arXiv subjects

Dong Wang

Publications and source records attributed to Dong Wang.

At least 505 records · Page 28Linked to original sources

arXiv2022

Probabilistic methods for approximate archetypal analysis

Archetypal analysis is an unsupervised learning method for exploratory data analysis. One major challenge that limits the applicability of archetypal analysis in practice is the inherent computational complexity of the existing algorithms. In this paper, we provide a novel approximation approach to partially address this issue. Utilizing probabilistic ideas from high-dimensional geometry, we introduce two preprocessing techniques to reduce the dimension and representation cardinality of the data, respectively. We prove that provided the data is approximately embedded in a low-dimensional linear subspace and the convex hull of the corresponding representations is well approximated by a polytope with a few vertices, our method can effectively reduce the scaling of archetypal analysis. Moreover, the solution of the reduced problem is near-optimal in terms of prediction errors. Our approach can be combined with other acceleration techniques to further mitigate the intrinsic complexity of archetypal analysis. We demonstrate the usefulness of our results by applying our method to summarize several moderately large-scale datasets.

stat.CO↗

arXiv2022

D-DPCC: Deep Dynamic Point Cloud Compression via 3D Motion Prediction

The non-uniformly distributed nature of the 3D dynamic point cloud (DPC) brings significant challenges to its high-efficient inter-frame compression. This paper proposes a novel 3D sparse convolution-based Deep Dynamic Point Cloud Compression (D-DPCC) network to compensate and compress the DPC geometry with 3D motion estimation and motion compensation in the feature space. In the proposed D-DPCC network, we design a {\it Multi-scale Motion Fusion} (MMF) module to accurately estimate the 3D optical flow between the feature representations of adjacent point cloud frames. Specifically, we utilize a 3D sparse convolution-based encoder to obtain the latent representation for motion estimation in the feature space and introduce the proposed MMF module for fused 3D motion embedding. Besides, for motion compensation, we propose a 3D {\it Adaptively Weighted Interpolation} (3DAWI) algorithm with a penalty coefficient to adaptively decrease the impact of distant neighbors. We compress the motion embedding and the residual with a lossy autoencoder-based network. To our knowledge, this paper is the first work proposing an end-to-end deep dynamic point cloud compression framework. The experimental result shows that the proposed D-DPCC framework achieves an average 76\% BD-Rate (Bjontegaard Delta Rate) gains against state-of-the-art Video-based Point Cloud Compression (V-PCC) v13 in inter mode.

cs.CV↗

arXiv2022

Enhanced exemplar autoencoder with cycle consistency loss in any-to-one voice conversion

Recent research showed that an autoencoder trained with speech of a single speaker, called exemplar autoencoder (eAE), can be used for any-to-one voice conversion (VC). Compared to large-scale many-to-many models such as AutoVC, the eAE model is easy and fast in training, and may recover more details of the target speaker. To ensure VC quality, the latent code should represent and only represent content information. However, this is not easy to attain for eAE as it is unaware of any speaker variation in model training. To tackle the problem, we propose a simple yet effective approach based on a cycle consistency loss. Specifically, we train eAEs of multiple speakers with a shared encoder, and meanwhile encourage the speech reconstructed from any speaker-specific decoder to get a consistent latent code as the original speech when cycled back and encoded again. Experiments conducted on the AISHELL-3 corpus showed that this new approach improved the baseline eAE consistently. The source code and examples are available at the project page: http://project.cslt.org/.

cs.SD↗

arXiv2022

Reliable Visualization for Deep Speaker Recognition

In spite of the impressive success of convolutional neural networks (CNNs) in speaker recognition, our understanding to CNNs' internal functions is still limited. A major obstacle is that some popular visualization tools are difficult to apply, for example those producing saliency maps. The reason is that speaker information does not show clear spatial patterns in the temporal-frequency space, which makes it hard to interpret the visualization results, and hence hard to confirm the reliability of a visualization tool. In this paper, we conduct an extensive analysis on three popular visualization methods based on CAM: Grad-CAM, Score-CAM and Layer-CAM, to investigate their reliability for speaker recognition tasks. Experiments conducted on a state-of-the-art ResNet34SE model show that the Layer-CAM algorithm can produce reliable visualization, and thus can be used as a promising tool to explain CNN-based speaker models. The source code and examples are available in our project page: http://project.cslt.org/.

cs.SD↗

arXiv2022

Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline

With the popularity of multi-modal sensors, visible-thermal (RGB-T) object tracking is to achieve robust performance and wider application scenarios with the guidance of objects' temperature information. However, the lack of paired training samples is the main bottleneck for unlocking the power of RGB-T tracking. Since it is laborious to collect high-quality RGB-T sequences, recent benchmarks only provide test sequences. In this paper, we construct a large-scale benchmark with high diversity for visible-thermal UAV tracking (VTUAV), including 500 sequences with 1.7 million high-resolution (1920 $\times$ 1080 pixels) frame pairs. In addition, comprehensive applications (short-term tracking, long-term tracking and segmentation mask prediction) with diverse categories and scenes are considered for exhaustive evaluation. Moreover, we provide a coarse-to-fine attribute annotation, where frame-level attributes are provided to exploit the potential of challenge-specific trackers. In addition, we design a new RGB-T baseline, named Hierarchical Multi-modal Fusion Tracker (HMFT), which fuses RGB-T data in various levels. Numerous experiments on several datasets are conducted to reveal the effectiveness of HMFT and the complement of different fusion types. The project is available at here.

cs.CV↗

arXiv2022

Newcomer OSS-Candidates: Characterizing Contributions of Novice Developers to GitHub

The ability of an Open Source Software (OSS) project to attract, onboard, and retain any newcomer is vital to its livelihood. Although, evidence suggests an upsurge in novice developers joining social coding platforms (such as GitHub), the extent to which their activities result in a OSS contribution is unknown. Henceforth, we execute the protocols of a registered report to study activities of a "Newcomer OSS-Candidate", who is a novice developer that is new to that social coding platform, and has the intention to later onboard an OSS project. Using GitHub as a case platform, we analyze 171 identified Newcomer OSS-Candidates to characterize their contribution activities. Results show that Newcomer OSS-Candidates are likely to target software based repositories (i.e., 66%), and their first contributions are mainly associated with development (commits) and maintenance (PRs). Newcomer OSS-Candidates are less likely to practice social coding, but eventually end up onboarding (i.e., 30% quantitative, 70% follow-up survey) an OSS project. Furthermore, they cite finding a way to start as the most challenging barrier to contribute. Our work reveals insights on how newcomers to social coding platforms are potential sources of OSS contributions.

cs.SE↗

arXiv2022

Deep Page-Level Interest Network in Reinforcement Learning for Ads Allocation

A mixed list of ads and organic items is usually displayed in feed and how to allocate the limited slots to maximize the overall revenue is a key problem. Meanwhile, modeling user preference with historical behavior is essential in recommendation and advertising (e.g., CTR prediction and ads allocation). Most previous works for user behavior modeling only model user's historical point-level positive feedback (i.e., click), which neglect the page-level information of feedback and other types of feedback. To this end, we propose Deep Page-level Interest Network (DPIN) to model the page-level user preference and exploit multiple types of feedback. Specifically, we introduce four different types of page-level feedback as input, and capture user preference for item arrangement under different receptive fields through the multi-channel interaction module. Through extensive offline and online experiments on Meituan food delivery platform, we demonstrate that DPIN can effectively model the page-level user preference and increase the revenue for the platform.

cs.LG↗

arXiv2022

An efficient unconditionally stable method for Dirichlet partitions in arbitrary domains

A Dirichlet $k$-partition of a domain is a collection of $k$ pairwise disjoint open subsets such that the sum of their first Laplace--Dirichlet eigenvalues is minimal. In this paper, we propose a new relaxation of the problem by introducing auxiliary indicator functions of domains and develop a simple and efficient diffusion generated method to compute Dirichlet $k$-partitions for arbitrary domains. The method only alternates three steps: 1. convolution, 2. thresholding, and 3. projection. The method is simple, easy to implement, insensitive to initial guesses and can be effectively applied to arbitrary domains without any special discretization. At each iteration, the computational complexity is linear in the discretization of the computational domain. Moreover, we theoretically prove the energy decaying property of the method. Experiments are performed to show the accuracy of approximation, efficiency and unconditional stability of the algorithm. We apply the proposed algorithms on both 2- and 3-dimensional flat tori, triangle, square, pentagon, hexagon, disk, three-fold star, five-fold star, cube, ball, and tetrahedron domains to compute Dirichlet $k$-partitions for different $k$ to show the effectiveness of the proposed method. Compared to previous work with reported computational time, the proposed method achieves hundreds of times acceleration.

math.NA↗

arXiv2022

Balanced Multimodal Learning via On-the-fly Gradient Modulation

Multimodal learning helps to comprehensively understand the world, by integrating different senses. Accordingly, multiple input modalities are expected to boost model performance, but we actually find that they are not fully exploited even when the multimodal model outperforms its uni-modal counterpart. Specifically, in this paper we point out that existing multimodal discriminative models, in which uniform objective is designed for all modalities, could remain under-optimized uni-modal representations, caused by another dominated modality in some scenarios, e.g., sound in blowing wind event, vision in drawing picture event, etc. To alleviate this optimization imbalance, we propose on-the-fly gradient modulation to adaptively control the optimization of each modality, via monitoring the discrepancy of their contribution towards the learning objective. Further, an extra Gaussian noise that changes dynamically is introduced to avoid possible generalization drop caused by gradient modulation. As a result, we achieve considerable improvement over common fusion methods on different multimodal tasks, and this simple strategy can also boost existing multimodal methods, which illustrates its efficacy and versatility. The source code is available at \url{https://github.com/GeWu-Lab/OGM-GE_CVPR2022}.

cs.CV↗

arXiv2022

Efficient Localness Transformer for Smart Sensor-Based Energy Disaggregation

Modern smart sensor-based energy management systems leverage non-intrusive load monitoring (NILM) to predict and optimize appliance load distribution in real-time. NILM, or energy disaggregation, refers to the decomposition of electricity usage conditioned on the aggregated power signals (i.e., smart sensor on the main channel). Based on real-time appliance power prediction using sensory technology, energy disaggregation has great potential to increase electricity efficiency and reduce energy expenditure. With the introduction of transformer models, NILM has achieved significant improvements in predicting device power readings. Nevertheless, transformers are less efficient due to O(l^2) complexity w.r.t. sequence length l. Moreover, transformers can fail to capture local signal patterns in sequence-to-point settings due to the lack of inductive bias in local context. In this work, we propose an efficient localness transformer for non-intrusive load monitoring (ELTransformer). Specifically, we leverage normalization functions and switch the order of matrix multiplication to approximate self-attention and reduce computational complexity. Additionally, we introduce localness modeling with sparse local attention heads and relative position encodings to enhance the model capacity in extracting short-term local patterns. To the best of our knowledge, ELTransformer is the first NILM model that addresses computational complexity and localness modeling in NILM. With extensive experiments and quantitative analyses, we demonstrate the efficiency and effectiveness of the the proposed ELTransformer with considerable improvements compared to state-of-the-art baselines.

cs.LG↗

arXiv2022

Fast operator splitting methods for obstacle problems

The obstacle problem is a class of free boundary problems which finds applications in many disciplines such as porous media, financial mathematics and optimal control. In this paper, we propose two operator-splitting methods to solve the linear and nonlinear obstacle problems. The proposed methods have three ingredients: (i) Utilize an indicator function to formularize the constrained problem as an unconstrained problem, and associate it to an initial value problem. The obstacle problem is then converted to solving for the steady state solution of an initial value problem. (ii) An operator-splitting strategy to time discretize the initial value problem. After splitting, a heat equation with obstacles is solved and other subproblems either have explicit solutions or can be solved efficiently. (iii) A new constrained alternating direction explicit method, a fully explicit method, to solve heat equations with obstacles. The proposed methods are easy to implement, do not require to solve any linear systems and are more efficient than existing numerical methods while keeping similar accuracy. Extensions of the proposed methods to related free boundary problems are also discussed.

math.NA↗

arXiv2022

Neural Topic Modeling with Deep Mutual Information Estimation

The emerging neural topic models make topic modeling more easily adaptable and extendable in unsupervised text mining. However, the existing neural topic models is difficult to retain representative information of the documents within the learnt topic representation. In this paper, we propose a neural topic model which incorporates deep mutual information estimation, i.e., Neural Topic Modeling with Deep Mutual Information Estimation(NTM-DMIE). NTM-DMIE is a neural network method for topic learning which maximizes the mutual information between the input documents and their latent topic representation. To learn robust topic representation, we incorporate the discriminator to discriminate negative examples and positive examples via adversarial learning. Moreover, we use both global and local mutual information to preserve the rich information of the input documents in the topic representation. We evaluate NTM-DMIE on several metrics, including accuracy of text clustering, with topic representation, topic uniqueness and topic coherence. Compared to the existing methods, the experimental results show that NTM-DMIE can outperform in all the metrics on the four datasets.

cs.CL↗

arXiv2022

Rényi State Entropy for Exploration Acceleration in Reinforcement Learning

One of the most critical challenges in deep reinforcement learning is to maintain the long-term exploration capability of the agent. To tackle this problem, it has been recently proposed to provide intrinsic rewards for the agent to encourage exploration. However, most existing intrinsic reward-based methods proposed in the literature fail to provide sustainable exploration incentives, a problem known as vanishing rewards. In addition, these conventional methods incur complex models and additional memory in their learning procedures, resulting in high computational complexity and low robustness. In this work, a novel intrinsic reward module based on the Rényi entropy is proposed to provide high-quality intrinsic rewards. It is shown that the proposed method actually generalizes the existing state entropy maximization methods. In particular, a $k$-nearest neighbor estimator is introduced for entropy estimation while a $k$-value search method is designed to guarantee the estimation accuracy. Extensive simulation results demonstrate that the proposed Rényi entropy-based method can achieve higher performance as compared to existing schemes.

cs.LG↗

arXiv2022

C-P Map: A Novel Evaluation Toolkit for Speaker Verification

Evaluation trials are used to probe performance of automatic speaker verification (ASV) systems. In spite of the clear importance and impact, evaluation trials have not been seriously treated in research and engineering practice. This paper firstly presents a theoretical analysis on evaluation trials and highlights potential bias with the most popular cross-pairing approach used in trials design. To interpret and settle this problem, we define the concept of trial config and C-P map derived from it. The C-P map measures the performance of an ASV system on various trial configs in a 2-dimensional map. On the map, each location represents a particular trial config and its corresponding color represents the system performance. Experiments conducted on representative ASV systems show that the proposed C-P map offers a powerful evaluation toolkit for ASV performance analysis and comparison. The source code for C-P map has been release at https://gitlab.com/csltstu/sunine.

cs.SD↗

arXiv2022

Gradient Importance Learning for Incomplete Observations

Though recent works have developed methods that can generate estimates (or imputations) of the missing entries in a dataset to facilitate downstream analysis, most depend on assumptions that may not align with real-world applications and could suffer from poor performance in subsequent tasks such as classification. This is particularly true if the data have large missingness rates or a small sample size. More importantly, the imputation error could be propagated into the prediction step that follows, which may constrain the capabilities of the prediction model. In this work, we introduce the gradient importance learning (GIL) method to train multilayer perceptrons (MLPs) and long short-term memories (LSTMs) to directly perform inference from inputs containing missing values without imputation. Specifically, we employ reinforcement learning (RL) to adjust the gradients used to train these models via back-propagation. This allows the model to exploit the underlying information behind missingness patterns. We test the approach on real-world time-series (i.e., MIMIC-III), tabular data obtained from an eye clinic, and a standard dataset (i.e., MNIST), where our imputation-free predictions outperform the traditional two-step imputation-based predictions using state-of-the-art imputation methods.

cs.LG↗

arXiv2022

An Exploration of npm Package Co-Usage Examples from Stack Overflow: A Case Study

Third-party package usage has become a common practice in contemporary software development. Developers often face different challenges, including choosing the right libraries, installing errors, discrepancies, setting up the environment, and building failures during software development. The risks of maintaining a third-party package are well known, but it is unclear how information from Stack Overflow (SO) can be useful. This paper performed an empirical study to explore npm co-usage in SO. From over 30,000 SO posts, we extracted 2,100 SO posts related to npm and matched them to 217,934 npm library packages. We find that, popular and highly used libraries are not discussed as often in SO. However, we can see that the accepted answers may prove useful, as we believe that the usage examples and executable commands could be reused for tool support.

cs.SE↗

arXiv2022

Overcoming Van der Waals Forces in reconfigurable nanostructures

Reconfigurable metamaterials require constituent nanostructures to demonstrate switching of shapes with external stimuli. For generality, such nanostructures would touch and stick to other surfaces in one of its configurations. Yet, a longstanding challenge is in overcoming this stiction caused by Van der Waals forces, which impedes shape recovery. Here, we introduce a stiff yet self-recovering material system based on acrylic acid, and tested it in high-aspect ratio structures, where recovery is weak. This designer material has a storage modulus of ~5.2 GPa at room temperature and ~90 MPa in the rubbery state at 150 Celsius, an order of magnitude higher than previous reports. A high-resolution resin for two-photon lithography was developed based on this polymer system, enabling 3D printing of nanopillars with diameters of ~400 nm and aspect ratio as high as ~10. Experimentally, we observed self-recovery as collapsed and touching structures overcome stiction to stand back up. We developed a theoretical model to explain the recoverability of these sub-micron structures. Reconfigurable structural colour prints and holograms were demonstrated, indicating potential applications of the material system as a shape memory polymer suitable for sub-micron reconfigurable metamaterials.

physics.app-ph↗

arXiv2022

Topmetal-M: a novel pixel sensor for compact tracking applications

The Topmetal-M is a large area pixel sensor (18 mm * 23 mm) prototype fabricated in a new 130 nm high-resistivity CMOS process in 2019. It contains 400 rows * 512 columns square pixels with the pitch of 40 μm. In Topmetal-M, a novel charge collection method combing the Monolithic Active Pixel Sensor (MAPS) and the Topmetal sensor has been proposed for the first time. Both the ionized charge deposited by the particle in the sensor and along the track over the sensor can be collected. The in-pixel circuit mainly consists of a low-noise charge sensitive amplifier to establish the signal for the energy reconstruction, and a discriminator with a Time-to-Amplitude Converter (TAC) for the Time of Arrival (TOA) measurement. With this mechanism, the trajectory, particle hit position, energy and arrival time of the particle can be measured. The analog signal from each pixel is accessible through time-shared multiplexing over the entire pixel array. This paper will discuss the design and preliminary test results of the Topmetal-M sensor.

physics.ins-det↗