arXiv subjects

Xin Yu

Publications and source records attributed to Xin Yu.

At least 253 records · Page 14Linked to original sources

arXiv2020

6DoF Object Pose Estimation via Differentiable Proxy Voting Loss

Estimating a 6DOF object pose from a single image is very challenging due to occlusions or textureless appearances. Vector-field based keypoint voting has demonstrated its effectiveness and superiority on tackling those issues. However, direct regression of vector-fields neglects that the distances between pixels and keypoints also affect the deviations of hypotheses dramatically. In other words, small errors in direction vectors may generate severely deviated hypotheses when pixels are far away from a keypoint. In this paper, we aim to reduce such errors by incorporating the distances between pixels and keypoints into our objective. To this end, we develop a simple yet effective differentiable proxy voting loss (DPVL) which mimics the hypothesis selection in the voting procedure. By exploiting our voting loss, we are able to train our network in an end-to-end manner. Experiments on widely used datasets, i.e., LINEMOD and Occlusion LINEMOD, manifest that our DPVL improves pose estimation performance significantly and speeds up the training convergence.

cs.CV↗

arXiv2020

Copy and Paste GAN: Face Hallucination from Shaded Thumbnails

Existing face hallucination methods based on convolutional neural networks (CNN) have achieved impressive performance on low-resolution (LR) faces in a normal illumination condition. However, their performance degrades dramatically when LR faces are captured in low or non-uniform illumination conditions. This paper proposes a Copy and Paste Generative Adversarial Network (CPGAN) to recover authentic high-resolution (HR) face images while compensating for low and non-uniform illumination. To this end, we develop two key components in our CPGAN: internal and external Copy and Paste nets (CPnets). Specifically, our internal CPnet exploits facial information residing in the input image to enhance facial details; while our external CPnet leverages an external HR face for illumination compensation. A new illumination compensation loss is thus developed to capture illumination from the external guided face image effectively. Furthermore, our method offsets illumination and upsamples facial details alternately in a coarse-to-fine fashion, thus alleviating the correspondence ambiguity between LR inputs and external HR inputs. Extensive experiments demonstrate that our method manifests authentic HR face images in a uniform illumination condition and outperforms state-of-the-art methods qualitatively and quantitatively.

cs.CV↗

arXiv2020

Transferring Cross-domain Knowledge for Video Sign Language Recognition

Word-level sign language recognition (WSLR) is a fundamental task in sign language interpretation. It requires models to recognize isolated sign words from videos. However, annotating WSLR data needs expert knowledge, thus limiting WSLR dataset acquisition. On the contrary, there are abundant subtitled sign news videos on the internet. Since these videos have no word-level annotation and exhibit a large domain gap from isolated signs, they cannot be directly used for training WSLR models. We observe that despite the existence of a large domain gap, isolated and news signs share the same visual concepts, such as hand gestures and body movements. Motivated by this observation, we propose a novel method that learns domain-invariant visual concepts and fertilizes WSLR models by transferring knowledge of subtitled news sign to them. To this end, we extract news signs using a base WSLR model, and then design a classifier jointly trained on news and isolated signs to coarsely align these two domain features. In order to learn domain-invariant features within each class and suppress domain-specific features, our method further resorts to an external memory to store the class centroids of the aligned news signs. We then design a temporal attention based on the learnt descriptor to improve recognition performance. Experimental results on standard WSLR datasets show that our method outperforms previous state-of-the-art methods significantly. We also demonstrate the effectiveness of our method on automatically localizing signs from sign news, achieving 28.1 for AP@0.5.

cs.CV↗

arXiv2020

Weakly-Supervised Salient Object Detection via Scribble Annotations

Compared with laborious pixel-wise dense labeling, it is much easier to label data by scribbles, which only costs 1$\sim$2 seconds to label one image. However, using scribble labels to learn salient object detection has not been explored. In this paper, we propose a weakly-supervised salient object detection model to learn saliency from such annotations. In doing so, we first relabel an existing large-scale salient object detection dataset with scribbles, namely S-DUTS dataset. Since object structure and detail information is not identified by scribbles, directly training with scribble labels will lead to saliency maps of poor boundary localization. To mitigate this problem, we propose an auxiliary edge detection task to localize object edges explicitly, and a gated structure-aware loss to place constraints on the scope of structure to be recovered. Moreover, we design a scribble boosting scheme to iteratively consolidate our scribble annotations, which are then employed as supervision to learn high-quality saliency maps. As existing saliency evaluation metrics neglect to measure structure alignment of the predictions, the saliency map ranking metric may not comply with human perception. We present a new metric, termed saliency structure measure, to measure the structure alignment of the predicted saliency maps, which is more consistent with human perception. Extensive experiments on six benchmark datasets demonstrate that our method not only outperforms existing weakly-supervised/unsupervised methods, but also is on par with several fully-supervised state-of-the-art models. Our code and data is publicly available at https://github.com/JingZhang617/Scribble_Saliency.

cs.CV↗

arXiv2020

Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison

Vision-based sign language recognition aims at helping deaf people to communicate with others. However, most existing sign language datasets are limited to a small number of words. Due to the limited vocabulary size, models learned from those datasets cannot be applied in practice. In this paper, we introduce a new large-scale Word-Level American Sign Language (WLASL) video dataset, containing more than 2000 words performed by over 100 signers. This dataset will be made publicly available to the research community. To our knowledge, it is by far the largest public ASL dataset to facilitate word-level sign recognition research. Based on this new large-scale dataset, we are able to experiment with several deep learning methods for word-level sign recognition and evaluate their performances in large scale scenarios. Specifically we implement and compare two different models,i.e., (i) holistic visual appearance-based approach, and (ii) 2D human pose based approach. Both models are valuable baselines that will benefit the community for method benchmarking. Moreover, we also propose a novel pose-based temporal graph convolution networks (Pose-TGCN) that models spatial and temporal dependencies in human pose trajectories simultaneously, which has further boosted the performance of the pose-based method. Our results show that pose-based and appearance-based models achieve comparable performances up to 66% at top-10 accuracy on 2,000 words/glosses, demonstrating the validity and challenges of our dataset. Our dataset and baseline deep models are available at \url{https://dxli94.github.io/WLASL/}.

cs.CV↗

arXiv2020

Using observed bacteria concentration and modeled transit time under an analytical framework to estimate overall removal rate of fecal coliform in an estuary

Abundance of fecal coliform (FC) is widely used to indicate the potential presence of pathogens, the No.1 cause of water impairments in the U.S. Despite extensive monitoring efforts, assessing and modeling FC pollution still faces challenges, largely owing to the uncertainties in estimation of overall removal rate (K). This study proposes an alternative method to estimate in situ K by combining observational data, hydrodynamic simulation, and analytical solution. The method requires the observed spatial distribution of FC concentration along an estuarine channel and the numerically-simulated transit time, and converts the K estimation from a temporal problem into a spatial problem, potentially reducing survey duration, effort, and cost. Application of the method gave an estimation of K = 0.5 d-1 on average for the Nassawadox Creek in Chesapeake Bay. The numerical and analytical model results with the estimated K agreed well with the observation, demonstrating the credibility of the method.

physics.ao-ph↗

arXiv2019

SOSNet: Second Order Similarity Regularization for Local Descriptor Learning

Despite the fact that Second Order Similarity (SOS) has been used with significant success in tasks such as graph matching and clustering, it has not been exploited for learning local descriptors. In this work, we explore the potential of SOS in the field of descriptor learning by building upon the intuition that a positive pair of matching points should exhibit similar distances with respect to other points in the embedding space. Thus, we propose a novel regularization term, named Second Order Similarity Regularization (SOSR), that follows this principle. By incorporating SOSR into training, our learned descriptor achieves state-of-the-art performance on several challenging benchmarks containing distinct tasks ranging from local patch retrieval to structure from motion. Furthermore, by designing a von Mises-Fischer distribution based evaluation method, we link the utilization of the descriptor space to the matching performance, thus demonstrating the effectiveness of our proposed SOSR. Extensive experimental results, empirical evidence, and in-depth analysis are provided, indicating that SOSR can significantly boost the matching performance of the learned descriptor.

cs.CV↗

arXiv2019

Optimal Feature Transport for Cross-View Image Geo-Localization

This paper addresses the problem of cross-view image geo-localization, where the geographic location of a ground-level street-view query image is estimated by matching it against a large scale aerial map (e.g., a high-resolution satellite image). State-of-the-art deep-learning based methods tackle this problem as deep metric learning which aims to learn global feature representations of the scene seen by the two different views. Despite promising results are obtained by such deep metric learning methods, they, however, fail to exploit a crucial cue relevant for localization, namely, the spatial layout of local features. Moreover, little attention is paid to the obvious domain gap (between aerial view and ground view) in the context of cross-view localization. This paper proposes a novel Cross-View Feature Transport (CVFT) technique to explicitly establish cross-view domain transfer that facilitates feature alignment between ground and aerial images. Specifically, we implement the CVFT as network layers, which transports features from one domain to the other, leading to more meaningful feature similarity comparison. Our model is differentiable and can be learned end-to-end. Experiments on large-scale datasets have demonstrated that our method has remarkably boosted the state-of-the-art cross-view localization performance, e.g., on the CVUSA dataset, with significant improvements for top-1 recall from 40.79% to 61.43%, and for top-10 from 76.36% to 90.49%. We expect the key insight of the paper (i.e., explicitly handling domain difference via domain transport) will prove to be useful for other similar problems in computer vision as well.

cs.CV↗

arXiv2019

An Automatic Debugging Tool of Instruction-Driven Multicore Systems with Synchronization Points

Tracing back the instruction execution sequence to debug a multicore system can be very time-consuming because the relationships of the instructions can be very complex. For instructions that cannot be checked by the environment immediately after their executions, the errors they triggered can propagate through the instruction execution sequence. Our task is to find the error-triggered instructions automatically. This paper presents an automatic debugging tool that can leverage the synchronization points in the instruction execution sequences of the multicore system being verified to locate the instruction which results in simulation error automatically. To evaluate the performance of the debugging tool, we analyze the complexity of the algorithms and count the number of instructions executed to locate the aimed instruction.

cs.DC↗

arXiv2019

Learning Strict Identity Mappings in Deep Residual Networks

A family of super deep networks, referred to as residual networks or ResNet, achieved record-beating performance in various visual tasks such as image recognition, object detection, and semantic segmentation. The ability to train very deep networks naturally pushed the researchers to use enormous resources to achieve the best performance. Consequently, in many applications super deep residual networks were employed for just a marginal improvement in performance. In this paper, we propose epsilon-ResNet that allows us to automatically discard redundant layers, which produces responses that are smaller than a threshold epsilon, with a marginal or no loss in performance. The epsilon-ResNet architecture can be achieved using a few additional rectified linear units in the original ResNet. Our method does not use any additional variables nor numerous trials like other hyper-parameter optimization techniques. The layer selection is achieved using a single training process and the evaluation is performed on CIFAR-10, CIFAR-100, SVHN, and ImageNet datasets. In some instances, we achieve about 80% reduction in the number of parameters.

cs.CV↗

arXiv2019

Can generalised relative pose estimation solve sparse 3D registration?

Popular 3D scan registration projects, such as Stanford digital Michelangelo or KinectFusion, exploit the high-resolution sensor data for scan alignment. It is particularly challenging to solve the registration of sparse 3D scans in the absence of RGB components. In this case, we can not establish point correspondences since the same 3D point cannot be captured in two successive scans. In contrast to correspondence based methods, we take a different viewpoint and formulate the sparse 3D registration problem based on the constraints from the intersection of line segments from adjacent scans. We obtain the line segments by modeling every horizontal and vertical scan-line as piece-wise linear segments. We propose a new alternating projection algorithm for solving the scan alignment problem using line intersection constraints. We develop two new minimal solvers for scan alignment in the presence of plane correspondences: 1) 3 line intersections and 1 plane correspondence, and 2) 1 line intersection and 2 plane correspondences. We outperform other competing methods on Kinect and LiDAR datasets.

cs.CV↗

arXiv2019

Identity-preserving Face Recovery from Stylized Portraits

Given an artistic portrait, recovering the latent photorealistic face that preserves the subject's identity is challenging because the facial details are often distorted or fully lost in artistic portraits. We develop an Identity-preserving Face Recovery from Portraits (IFRP) method that utilizes a Style Removal network (SRN) and a Discriminative Network (DN). Our SRN, composed of an autoencoder with residual block-embedded skip connections, is designed to transfer feature maps of stylized images to the feature maps of the corresponding photorealistic faces. Owing to the Spatial Transformer Network (STN), SRN automatically compensates for misalignments of stylized portraits to output aligned realistic face images. To ensure the identity preservation, we promote the recovered and ground truth faces to share similar visual features via a distance measure which compares features of recovered and ground truth faces extracted from a pre-trained FaceNet network. DN has multiple convolutional and fully-connected layers, and its role is to enforce recovered faces to be similar to authentic faces. Thus, we can recover high-quality photorealistic faces from unaligned portraits while preserving the identity of the face in an image. By conducting extensive evaluations on a large-scale synthesized dataset and a hand-drawn sketch dataset, we demonstrate that our method achieves superior face recovery and attains state-of-the-art results. In addition, our method can recover photorealistic faces from unseen stylized portraits, artistic paintings, and hand-drawn sketches.

cs.CV↗

arXiv2019

Recovering Faces from Portraits with Auxiliary Facial Attributes

Recovering a photorealistic face from an artistic portrait is a challenging task since crucial facial details are often distorted or completely lost in artistic compositions. To handle this loss, we propose an Attribute-guided Face Recovery from Portraits (AFRP) that utilizes a Face Recovery Network (FRN) and a Discriminative Network (DN). FRN consists of an autoencoder with residual block-embedded skip-connections and incorporates facial attribute vectors into the feature maps of input portraits at the bottleneck of the autoencoder. DN has multiple convolutional and fully-connected layers, and its role is to enforce FRN to generate authentic face images with corresponding facial attributes dictated by the input attribute vectors. %Leveraging on the spatial transformer networks, FRN automatically compensates for misalignments of portraits. % and generates aligned face images. For the preservation of identities, we impose the recovered and ground-truth faces to share similar visual features. Specifically, DN determines whether the recovered image looks like a real face and checks if the facial attributes extracted from the recovered image are consistent with given attributes. %Our method can recover high-quality photorealistic faces from unaligned portraits while preserving the identity of the face images as well as it can reconstruct a photorealistic face image with a desired set of attributes. Our method can recover photorealistic identity-preserving faces with desired attributes from unseen stylized portraits, artistic paintings, and hand-drawn sketches. On large-scale synthesized and sketch datasets, we demonstrate that our face recovery method achieves state-of-the-art results.

cs.CV↗

arXiv2018

Periodic parabola solitons for the nonautonomous KP equation

Kadomtsev-Petviashvili (KP) equation, who can describe different models in fluids and plasmas, has drawn investigation for its solitonic solutions with various methods. In this paper, we focus on the periodic parabola solitons for the (2+1) dimensional nonautonomous KP equations where the necessary constraints of the parameters are figured out. With Painleve analysis and Hirota bilinear method, we find that the solution has six undetermined parameters as well as analyze the features of some typical cases of the solutions. Based on the constructed solutions, the conditions of their convergence are also discussed.

nlin.SI↗

arXiv2018

Bringing a Blurry Frame Alive at High Frame-Rate with an Event Camera

Event-based cameras can measure intensity changes (called `{\it events}') with microsecond accuracy under high-speed motion and challenging lighting conditions. With the active pixel sensor (APS), the event camera allows simultaneous output of the intensity frames. However, the output images are captured at a relatively low frame-rate and often suffer from motion blur. A blurry image can be regarded as the integral of a sequence of latent images, while the events indicate the changes between the latent images. Therefore, we are able to model the blur-generation process by associating event data to a latent image. In this paper, we propose a simple and effective approach, the \textbf{Event-based Double Integral (EDI)} model, to reconstruct a high frame-rate, sharp video from a single blurry frame and its event data. The video generation is based on solving a simple non-convex optimization problem in a single scalar variable. Experimental results on both synthetic and real images demonstrate the superiority of our EDI model and optimization method in comparison to the state-of-the-art.

cs.CV↗

arXiv2018

Generalized Lyapunov criteria on finite-time stability of stochastic nonlinear systems

This paper considers the problem of finite-time stability for stochastic nonlinear systems. A new Lyapunov theorem of stochastic finite-time stability is proposed, and an important corollary is obtained. Some comparisons with the existing results are given, and it shows that this new Lyapunov theorem not only is a generalization of classical stochastic finite-time theorem, but also reveals the important role of white-noise in finite-time stabilizing stochastic systems. In addition, multiple Lyapunov functions-based criteria on stochastic finite-time stability are presented, which further relax the constraint of the infinitesimal generator $\mathcal{L}V$. Some examples are constructed to show significant features of the proposed theorems. Finally, simulation results are presented to demonstrate the theoretical analysis.

math.PR↗

arXiv2018

Estimating the Distribution of Random Parameters in a Diffusion Equation Forward Model for a Transdermal Alcohol Biosensor

We estimate the distribution of random parameters in a distributed parameter model with unbounded input and output for the transdermal transport of ethanol in humans. The model takes the form of a diffusion equation with the input being the blood alcohol concentration and the output being the transdermal alcohol concentration. Our approach is based on the idea of reformulating the underlying dynamical system in such a way that the random parameters are now treated as additional space variables. When the distribution to be estimated is assumed to be defined in terms of a joint density, estimating the distribution is equivalent to estimating the diffusivity in a multi-dimensional diffusion equation and thus well-established finite dimensional approximation schemes, functional analytic based convergence arguments, optimization techniques, and computational methods may all be employed. We use our technique to estimate a bivariate normal distribution based on data for multiple drinking episodes from a single subject.

math.OC↗

arXiv2018

VLASE: Vehicle Localization by Aggregating Semantic Edges

In this paper, we propose VLASE, a framework to use semantic edge features from images to achieve on-road localization. Semantic edge features denote edge contours that separate pairs of distinct objects such as building-sky, road- sidewalk, and building-ground. While prior work has shown promising results by utilizing the boundary between prominent classes such as sky and building using skylines, we generalize this approach to consider semantic edge features that arise from 19 different classes. Our localization algorithm is simple, yet very powerful. We extract semantic edge features using a recently introduced CASENet architecture and utilize VLAD framework to perform image retrieval. Our experiments show that we achieve improvement over some of the state-of-the-art localization algorithms such as SIFT-VLAD and its deep variant NetVLAD. We use ablation study to study the importance of different semantic classes and show that our unified approach achieves better performance compared to individual prominent features such as skylines.

cs.CV↗