arXiv subjects

Kai Xu

Publications and source records attributed to Kai Xu.

At least 379 records · Page 21Linked to original sources

arXiv2019

Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes

For the task of mobility analysis of 3D shapes, we propose joint analysis for simultaneous motion part segmentation and motion attribute estimation, taking a single 3D model as input. The problem is significantly different from those tackled in the existing works which assume the availability of either a pre-existing shape segmentation or multiple 3D models in different motion states. To that end, we develop Shape2Motion which takes a single 3D point cloud as input, and jointly computes a mobility-oriented segmentation and the associated motion attributes. Shape2Motion is comprised of two deep neural networks designed for mobility proposal generation and mobility optimization, respectively. The key contribution of these networks is the novel motion-driven features and losses used in both motion part segmentation and motion attribute estimation. This is based on the observation that the movement of a functional part preserves the shape structure. We evaluate Shape2Motion with a newly proposed benchmark for mobility analysis of 3D shapes. Results demonstrate that our method achieves the state-of-the-art performance both in terms of motion part segmentation and motion attribute estimation.

cs.CV↗

arXiv2019

Experimental Realization of Nonadiabatic Shortcut to Non-Abelian Geometric Gates

When a quantum system is driven adiabatically through a parametric cycle in a degenerate Hilbert space, the state would acquire a non-Abelian geometric phase, which is stable and forms the foundation for holonomic quantum computation (HQC). However, in the adiabatic limit, the environmental decoherence becomes a significant source of errors. Recently, various non-adiabatic HQC schemes have been proposed, but all at the price of increased sensitivity to control errors. Alternatively, there exist theoretical proposals for speeding up HQC by the technique of "shortcut to adiabaticity" (STA), but no experimental demonstration has been reported so far, as these proprosals involve a complicated control of four energy levels simultaneously. Here we propose and experimentally demonstrate that HQC via shortcut to adiabaticity can be constructed with only three energy levels, using a superconducting qubit in a scalable architecture. With this scheme, all holonomic single-qubit operations can be realized non-adiabatically through a single cycle of state evolution. As a result, we are able to experimentally benchmark the stability of STA+HQC against NHQC in the same platform. The flexibility and simplicity of our scheme makes it also implementable on other systems, such as nitrogen-vacancy center, quantum dots, and nuclear magnetic resonance.

quant-ph↗

arXiv2018

Dynamical speedup of a two-level system induced by coupling in the hierarchical environment

We investigate the dynamics of a two-level system in the presence of an overall environment composed of two layers. The first layer is just one single-mode cavity which decays to memoryless reservoir while the second layer is the two coupled single-mode cavities which decay to memoryless or memory-keeping reservoirs. In the weak-coupling regime between the qubit and the first-layer environment, our attention is focused on the effects of the coupling in the hierarchical environment on the non-Markovian speedup dynamics behavior of the system. We show that, by controlling the coupling in the second-layer environment, the multiple dynamics crossovers from Markovian to non-Markovian and from no-speedup to speedup can be realized. This results hold independently on the nature of the second-layer environment. Differently, we find that how the coupling between the two layers affects the non-Markovian speedup dynamics behavior depends on the nature of the second-layer environment.

quant-ph↗

arXiv2018

LAPRAN: A Scalable Laplacian Pyramid Reconstructive Adversarial Network for Flexible Compressive Sensing Reconstruction

This paper addresses the single-image compressive sensing (CS) and reconstruction problem. We propose a scalable Laplacian pyramid reconstructive adversarial network (LAPRAN) that enables high-fidelity, flexible and fast CS images reconstruction. LAPRAN progressively reconstructs an image following the concept of Laplacian pyramid through multiple stages of reconstructive adversarial networks (RANs). At each pyramid level, CS measurements are fused with a contextual latent vector to generate a high-frequency image residual. Consequently, LAPRAN can produce hierarchies of reconstructed images and each with an incremental resolution and improved quality. The scalable pyramid structure of LAPRAN enables high-fidelity CS reconstruction with a flexible resolution that is adaptive to a wide range of compression ratios (CRs), which is infeasible with existing methods. Experimental results on multiple public datasets show that LAPRAN offers an average 7.47dB and 5.98dB PSNR, and an average 57.93% and 33.20% SSIM improvement compared to model-based and data-driven baselines, respectively.

cs.CV↗

arXiv2018

SCORES: Shape Composition with Recursive Substructure Priors

We introduce SCORES, a recursive neural network for shape composition. Our network takes as input sets of parts from two or more source 3D shapes and a rough initial placement of the parts. It outputs an optimized part structure for the composed shape, leading to high-quality geometry construction. A unique feature of our composition network is that it is not merely learning how to connect parts. Our goal is to produce a coherent and plausible 3D shape, despite large incompatibilities among the input parts. The network may significantly alter the geometry and structure of the input parts and synthesize a novel shape structure based on the inputs, while adding or removing parts to minimize a structure plausibility loss. We design SCORES as a recursive autoencoder network. During encoding, the input parts are recursively grouped to generate a root code. During synthesis, the root code is decoded, recursively, to produce a new, coherent part assembly. Assembled shape structures may be novel, with little global resemblance to training exemplars, yet have plausible substructures. SCORES therefore learns a hierarchical substructure shape prior based on per-node losses. It is trained on structured shapes from ShapeNet, and is applied iteratively to reduce the plausibility loss.We showresults of shape composition from multiple sources over different categories of man-made shapes and compare with state-of-the-art alternatives, demonstrating that our network can significantly expand the range of composable shapes for assembly-based modeling.

cs.GR↗

arXiv2018

Learning to Group and Label Fine-Grained Shape Components

A majority of stock 3D models in modern shape repositories are assembled with many fine-grained components. The main cause of such data form is the component-wise modeling process widely practiced by human modelers. These modeling components thus inherently reflect some function-based shape decomposition the artist had in mind during modeling. On the other hand, modeling components represent an over-segmentation since a functional part is usually modeled as a multi-component assembly. Based on these observations, we advocate that labeled segmentation of stock 3D models should not overlook the modeling components and propose a learning solution to grouping and labeling of the fine-grained components. However, directly characterizing the shape of individual components for the purpose of labeling is unreliable, since they can be arbitrarily tiny and semantically meaningless. We propose to generate part hypotheses from the components based on a hierarchical grouping strategy, and perform labeling on those part groups instead of directly on the components. Part hypotheses are mid-level elements which are more probable to carry semantic information. A multiscale 3D convolutional neural network is trained to extract context-aware features for the hypotheses. To accomplish a labeled segmentation of the whole shape, we formulate higher-order conditional random fields (CRFs) to infer an optimal label assignment for all components. Extensive experiments demonstrate that our method achieves significantly robust labeling results on raw 3D models from public shape repositories. Our work also contributes the first benchmark for component-wise labeling.

cs.GR↗

arXiv2018

Learning Discriminative 3D Shape Representations by View Discerning Networks

In view-based 3D shape recognition, extracting discriminative visual representation of 3D shapes from projected images is considered the core problem. Projections with low discriminative ability can adversely influence the final 3D shape representation. Especially under the real situations with background clutter and object occlusion, the adverse effect is even more severe. To resolve this problem, we propose a novel deep neural network, View Discerning Network, which learns to judge the quality of views and adjust their contributions to the representation of shapes. In this network, a Score Generation Unit is devised to evaluate the quality of each projected image with score vectors. These score vectors are used to weight the image features and the weighted features perform much better than original features in 3D shape recognition task. In particular, we introduce two structures of Score Generation Unit, Channel-wise Score Unit and Part-wise Score Unit, to assess the quality of feature maps from different perspectives. Our network aggregates features and scores in an end-to-end framework, so that final shape descriptors are directly obtained from its output. Our experiments on ModelNet and ShapeNet Core55 show that View Discerning Network outperforms the state-of-the-arts in terms of the retrieval task, with excellent robustness against background clutter and object occlusion.

cs.CV↗

arXiv2018

Triangle Lasso for Simultaneous Clustering and Optimization in Graph Datasets

Recently, network lasso has drawn many attentions due to its remarkable performance on simultaneous clustering and optimization. However, it usually suffers from the imperfect data (noise, missing values etc), and yields sub-optimal solutions. The reason is that it finds the similar instances according to their features directly, which is usually impacted by the imperfect data, and thus returns sub-optimal results. In this paper, we propose triangle lasso to avoid its disadvantage. Triangle lasso finds the similar instances according to their neighbours. If two instances have many common neighbours, they tend to become similar. Although some instances are profiled by the imperfect data, it is still able to find the similar counterparts. Furthermore, we develop an efficient algorithm based on Alternating Direction Method of Multipliers (ADMM) to obtain a moderately accurate solution. In addition, we present a dual method to obtain the accurate solution with the low additional time consumption. We demonstrate through extensive numerical experiments that triangle lasso is robust to the imperfect data. It usually yields a better performance than the state-of-the-art method when performing data analysis tasks in practical scenarios.

cs.LG↗

arXiv2018

VERAM: View-Enhanced Recurrent Attention Model for 3D Shape Classification

Multi-view deep neural network is perhaps the most successful approach in 3D shape classification. However, the fusion of multi-view features based on max or average pooling lacks a view selection mechanism, limiting its application in, e.g., multi-view active object recognition by a robot. This paper presents VERAM, a recurrent attention model capable of actively selecting a sequence of views for highly accurate 3D shape classification. VERAM addresses an important issue commonly found in existing attention-based models, i.e., the unbalanced training of the subnetworks corresponding to next view estimation and shape classification. The classification subnetwork is easily overfitted while the view estimation one is usually poorly trained, leading to a suboptimal classification performance. This is surmounted by three essential view-enhancement strategies: 1) enhancing the information flow of gradient backpropagation for the view estimation subnetwork, 2) devising a highly informative reward function for the reinforcement training of view estimation and 3) formulating a novel loss function that explicitly circumvents view duplication. Taking grayscale image as input and AlexNet as CNN architecture, VERAM with 9 views achieves instance-level and class-level accuracy of 95:5% and 95:3% on ModelNet10, 93:7% and 92:1% on ModelNet40, both are the state-of-the-art performance under the same number of views.

cs.CV↗

arXiv2018

Caging Loops in Shape Embedding Space: Theory and Computation

We propose to synthesize feasible caging grasps for a target object through computing Caging Loops, a closed curve defined in the shape embedding space of the object. Different from the traditional methods, our approach decouples caging loops from the surface geometry of target objects through working in the embedding space. This enables us to synthesize caging loops encompassing multiple topological holes, instead of always tied with one specific handle which could be too small to be graspable by the robot gripper. Our method extracts caging loops through a topological analysis of the distance field defined for the target surface in the embedding space, based on a rigorous theoretical study on the relation between caging loops and the field topology. Due to the decoupling, our method can tolerate incomplete and noisy surface geometry of an unknown target object captured on-the-fly. We implemented our method with a robotic gripper and demonstrate through extensive experiments that our method can synthesize reliable grasps for objects with complex surface geometry and topology and in various scales.

cs.RO↗

arXiv2018

PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Reconstruction

We introduce a novel RGB-D patch descriptor designed for detecting coplanar surfaces in SLAM reconstruction. The core of our method is a deep convolutional neural net that takes in RGB, depth, and normal information of a planar patch in an image and outputs a descriptor that can be used to find coplanar patches from other images.We train the network on 10 million triplets of coplanar and non-coplanar patches, and evaluate on a new coplanarity benchmark created from commodity RGB-D scans. Experiments show that our learned descriptor outperforms alternatives extended for this new task by a significant margin. In addition, we demonstrate the benefits of coplanarity matching in a robust RGBD reconstruction formulation.We find that coplanarity constraints detected with our method are sufficient to get reconstruction results comparable to state-of-the-art frameworks on most scenes, but outperform other methods on standard benchmarks when combined with a simple keypoint method.

cs.CV↗

arXiv2018

Object-Aware Guidance for Autonomous Scene Reconstruction

To carry out autonomous 3D scanning and online reconstruction of unknown indoor scenes, one has to find a balance between global exploration of the entire scene and local scanning of the objects within it. In this work, we propose a novel approach, which provides object-aware guidance for autoscanning, for exploring, reconstructing, and understanding an unknown scene within one navigation pass. Our approach interleaves between object analysis to identify the next best object (NBO) for global exploration, and object-aware information gain analysis to plan the next best view (NBV) for local scanning. First, an objectness-based segmentation method is introduced to extract semantic objects from the current scene surface via a multi-class graph cuts minimization. Then, an object of interest (OOI) is identified as the NBO which the robot aims to visit and scan. The robot then conducts fine scanning on the OOI with views determined by the NBV strategy. When the OOI is recognized as a full object, it can be replaced by its most similar 3D model in a shape database. The algorithm iterates until all of the objects are recognized and reconstructed in the scene. Various experiments and comparisons have shown the feasibility of our proposed approach.

cs.GR↗

arXiv2018

Im2Struct: Recovering 3D Shape Structure from a Single RGB Image

We propose to recover 3D shape structures from single RGB images, where structure refers to shape parts represented by cuboids and part relations encompassing connectivity and symmetry. Given a single 2D image with an object depicted, our goal is automatically recover a cuboid structure of the object parts as well as their mutual relations. We develop a convolutional-recursive auto-encoder comprised of structure parsing of a 2D image followed by structure recovering of a cuboid hierarchy. The encoder is achieved by a multi-scale convolutional network trained with the task of shape contour estimation, thereby learning to discern object structures in various forms and scales. The decoder fuses the features of the structure parsing network and the original image, and recursively decodes a hierarchy of cuboids. Since the decoder network is learned to recover part relations including connectivity and symmetry explicitly, the plausibility and generality of part structure recovery can be ensured. The two networks are jointly trained using the training data of contour-mask and cuboid structure pairs. Such pairs are generated by rendering stock 3D CAD models coming with part segmentation. Our method achieves unprecedentedly faithful and detailed recovery of diverse 3D part structures from single-view 2D images. We demonstrate two applications of our method including structure-guided completion of 3D volumes reconstructed from single-view images and structure-aware interactive editing of 2D images.

cs.CV↗

arXiv2018

LCANet: End-to-End Lipreading with Cascaded Attention-CTC

Machine lipreading is a special type of automatic speech recognition (ASR) which transcribes human speech by visually interpreting the movement of related face regions including lips, face, and tongue. Recently, deep neural network based lipreading methods show great potential and have exceeded the accuracy of experienced human lipreaders in some benchmark datasets. However, lipreading is still far from being solved, and existing methods tend to have high error rates on the wild data. In this paper, we propose LCANet, an end-to-end deep neural network based lipreading system. LCANet encodes input video frames using a stacked 3D convolutional neural network (CNN), highway network and bidirectional GRU network. The encoder effectively captures both short-term and long-term spatio-temporal information. More importantly, LCANet incorporates a cascaded attention-CTC decoder to generate output texts. By cascading CTC with attention, it partially eliminates the defect of the conditional independence assumption of CTC within the hidden neural layers, and this yields notably performance improvement as well as faster convergence. The experimental results show the proposed system achieves a 1.3% CER and 3.0% WER on the GRID corpus database, leading to a 12.3% improvement compared to the state-of-the-art methods.

cs.CV↗

arXiv2018

Interpreting Deep Classifier by Visual Distillation of Dark Knowledge

Interpreting black box classifiers, such as deep networks, allows an analyst to validate a classifier before it is deployed in a high-stakes setting. A natural idea is to visualize the deep network's representations, so as to "see what the network sees". In this paper, we demonstrate that standard dimension reduction methods in this setting can yield uninformative or even misleading visualizations. Instead, we present DarkSight, which visually summarizes the predictions of a classifier in a way inspired by notion of dark knowledge. DarkSight embeds the data points into a low-dimensional space such that it is easy to compress the deep classifier into a simpler one, essentially combining model compression and dimension reduction. We compare DarkSight against t-SNE both qualitatively and quantitatively, demonstrating that DarkSight visualizations are more informative. Our method additionally yields a new confidence measure based on dark knowledge by quantifying how unusual a given vector of predictions is.

cs.LG↗

arXiv2018

Hierarchical environment-assisted dynamical speedup control

We investigate the qubit in the hierarchical environment where the first level is just one lossy cavity while the second level is the N-coupled lossy cavities. In the weak coupling regime between the qubit and the first level environment, the dynamics crossovers from the original Markovian to the new non-Markovian and from no-speedup to speedup can be realized by controlling the hierarchical environment, i.e., manipulating the number of cavities or the coupling strength between two nearest-neighbor cavities in the second level environment. And we find that the coupling strength between two nearest-neighbor cavities and the number of cavities in the second level environment have the opposite effect on the non-Markovian dynamics and speedup evolution of the qubit. In addition, in the case of strong coupling between the qubit and the first level environment, we can be surprised to find that, compared with the original non-Markovian dynamics, the added second level environment cannot play a beneficial role on the speedup of the dynamics of the system.

quant-ph↗

arXiv2018

CSVideoNet: A Real-time End-to-end Learning Framework for High-frame-rate Video Compressive Sensing

This paper addresses the real-time encoding-decoding problem for high-frame-rate video compressive sensing (CS). Unlike prior works that perform reconstruction using iterative optimization-based approaches, we propose a non-iterative model, named "CSVideoNet". CSVideoNet directly learns the inverse mapping of CS and reconstructs the original input in a single forward propagation. To overcome the limitations of existing CS cameras, we propose a multi-rate CNN and a synthesizing RNN to improve the trade-off between compression ratio (CR) and spatial-temporal resolution of the reconstructed videos. The experiment results demonstrate that CSVideoNet significantly outperforms the state-of-the-art approaches. With no pre/post-processing, we achieve 25dB PSNR recovery quality at 100x CR, with a frame rate of 125 fps on a Titan X GPU. Due to the feedforward and high-data-concurrency natures of CSVideoNet, it can take advantage of GPU acceleration to achieve three orders of magnitude speed-up over conventional iterative-based approaches. We share the source code at https://github.com/PSCLab-ASU/CSVideoNet.

cs.CV↗

arXiv2017

Test of the multiquark structure of $a_1(1420)$ in strong two-body decays

We present an analysis of strong two-body decays of the $a_1(1420)$ with $J^{PC} = 1^{++}$ recently reported by the COMPASS Collaboration at CERN. Following the interpretation of the COMPASS Collaboration that the $a_1$ is an unusual state with a four-quark $q\bar q s \bar s$ structure we consider two possible configurations for this state --- hadronic molecular and color diquark-antidiquark structures. We find that the dominant decay mode of the $a_1$ is the decay into $K$ and $K^*$. In particular, we calculate that the four decay modes $a_1 \to VP$ with $VP = K^{*\pm}K^\mp$, $K^{*0}\bar K^0$, $\bar K^{*0}K^0$ together give a dominant contribution to the measured total width of about 150 MeV. The observational mode $a_1 \to f_0(980) + π^0$ is significantly suppressed by one order of magnitude.

hep-ph↗