arXiv subjects

Wenbo Li

Publications and source records attributed to Wenbo Li.

At least 181 records · Page 10Linked to original sources

arXiv2021

LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond

Single image super-resolution (SISR) deals with a fundamental problem of upsampling a low-resolution (LR) image to its high-resolution (HR) version. Last few years have witnessed impressive progress propelled by deep learning methods. However, one critical challenge faced by existing methods is to strike a sweet spot of deep model complexity and resulting SISR quality. This paper addresses this pain point by proposing a linearly-assembled pixel-adaptive regression network (LAPAR), which casts the direct LR to HR mapping learning into a linear coefficient regression task over a dictionary of multiple predefined filter bases. Such a parametric representation renders our model highly lightweight and easy to optimize while achieving state-of-the-art results on SISR benchmarks. Moreover, based on the same idea, LAPAR is extended to tackle other restoration tasks, e.g., image denoising and JPEG image deblocking, and again, yields strong performance. The code is available at https://github.com/dvlab-research/Simple-SR.

cs.CV↗

arXiv2021

Finite element algorithms for nonlocal minimal graphs

We discuss computational and qualitative aspects of the fractional Plateau and the prescribed fractional mean curvature problems on bounded domains subject to exterior data being a subgraph. We recast these problems in terms of energy minimization, and we discretize the latter with piecewise linear finite elements. For the computation of the discrete solutions, we propose and study a gradient flow and a Newton scheme, and we quantify the effect of Dirichlet data truncation. We also present a wide variety of numerical experiments that illustrate qualitative and quantitative features of fractional minimal graphs and the associated discrete problems.

math.NA↗

arXiv2021

Unsupervised data augmentation for object detection

Data augmentation has always been an effective way to overcome overfitting issue when the dataset is small. There are already lots of augmentation operations such as horizontal flip, random crop or even Mixup. However, unlike image classification task, we cannot simply perform these operations for object detection task because of the lack of labeled bounding boxes information for corresponding generated images. To address this challenge, we propose a framework making use of Generative Adversarial Networks(GAN) to perform unsupervised data augmentation. To be specific, based on the recently supreme performance of YOLOv4, we propose a two-step pipeline that enables us to generate an image where the object lies in a certain position. In this way, we can accomplish the goal that generating an image with bounding box label.

cs.CV↗

arXiv2021

Quasisymmetric embeddings of slit Sierpiński carpets

We study the problem of quasisymmetrically embedding spaces homeomorphic to the Sierpiński carpet into the plane. In the case of so called dyadic slit carpets, several characterizations are obtained. One characterization is in terms of a Transboundary Loewner Property (TLP) which is a transboundary analogue of the Loewner property of Heinonen and Koskela. We show that a dyadic slit carpet can be quasisymmetrically embedded into the plane if and only if it is TLP. Moreover, every dyadic slit carpet $X$ can be associated to a "pillowcase sphere" $\widehat{X}$ which is a metric space homeomorphic to the sphere $\mathbb{S}^2$. We show that $X$ quasisymmetrically embeds into the plane if and only if $\widehat{X}$ is quasisymmetric to $\mathbb{S}^2$ if and only if $\widehat{X}$ is Ahlfors $2$-regular.

math.MG↗

arXiv2021

Time fractional gradient flows: Theory and numerics

We develop the theory of fractional gradient flows: an evolution aimed at the minimization of a convex, l.s.c.~energy, with memory effects. This memory is characterized by the fact that the negative of the (sub)gradient of the energy equals the so-called Caputo derivative of the state. We introduce the notion of energy solutions, for which we provide existence, uniqueness and certain regularizing effects. We also consider Lipschitz perturbations of this energy. For these problems we provide an a posteriori error estimate and show its reliability. This estimate depends only on the problem data, and imposes no constraints between consecutive time-steps. On the basis of this estimate we provide an a priori error analysis that makes no assumptions on the smoothness of the solution.

math.AP↗

arXiv2020

MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network

We present Mask-guided Generative Adversarial Network (MagGAN) for high-resolution face attribute editing, in which semantic facial masks from a pre-trained face parser are used to guide the fine-grained image editing process. With the introduction of a mask-guided reconstruction loss, MagGAN learns to only edit the facial parts that are relevant to the desired attribute changes, while preserving the attribute-irrelevant regions (e.g., hat, scarf for modification `To Bald'). Further, a novel mask-guided conditioning strategy is introduced to incorporate the influence region of each attribute change into the generator. In addition, a multi-level patch-wise discriminator structure is proposed to scale our model for high-resolution ($1024 \times 1024$) face editing. Experiments on the CelebA benchmark show that the proposed method significantly outperforms prior state-of-the-art approaches in terms of both image quality and editing performance.

cs.CV↗

arXiv2020

MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution

Video super-resolution (VSR) aims to utilize multiple low-resolution frames to generate a high-resolution prediction for each frame. In this process, inter- and intra-frames are the key sources for exploiting temporal and spatial information. However, there are a couple of limitations for existing VSR methods. First, optical flow is often used to establish temporal correspondence. But flow estimation itself is error-prone and affects recovery results. Second, similar patterns existing in natural images are rarely exploited for the VSR task. Motivated by these findings, we propose a temporal multi-correspondence aggregation strategy to leverage similar patches across frames, and a cross-scale nonlocal-correspondence aggregation scheme to explore self-similarity of images across scales. Based on these two new modules, we build an effective multi-correspondence aggregation network (MuCAN) for VSR. Our method achieves state-of-the-art results on multiple benchmark datasets. Extensive experiments justify the effectiveness of our method.

cs.CV↗

arXiv2020

Reinforcement Learning-Enabled Decision-Making Strategies for a Vehicle-Cyber-Physical-System in Connected Environment

As a typical vehicle-cyber-physical-system (V-CPS), connected automated vehicles attracted more and more attention in recent years. This paper focuses on discussing the decision-making (DM) strategy for autonomous vehicles in a connected environment. First, the highway DM problem is formulated, wherein the vehicles can exchange information via wireless networking. Then, two classical reinforcement learning (RL) algorithms, Q-learning and Dyna, are leveraged to derive the DM strategies in a predefined driving scenario. Finally, the control performance of the derived DM policies in safety and efficiency is analyzed. Furthermore, the inherent differences of the RL algorithms are embodied and discussed in DM strategies.

eess.SP↗

arXiv2020

Novel Human-Object Interaction Detection via Adversarial Domain Generalization

We study in this paper the problem of novel human-object interaction (HOI) detection, aiming at improving the generalization ability of the model to unseen scenarios. The challenge mainly stems from the large compositional space of objects and predicates, which leads to the lack of sufficient training data for all the object-predicate combinations. As a result, most existing HOI methods heavily rely on object priors and can hardly generalize to unseen combinations. To tackle this problem, we propose a unified framework of adversarial domain generalization to learn object-invariant features for predicate prediction. To measure the performance improvement, we create a new split of the HICO-DET dataset, where the HOIs in the test set are all unseen triplet categories in the training set. Our experiments show that the proposed framework significantly increases the performance by up to 50% on the new split of HICO-DET dataset and up to 125% on the UnRel dataset for auxiliary evaluation in detecting novel HOIs.

cs.CV↗

arXiv2020

A Spontaneous Driver Emotion Facial Expression (DEFE) Dataset for Intelligent Vehicles

In this paper, we introduce a new dataset, the driver emotion facial expression (DEFE) dataset, for driver spontaneous emotions analysis. The dataset includes facial expression recordings from 60 participants during driving. After watching a selected video-audio clip to elicit a specific emotion, each participant completed the driving tasks in the same driving scenario and rated their emotional responses during the driving processes from the aspects of dimensional emotion and discrete emotion. We also conducted classification experiments to recognize the scales of arousal, valence, dominance, as well as the emotion category and intensity to establish baseline results for the proposed dataset. Besides, this paper compared and discussed the differences in facial expressions between driving and non-driving scenarios. The results show that there were significant differences in AUs (Action Units) presence of facial expressions between driving and non-driving scenarios, indicating that human emotional expressions in driving scenarios were different from other life scenarios. Therefore, publishing a human emotion dataset specifically for the driver is necessary for traffic safety improvement. The proposed dataset will be publicly available so that researchers worldwide can use it to develop and examine their driver emotion analysis methods. To the best of our knowledge, this is currently the only public driver facial expression dataset.

cs.CV↗

arXiv2020

Quantitative Stability and Error Estimates for Optimal Transport Plans

Optimal transport maps and plans between two absolutely continuous measures $μ$ and $ν$ can be approximated by solving semi-discrete or fully-discrete optimal transport problems. These two problems ensue from approximating $μ$ or both $μ$ and $ν$ by Dirac measures. Extending an idea from [Gigli, On Hölder continuity-in-time of the optimal transport map towards measures along a curve], we characterize how transport plans change under perturbation of both $μ$ and $ν$. We apply this insight to prove error estimates for semi-discrete and fully-discrete algorithms in terms of errors solely arising from approximating measures. We obtain weighted $L^2$ error estimates for both types of algorithms with a convergence rate $O(h^{1/2})$. This coincides with the rate in [Berman, Convergence rates for discretized Monge--Ampère equations and quantitative stability of Optimal Transport, Theorem 5.4] for semi-discrete methods, but the error notion is different.

math.NA↗

arXiv2020

Incubation Induced Light Concentration Beyond the Diffraction Limit for High-Resolution Glass Printing

In the past two decades, tremendous efforts have been exerted to understand and control the delivery of ultrashort laser pulses into various types of transparent materials ranging from glass and crystal to polymer and even bio-materials. This approach opens up the route toward determinative and highly localized modification within the transparent materials, enabling three-dimensional (3D) micromachining of the materials into sophisticated structures and devices with the extreme geometrical flexibility. Owing to the linear diffraction and nonlinear self-focusing effects, the focal volume typically exhibits an asymmetric profile stretching along the longitudinal direction. This effect becomes more severe when focusing deeply into the transparent substrates for printing objects of large heights. In this work a new laser-material interaction regime is identified with the exceptional incubation effect originating from self-regulated multiple-pulse interactions with accumulated material changes. Our finding reveals a focal-volume-invariant modification deeply inside the fused silica glass, in striking contrary to the traditional believes that the geometrical shape of the laser induced modification follows the intensity distribution of the inscription laser. A macro-scale geometrically complex glass sculpture is successfully manufactured with the incubation assisted ultrashort laser inscription at uniform micrometer resolutions in all three dimensions.

physics.optics↗

arXiv2020

Finite element discretizations of nonlocal minimal graphs: convergence

In this paper, we propose and analyze a finite element discretization for the computation of fractional minimal graphs of order~$s \in (0,1/2)$ on a bounded domain $Ω$. Such a Plateau problem of order $s$ can be reinterpreted as a Dirichlet problem for a nonlocal, nonlinear, degenerate operator of order $s + 1/2$. We prove that our numerical scheme converges in $W^{2r}_1(Ω)$ for all $r<s$, where $W^{2s}_1(Ω)$ is closely related to the natural energy space. Moreover, we introduce a geometric notion of error that, for any pair of $H^1$ functions, in the limit $s \to 1/2$ recovers a weighted $L^2$-discrepancy between the normal vectors to their graphs. We derive error bounds with respect to this novel geometric quantity as well. In spite of performing approximations with continuous, piecewise linear, Lagrangian finite elements, the so-called {\em stickiness} phenomenon becomes apparent in the numerical experiments we present.

math.NA↗

arXiv2020

Convolution Neural Network Architecture Learning for Remote Sensing Scene Classification

Remote sensing image scene classification is a fundamental but challenging task in understanding remote sensing images. Recently, deep learning-based methods, especially convolutional neural network-based (CNN-based) methods have shown enormous potential to understand remote sensing images. CNN-based methods meet with success by utilizing features learned from data rather than features designed manually. The feature-learning procedure of CNN largely depends on the architecture of CNN. However, most of the architectures of CNN used for remote sensing scene classification are still designed by hand which demands a considerable amount of architecture engineering skills and domain knowledge, and it may not play CNN's maximum potential on a special dataset. In this paper, we proposed an automatically architecture learning procedure for remote sensing scene classification. We designed a parameters space in which every set of parameters represents a certain architecture of CNN (i.e., some parameters represent the type of operators used in the architecture such as convolution, pooling, no connection or identity, and the others represent the way how these operators connect). To discover the optimal set of parameters for a given dataset, we introduced a learning strategy which can allow efficient search in the architecture space by means of gradient descent. An architecture generator finally maps the set of parameters into the CNN used in our experiments.

cs.CV↗

arXiv2019

Linear and Nonlinear Fractional Elliptic Problems

This paper surveys recent analytical and numerical research on linear problems for the integral fractional Laplacian, fractional obstacle problems, and fractional minimal graphs. The emphasis is on the interplay between regularity, including boundary behavior, and approximability by piecewise linear finite element methods. We discuss several error estimates on graded meshes, and computational challenges associated to implementing and solving efficiently the ensuing integral equations, along with numerical experiments.

math.NA↗

arXiv2019

A compact and efficient three-dimensional microfluidic mixer

Microfluidic mixing is a fundamental functionality in most lab on a chip (LOC) systems,whereas realization of efficient mixing is challenging in microfluidic channels due to the small Reynolds numbers. Here, we design and fabricate a compact three-dimensional (3D) micromixer to enable efficient mixing at various flow rates. The performance of the fabricated micromixer was examined using blue and red inks. The extreme flexibility in fabricating microfluidic structures of arbitrary 3D geometries using femtosecond laser micromachining allows us to tackle the major disadvantageous effects for optimizing the mixing efficiency.

physics.app-ph↗

arXiv2019

Rethinking on Multi-Stage Networks for Human Pose Estimation

Existing pose estimation approaches fall into two categories: single-stage and multi-stage methods. While multi-stage methods are seemingly more suited for the task, their performance in current practice is not as good as single-stage methods. This work studies this issue. We argue that the current multi-stage methods' unsatisfactory performance comes from the insufficiency in various design choices. We propose several improvements, including the single-stage module design, cross stage feature aggregation, and coarse-to-fine supervision. The resulting method establishes the new state-of-the-art on both MS COCO and MPII Human Pose dataset, justifying the effectiveness of a multi-stage architecture. The source code is publicly available for further research.

cs.CV↗

arXiv2019

Object-driven Text-to-Image Synthesis via Adversarial Training

In this paper, we propose Object-driven Attentive Generative Adversarial Newtorks (Obj-GANs) that allow object-centered text-to-image synthesis for complex scenes. Following the two-step (layout-image) generation process, a novel object-driven attentive image generator is proposed to synthesize salient objects by paying attention to the most relevant words in the text description and the pre-generated semantic layout. In addition, a new Fast R-CNN based object-wise discriminator is proposed to provide rich object-wise discrimination signals on whether the synthesized object matches the text description and the pre-generated layout. The proposed Obj-GAN significantly outperforms the previous state of the art in various metrics on the large-scale COCO benchmark, increasing the Inception score by 27% and decreasing the FID score by 11%. A thorough comparison between the traditional grid attention and the new object-driven attention is provided through analyzing their mechanisms and visualizing their attention layers, showing insights of how the proposed model generates complex scenes in high quality.

cs.CV↗