced and facilitate the learning of local surface geometry. Specifically, we propose Laplacian Unit (LU), a simple yet effective architectural unit that can enhance the learning of local geometry. Extensive experiments demonstrate that networks equipped with LUs achieve competitive or superior performance on typical point cloud understanding tasks. Moreover, through establishing connections between the mean curvature flow, a further investigation of LU based on curvatures is made to interpret the adaptive smoothing and sharpening effect of LU. The code will be available.

cs.CV↗

arXiv2022

Enhancing Local Feature Learning for 3D Point Cloud Processing using Unary-Pairwise Attention

We present a simple but effective attention named the unary-pairwise attention (UPA) for modeling the relationship between 3D point clouds. Our idea is motivated by the analysis that the standard self-attention (SA) that operates globally tends to produce almost the same attention maps for different query positions, revealing difficulties for learning query-independent and query-dependent information jointly. Therefore, we reformulate the SA and propose query-independent (Unary) and query-dependent (Pairwise) components to facilitate the learning of both terms. In contrast to the SA, the UPA ensures query dependence via operating locally. Extensive experiments show that the UPA outperforms the SA consistently on various point cloud understanding tasks including shape classification, part segmentation, and scene segmentation. Moreover, simply equipping the popular PointNet++ method with the UPA even outperforms or is on par with the state-of-the-art attention-based approaches. In addition, the UPA systematically boosts the performance of both standard and modern networks when it is integrated into them as a compositional module.

cs.CV↗

arXiv2021

Convergence problem of the Kawahara equation on the real line

In this paper, we consider the convergence problem of the Kawahara equation \begin{eqnarray*} &&u_{t}+α\partial_{x}^{5}u+β\partial_{x}^{3}u+\partial_{x}(u^{2})=0 \end{eqnarray*} on the real line with rough data. Firstly, by using Strichartz estimates as well as high-low frequency idea, we establish two crucial bilinear estimates, which are just Lemmas 3.1-3.2 in this paper; we also present the proof of Lemma 3.3 which shows that $s>-\frac{1}{2}$ is necessary for Lemma 3.2. Secondly, by using frequency truncated technique and high-low frequency technique, we show the pointwise convergence of the Kawahara equation with rough data in $H^{s}(\R)(s\geq\frac{1}{4})$; more precisely, we prove \begin{eqnarray*} &&\lim\limits_{t\rightarrow0}u(x,t)=u(x,0), \qquad a.e. x\in\R, \end{eqnarray*} where $u(x,t)$ is the solution to the Kawahara equation with initial data $u(x,0).$ Lastly, we show \begin{eqnarray*} &&\lim\limits_{t\rightarrow0}\sup\limits_{x\in\SR}|u(x,t)-U(t)u_{0}|=0 \end{eqnarray*} with rough data in $H^{s}(\R)(s>-\frac{1}{2})$.

math.AP↗

arXiv2021

3rd Place Solution to Google Landmark Recognition Competition 2021

In this paper, we show our solution to the Google Landmark Recognition 2021 Competition. Firstly, embeddings of images are extracted via various architectures (i.e. CNN-, Transformer- and hybrid-based), which are optimized by ArcFace loss. Then we apply an efficient pipeline to re-rank predictions by adjusting the retrieval score with classification logits and non-landmark distractors. Finally, the ensembled model scores 0.489 on the private leaderboard, achieving the 3rd place in the 2021 edition of the Google Landmark Recognition Competition.

cs.CV↗

arXiv2021

Spatio-Temporal Perturbations for Video Attribution

The attribution method provides a direction for interpreting opaque neural networks in a visual way by identifying and visualizing the input regions/pixels that dominate the output of a network. Regarding the attribution method for visually explaining video understanding networks, it is challenging because of the unique spatiotemporal dependencies existing in video inputs and the special 3D convolutional or recurrent structures of video understanding networks. However, most existing attribution methods focus on explaining networks taking a single image as input and a few works specifically devised for video attribution come short of dealing with diversified structures of video understanding networks. In this paper, we investigate a generic perturbation-based attribution method that is compatible with diversified video understanding networks. Besides, we propose a novel regularization term to enhance the method by constraining the smoothness of its attribution results in both spatial and temporal dimensions. In order to assess the effectiveness of different video attribution methods without relying on manual judgement, we introduce reliable objective metrics which are checked by a newly proposed reliability measurement. We verified the effectiveness of our method by both subjective and objective evaluation and comparison with multiple significant attribution methods.

cs.CV↗

arXiv2021

Weighted boxes fusion: Ensembling boxes from different object detection models

In this work, we present a novel method for combining predictions of object detection models: weighted boxes fusion. Our algorithm utilizes confidence scores of all proposed bounding boxes to constructs the averaged boxes. We tested method on several datasets and evaluated it in the context of the Open Images and COCO Object Detection tracks, achieving top results in these challenges. The source code is publicly available at https://github.com/ZFTurbo/Weighted-Boxes-Fusion

cs.CV↗

arXiv2020

Towards Visually Explaining Video Understanding Networks with Perturbation

''Making black box models explainable'' is a vital problem that accompanies the development of deep learning networks. For networks taking visual information as input, one basic but challenging explanation method is to identify and visualize the input pixels/regions that dominate the network's prediction. However, most existing works focus on explaining networks taking a single image as input and do not consider the temporal relationship that exists in videos. Providing an easy-to-use visual explanation method that is applicable to diversified structures of video understanding networks still remains an open challenge. In this paper, we investigate a generic perturbation-based method for visually explaining video understanding networks. Besides, we propose a novel loss function to enhance the method by constraining the smoothness of its results in both spatial and temporal dimensions. The method enables the comparison of explanation results between different network structures to become possible and can also avoid generating the pathological adversarial explanations for video inputs. Experimental comparison results verified the effectiveness of our method.

cs.CV↗

arXiv2020

3D Object Detection Method Based on YOLO and K-Means for Image and Point Clouds

Lidar based 3D object detection and classification tasks are essential for autonomous driving(AD). A lidar sensor can provide the 3D point cloud data reconstruction of the surrounding environment. However, real time detection in 3D point clouds still needs a strong algorithmic. This paper proposes a 3D object detection method based on point cloud and image which consists of there parts.(1)Lidar-camera calibration and undistorted image transformation. (2)YOLO-based detection and PointCloud extraction, (3)K-means based point cloud segmentation and detection experiment test and evaluation in depth image. In our research, camera can capture the image to make the Real-time 2D object detection by using YOLO, we transfer the bounding box to node whose function is making 3d object detection on point cloud data from Lidar. By comparing whether 2D coordinate transferred from the 3D point is in the object bounding box or not can achieve High-speed 3D object recognition function in GPU. The accuracy and precision get imporved after k-means clustering in point cloud. The speed of our detection method is a advantage faster than PointNet.

cs.CV↗

arXiv2020

SOIC: Semantic Online Initialization and Calibration for LiDAR and Camera

This paper presents a novel semantic-based online extrinsic calibration approach, SOIC (so, I see), for Light Detection and Ranging (LiDAR) and camera sensors. Previous online calibration methods usually need prior knowledge of rough initial values for optimization. The proposed approach removes this limitation by converting the initialization problem to a Perspective-n-Point (PnP) problem with the introduction of semantic centroids (SCs). The closed-form solution of this PnP problem has been well researched and can be found with existing PnP methods. Since the semantic centroid of the point cloud usually does not accurately match with that of the corresponding image, the accuracy of parameters are not improved even after a nonlinear refinement process. Thus, a cost function based on the constraint of the correspondence between semantic elements from both point cloud and image data is formulated. Subsequently, optimal extrinsic parameters are estimated by minimizing the cost function. We evaluate the proposed method either with GT or predicted semantics on KITTI dataset. Experimental results and comparisons with the baseline method verify the feasibility of the initialization strategy and the accuracy of the calibration approach. In addition, we release the source code at https://github.com/--/SOIC.

cs.CV↗

arXiv2019

Acoustic scene analysis with multi-head attention networks

Acoustic Scene Classification (ASC) is a challenging task, as a single scene may involve multiple events that contain complex sound patterns. For example, a cooking scene may contain several sound sources including silverware clinking, chopping, frying, etc. What complicates ASC more is that classes of different activities could have overlapping sounds patterns (e.g. both cooking and dishwashing could have silverware clinking sound). In this paper, we propose a multi-head attention network to model the complex temporal input structures for ASC. The proposed network takes the audio's time-frequency representation as input, and it leverages standard VGG plus LSTM layers to extract high-level feature representation. Further more, it applies multiple attention heads to summarize various patterns of sound events into fixed dimensional representation, for the purpose of final scene classification. The whole network is trained in an end-to-end fashion with back-propagation. Experimental results confirm that our model discovers meaningful sound patterns through the attention mechanism, without using explicit supervision in the alignment. We evaluated our proposed model using DCASE 2018 Task 5 dataset, and achieved competitive performance on par with previous winner's results.

eess.AS↗

arXiv2019

Optical Control of transverse Motion of Ionization injected Electrons in Laser Plasma Wakefield

We demonstrate an all-optical method for controlling the transverse motion of ionization injected electron beam, by utilizing the transversely asymmetrical wakefield via adjusting the shape of the laser focal spot. When the laser spot shape is changed from the circular to the obliquely elliptic in experiment, the electron beam shape becomes from elliptic to three different shapes. The 3D-PIC simulation results agree well with experiment, and it shows the trajectories of the accelerated electrons change from undulation to helix. Such an all-optical method could be useful for convenient control of the transverse motion of an electron beam which results in synchrotron radiation with orbit angular momentum.

physics.plasm-ph↗

arXiv2019

Neural Style Transfer for Point Clouds

How can we edit or transform the geometric or color property of a point cloud? In this study, we propose a neural style transfer method for point clouds which allows us to transfer the style of geometry or color from one point cloud either independently or simultaneously to another. This transfer is achieved by manipulating the content representations and Gram-based style representations extracted from a pre-trained PointNet-based classification network for colored point clouds. As Gram-based style representation is invariant to the number or the order of points, the same method can be extended to transfer the style extracted from an image to the color expression of a point cloud by merely treating the image as a set of pixels. Experimental results demonstrate the capability of the proposed method for transferring style from either an image or a point cloud to another point cloud of a single object or even an indoor scene.

cs.CV↗

arXiv2018

Strong Resonances of Quasi 1D Structures at the Bi/InAs(100) Surface

Thin Bi films are interesting candidates for spintronic applications due to a large spin-orbit splitting that, combined with the loss of inversion symmetry at the surface, results in a band structure that is not spin-degenerate. In recent years, applications for topological insulators based on Bi and Bi alloys have as well attracted much attention. Here we present ARPES studies of Bi/InAs(100) interface. Bismuth deposition followed by annealing of the surface results in the formation of one full Bi monolayer decorated by Bi-nanolines. We found that the building up of the interface does affect the electronic structure of the substrate. As a consequence of weak interaction, bismuth states are placed in the gaps of the electronic structure of InAs(100). We observe a strong resonance of the Bi electronic states close to the Fermi level; its intensity depends on the photon energy and the photon polarization. These states show nearly no dispersion when measured perpendicular to the nanolines, confirming their one-dimensionality.

cond-mat.str-el↗

arXiv2018

THz pulses over 50 millijoules generated from relativistic picosecond laser-plasma interactions

Ultrahigh-power terahertz (THz) radiation sources are essential for many applications, such as nonlinear THz physics, THz-wave based compact accelerators, etc. However, until now none of THz sources reported, whether based upon large-scale accelerators or high power lasers, have produced THz pulses with energies above the millijoule (mJ) barrier. Here we report on the efficient generation of low-frequency (<3 THz) THz pulses with unprecedentedly high energies over 50 mJ. The THz radiation is produced by coherent transition radiation of a picosecond laser-accelerated ultra-bright bunch of relativistic electrons from a solid target. Such high energy THz pulses can not only trigger various nonlinear dynamics in matter, but also open up a new research field of relativistic THz optics.

physics.plasm-ph↗

arXiv2017

Dense Optical Flow based Change Detection Network Robust to Difference of Camera Viewpoints

This paper presents a novel method for detecting scene changes from a pair of images with a difference of camera viewpoints using a dense optical flow based change detection network. In the case that camera poses of input images are fixed or known, such as with surveillance and satellite cameras, the pixel correspondence between the images captured at different times can be known. Hence, it is possible to comparatively accurately detect scene changes between the images by modeling the appearance of the scene. On the other hand, in case of cameras mounted on a moving object, such as ground and aerial vehicles, we must consider the spatial correspondence between the images captured at different times. However, it can be difficult to accurately estimate the camera pose or 3D model of a scene, owing to the scene changes or lack of imagery. To solve this problem, we propose a change detection convolutional neural network utilizing dense optical flow between input images to improve the robustness to the difference between camera viewpoints. Our evaluation based on the panoramic change detection dataset shows that the proposed method outperforms state-of-the-art change detection algorithms.

cs.CV↗

arXiv2017

Filmy Cloud Removal on Satellite Imagery with Multispectral Conditional Generative Adversarial Nets

In this paper, we propose a method for cloud removal from visible light RGB satellite images by extending the conditional Generative Adversarial Networks (cGANs) from RGB images to multispectral images. Satellite images have been widely utilized for various purposes, such as natural environment monitoring (pollution, forest or rivers), transportation improvement and prompt emergency response to disasters. However, the obscurity caused by clouds makes it unstable to monitor the situation on the ground with the visible light camera. Images captured by a longer wavelength are introduced to reduce the effects of clouds. Synthetic Aperture Radar (SAR) is such an example that improves visibility even the clouds exist. On the other hand, the spatial resolution decreases as the wavelength increases. Furthermore, the images captured by long wavelengths differs considerably from those captured by visible light in terms of their appearance. Therefore, we propose a network that can remove clouds and generate visible light images from the multispectral images taken as inputs. This is achieved by extending the input channels of cGANs to be compatible with multispectral images. The networks are trained to output images that are close to the ground truth using the images synthesized with clouds over the ground truth as inputs. In the available dataset, the proportion of images of the forest or the sea is very high, which will introduce bias in the training dataset if uniformly sampled from the original dataset. Thus, we utilize the t-Distributed Stochastic Neighbor Embedding (t-SNE) to improve the problem of bias in the training dataset. Finally, we confirm the feasibility of the proposed network on the dataset of four bands images, which include three visible light bands and one near-infrared (NIR) band.

cs.CV↗

arXiv2017

Reflectance Intensity Assisted Automatic and Accurate Extrinsic Calibration of 3D LiDAR and Panoramic Camera Using a Printed Chessboard

This paper presents a novel method for fully automatic and convenient extrinsic calibration of a 3D LiDAR and a panoramic camera with a normally printed chessboard. The proposed method is based on the 3D corner estimation of the chessboard from the sparse point cloud generated by one frame scan of the LiDAR. To estimate the corners, we formulate a full-scale model of the chessboard and fit it to the segmented 3D points of the chessboard. The model is fitted by optimizing the cost function under constraints of correlation between the reflectance intensity of laser and the color of the chessboard's patterns. Powell's method is introduced for resolving the discontinuity problem in optimization. The corners of the fitted model are considered as the 3D corners of the chessboard. Once the corners of the chessboard in the 3D point cloud are estimated, the extrinsic calibration of the two sensors is converted to a 3D-2D matching problem. The corresponding 3D-2D points are used to calculate the absolute pose of the two sensors with Unified Perspective-n-Point (UPnP). Further, the calculated parameters are regarded as initial values and are refined using the Levenberg-Marquardt method. The performance of the proposed corner detection method from the 3D point cloud is evaluated using simulations. The results of experiments, conducted on a Velodyne HDL-32e LiDAR and a Ladybug3 camera under the proposed re-projection error metric, qualitatively and quantitatively demonstrate the accuracy and stability of the final extrinsic calibration parameters.

cs.CV↗

arXiv2015

Information Rate Decomposition for Feedback Systems with Output Disturbance

This technical note considers the problem of resource allocation in linear feedback control system with output disturbance. By decomposing the information rate in the feedback communication channel, the channel resource allocation is thoroughly analyzed. The results show that certain amount of resource is used to transmit the output disturbance and this resource allocation is independent from feedback controller design.

cs.IT↗