arXiv subjects

Jianwei Zhang

Publications and source records attributed to Jianwei Zhang.

At least 145 records · Page 8Linked to original sources

arXiv2021

Restoring degraded speech via a modified diffusion model

There are many deterministic mathematical operations (e.g. compression, clipping, downsampling) that degrade speech quality considerably. In this paper we introduce a neural network architecture, based on a modification of the DiffWave model, that aims to restore the original speech signal. DiffWave, a recently published diffusion-based vocoder, has shown state-of-the-art synthesized speech quality and relatively shorter waveform generation times, with only a small set of parameters. We replace the mel-spectrum upsampler in DiffWave with a deep CNN upsampler, which is trained to alter the degraded speech mel-spectrum to match that of the original speech. The model is trained using the original speech waveform, but conditioned on the degraded speech mel-spectrum. Post-training, only the degraded mel-spectrum is used as input and the model generates an estimate of the original speech. Our model results in improved speech quality (original DiffWave model as baseline) on several different experiments. These include improving the quality of speech degraded by LPC-10 compression, AMR-NB compression, and signal clipping. Compared to the original DiffWave architecture, our scheme achieves better performance on several objective perceptual metrics and in subjective comparisons. Improvements over baseline are further amplified in a out-of-corpus evaluation setting.

cs.SD↗

arXiv2021

Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation

In the classic setting of unsupervised domain adaptation (UDA), the labeled source data are available in the training phase. However, in many real-world scenarios, owing to some reasons such as privacy protection and information security, the source data is inaccessible, and only a model trained on the source domain is available. This paper proposes a novel deep clustering method for this challenging task. Aiming at the dynamical clustering at feature-level, we introduce extra constraints hidden in the geometric structure between data to assist the process. Concretely, we propose a geometry-based constraint, named semantic consistency on the nearest neighborhood (SCNNH), and use it to encourage robust clustering. To reach this goal, we construct the nearest neighborhood for every target data and take it as the fundamental clustering unit by building our objective on the geometry. Also, we develop a more SCNNH-compliant structure with an additional semantic credibility constraint, named semantic hyper-nearest neighborhood (SHNNH). After that, we extend our method to this new geometry. Extensive experiments on three challenging UDA datasets indicate that our method achieves state-of-the-art results. The proposed method has significant improvement on all datasets (as we adopt SHNNH, the average accuracy increases by over 3.0% on the large-scaled dataset). Code is available at https://github.com/tntek/N2DCX.

cs.CV↗

arXiv2021

Learning compliant grasping and manipulation by teleoperation with adaptive force control

In this work, we focus on improving the robot's dexterous capability by exploiting visual sensing and adaptive force control. TeachNet, a vision-based teleoperation learning framework, is exploited to map human hand postures to a multi-fingered robot hand. We augment TeachNet, which is originally based on an imprecise kinematic mapping and position-only servoing, with a biomimetic learning-based compliance control algorithm for dexterous manipulation tasks. This compliance controller takes the mapped robotic joint angles from TeachNet as the desired goal, computes the desired joint torques. It is derived from a computational model of the biomimetic control strategy in human motor learning, which allows adapting the control variables (impedance and feedforward force) online during the execution of the reference joint angle trajectories. The simultaneous adaptation of the impedance and feedforward profiles enables the robot to interact with the environment in a compliant manner. Our approach has been verified in multiple tasks in physics simulation, i.e., grasping, opening-a-door, turning-a-cap, and touching-a-mouse, and has shown more reliable performances than the existing position control and the fixed-gain-based force control approaches.

cs.RO↗

arXiv2021

TransSC: Transformer-based Shape Completion for Grasp Evaluation

Currently, robotic grasping methods based on sparse partial point clouds have attained a great grasping performance on various objects while they often generate wrong grasping candidates due to the lack of geometric information on the object. In this work, we propose a novel and robust shape completion model (TransSC). This model has a transformer-based encoder to explore more point-wise features and a manifold-based decoder to exploit more object details using a partial point cloud as input. Quantitative experiments verify the effectiveness of the proposed shape completion network and demonstrate it outperforms existing methods. Besides, TransSC is integrated into a grasp evaluation network to generate a set of grasp candidates. The simulation experiment shows that TransSC improves the grasping generation result compared to the existing shape completion baselines. Furthermore, our robotic experiment shows that with TransSC the robot is more successful in grasping objects that are randomly placed on a support surface.

cs.RO↗

arXiv2021

Contrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systems

Deep candidate generation (DCG) that narrows down the collection of relevant items from billions to hundreds via representation learning has become prevalent in industrial recommender systems. Standard approaches approximate maximum likelihood estimation (MLE) through sampling for better scalability and address the problem of DCG in a way similar to language modeling. However, live recommender systems face severe exposure bias and have a vocabulary several orders of magnitude larger than that of natural language, implying that MLE will preserve and even exacerbate the exposure bias in the long run in order to faithfully fit the observed samples. In this paper, we theoretically prove that a popular choice of contrastive loss is equivalent to reducing the exposure bias via inverse propensity weighting, which provides a new perspective for understanding the effectiveness of contrastive learning. Based on the theoretical discovery, we design CLRec, a contrastive learning method to improve DCG in terms of fairness, effectiveness and efficiency in recommender systems with extremely large candidate size. We further improve upon CLRec and propose Multi-CLRec, for accurate multi-intention aware bias reduction. Our methods have been successfully deployed in Taobao, where at least four-month online A/B tests and offline analyses demonstrate its substantial improvements, including a dramatic reduction in the Matthew effect.

cs.IR↗

arXiv2021

M6: A Chinese Multimodal Pretrainer

In this work, we construct the largest dataset for multimodal pretraining in Chinese, which consists of over 1.9TB images and 292GB texts that cover a wide range of domains. We propose a cross-modal pretraining method called M6, referring to Multi-Modality to Multi-Modality Multitask Mega-transformer, for unified pretraining on the data of single modality and multiple modalities. We scale the model size up to 10 billion and 100 billion parameters, and build the largest pretrained model in Chinese. We apply the model to a series of downstream applications, and demonstrate its outstanding performance in comparison with strong baselines. Furthermore, we specifically design a downstream task of text-guided image generation, and show that the finetuned M6 can create high-quality images with high resolution and abundant details.

cs.CL↗

arXiv2021

CloudAAE: Learning 6D Object Pose Regression with On-line Data Synthesis on Point Clouds

It is often desired to train 6D pose estimation systems on synthetic data because manual annotation is expensive. However, due to the large domain gap between the synthetic and real images, synthesizing color images is expensive. In contrast, this domain gap is considerably smaller and easier to fill for depth information. In this work, we present a system that regresses 6D object pose from depth information represented by point clouds, and a lightweight data synthesis pipeline that creates synthetic point cloud segments for training. We use an augmented autoencoder (AAE) for learning a latent code that encodes 6D object pose information for pose regression. The data synthesis pipeline only requires texture-less 3D object models and desired viewpoints, and it is cheap in terms of both time and hardware storage. Our data synthesis process is up to three orders of magnitude faster than commonly applied approaches that render RGB image data. We show the effectiveness of our system on the LineMOD, LineMOD Occlusion, and YCB Video datasets. The implementation of our system is available at: https://github.com/GeeeG/CloudAAE.

cs.CV↗

arXiv2021

Sparse-Interest Network for Sequential Recommendation

Recent methods in sequential recommendation focus on learning an overall embedding vector from a user's behavior sequence for the next-item recommendation. However, from empirical analysis, we discovered that a user's behavior sequence often contains multiple conceptually distinct items, while a unified embedding vector is primarily affected by one's most recent frequent actions. Thus, it may fail to infer the next preferred item if conceptually similar items are not dominant in recent interactions. To this end, an alternative solution is to represent each user with multiple embedding vectors encoding different aspects of the user's intentions. Nevertheless, recent work on multi-interest embedding usually considers a small number of concepts discovered via clustering, which may not be comparable to the large pool of item categories in real systems. It is a non-trivial task to effectively model a large number of diverse conceptual prototypes, as items are often not conceptually well clustered in fine granularity. Besides, an individual usually interacts with only a sparse set of concepts. In light of this, we propose a novel \textbf{S}parse \textbf{I}nterest \textbf{NE}twork (SINE) for sequential recommendation. Our sparse-interest module can adaptively infer a sparse set of concepts for each user from the large concept pool and output multiple embeddings accordingly. Given multiple interest embeddings, we develop an interest aggregation module to actively predict the user's current intention and then use it to explicitly model multiple interests for next-item prediction. Empirical results on several public benchmark datasets and one large-scale industrial dataset demonstrate that SINE can achieve substantial improvement over state-of-the-art methods.

cs.IR↗

arXiv2021

Dynamic Memory based Attention Network for Sequential Recommendation

Sequential recommendation has become increasingly essential in various online services. It aims to model the dynamic preferences of users from their historical interactions and predict their next items. The accumulated user behavior records on real systems could be very long. This rich data brings opportunities to track actual interests of users. Prior efforts mainly focus on making recommendations based on relatively recent behaviors. However, the overall sequential data may not be effectively utilized, as early interactions might affect users' current choices. Also, it has become intolerable to scan the entire behavior sequence when performing inference for each user, since real-world system requires short response time. To bridge the gap, we propose a novel long sequential recommendation model, called Dynamic Memory-based Attention Network (DMAN). It segments the overall long behavior sequence into a series of sub-sequences, then trains the model and maintains a set of memory blocks to preserve long-term interests of users. To improve memory fidelity, DMAN dynamically abstracts each user's long-term interest into its own memory blocks by minimizing an auxiliary reconstruction loss. Based on the dynamic memory, the user's short-term and long-term interests can be explicitly extracted and combined for efficient joint recommendation. Empirical results over four benchmark datasets demonstrate the superiority of our model in capturing long-term dependency over various state-of-the-art sequential models.

cs.IR↗

arXiv2021

ATCSpeechNet: A multilingual end-to-end speech recognition framework for air traffic control systems

In this paper, a multilingual end-to-end framework, called as ATCSpeechNet, is proposed to tackle the issue of translating communication speech into human-readable text in air traffic control (ATC) systems. In the proposed framework, we focus on integrating the multilingual automatic speech recognition (ASR) into one model, in which an end-to-end paradigm is developed to convert speech waveform into text directly, without any feature engineering or lexicon. In order to make up for the deficiency of the handcrafted feature engineering caused by ATC challenges, a speech representation learning (SRL) network is proposed to capture robust and discriminative speech representations from the raw wave. The self-supervised training strategy is adopted to optimize the SRL network from unlabeled data, and further to predict the speech features, i.e., wave-to-feature. An end-to-end architecture is improved to complete the ASR task, in which a grapheme-based modeling unit is applied to address the multilingual ASR issue. Facing the problem of small transcribed samples in the ATC domain, an unsupervised approach with mask prediction is applied to pre-train the backbone network of the ASR model on unlabeled data by a feature-to-feature process. Finally, by integrating the SRL with ASR, an end-to-end multilingual ASR framework is formulated in a supervised manner, which is able to translate the raw wave into text in one model, i.e., wave-to-text. Experimental results on the ATCSpeech corpus demonstrate that the proposed approach achieves a high performance with a very small labeled corpus and less resource consumption, only 4.20% label error rate on the 58-hour transcribed corpus. Compared to the baseline model, the proposed approach obtains over 100% relative performance improvement which can be further enhanced with the increasing of the size of the transcribed samples.

cs.CL↗

arXiv2021

Continuous Learning and Inference of Individual Probability of SARS-CoV-2 Infection Based on Interaction Data

This study presents a new approach to determine the likelihood of asymptomatic carriers of the SARS-CoV-2 virus by using interaction-based continuous learning and inference of individual probability (CLIIP) for contagious ranking. This approach is developed based on an individual directed graph (IDG), using multi-layer bidirectional path tracking and inference searching. The IDG is determined by the appearance timeline and spatial data that can adapt over time. Additionally, the approach takes into consideration the incubation period and several features that can represent real-world circumstances, such as the number of asymptomatic carriers present. After each update of confirmed cases, the model collects the interaction features and infers the individual person's probability of getting infected using the status of the surrounding people. The CLIIP approach is validated using the individualized bidirectional SEIR model to simulate the contagion process. Compared to traditional contact tracing methods, our approach significantly reduces the screening and quarantine required to search for the potential asymptomatic virus carriers by as much as 94%.

cs.SI↗

arXiv2020

Extreme Flow Decomposition for Multi-Source Multicast with Intra-Session Network Coding

Network coding (NC), when combined with multipath routing, enables a linear programming (LP) formulation for a multi-source multicast with intra-session network coding (MISNC) problem. However, it is still hard to solve using conventional methods due to the enormous scale of variables or constraints. In this paper, we try to solve this problem in terms of throughput maximization from an algorithmic perspective. We propose a novel formulation based on the extereme flow decomposition technique, which facilitates the design and analysis of approximation and online algorithms. For the offline scenario, we develop a fully polynomial time approximation scheme (FPTAS) which can find a $(1+ω)$-approximation solution for any specified $ω>0$. For the online scenario, we develop an online primal-dual algorithm which proves $O(1)$-competitive and violates link capacities by a factor of $O(\log m)$, where $m$ is the link number. The proposed algorithms share an elegant primal-dual form and thereby have inherent advantages of simplicity, efficiency, and scalability. To better understand the advantages of the extereme flow decomposition approach, we devise delicate numerical examples on an extended butterfly network. We validate the effects of algorithmic parameters and make an interesting comparison between the proposed FPTAS and online algorithm. The results show that the online algorithm has satisfactory performance while keeping the overall link utilization acceptable compared with the FPTAS.

cs.NI↗

arXiv2020

Q-SR: An Extensible Optimization Framework for Segment Routing

Segment routing (SR) combines the advantages of source routing supported by centralized software-defined networking (SDN) paradigm and hop-by-hop routing applied in distributed IP network infrastructure. However, because of the computation inefficiency, it is nearly impossible to evaluate whether various types of networks will benefit from the SR with multiple segments using conventional approaches. In this paper, we propose a flexible $Q$-SR model as well as its formulation in order to fully explore the potential of SR from an algorithmic perspective. The model leads to a highly extensible framework to design and evaluate algorithms that can be adapted to various network topologies and traffic matrices. For the offline setting, we develop a fully polynomial time approximation scheme (FPTAS) which can finds a $(1+ω)$-approximation solution for any specified $ω>0$ in time that is a polynomial function of the network size. To the best of our knowledge, the proposed FPTAS is the first algorithm that can compute arbitrarily accurate solution. For the online setting, we develop an online primal-dual algorithm that proves $O(1)$-competitive and violates link capacities by a factor of $O(\log n)$, where $n$ is the node number. We also prove performance bounds for the proposed algorithms. We conduct simulations on realistic topologies to validate SR parameters and algorithmic parameters in both offline and online scenarios.

cs.NI↗

arXiv2020

Dimensional Reweighting Graph Convolutional Networks

Graph Convolution Networks (GCNs) are becoming more and more popular for learning node representations on graphs. Though there exist various developments on sampling and aggregation to accelerate the training process and improve the performances, limited works focus on dealing with the dimensional information imbalance of node representations. To bridge the gap, we propose a method named Dimensional reweighting Graph Convolution Network (DrGCN). We theoretically prove that our DrGCN can guarantee to improve the stability of GCNs via mean field theory. Our dimensional reweighting method is very flexible and can be easily combined with most sampling and aggregation techniques for GCNs. Experimental results demonstrate its superior performances on several challenging transductive and inductive node classification benchmark datasets. Our DrGCN also outperforms existing models on an industrial-sized Alibaba recommendation dataset.

cs.LG↗

arXiv2020

Proactive Action Visual Residual Reinforcement Learning for Contact-Rich Tasks Using a Torque-Controlled Robot

Contact-rich manipulation tasks are commonly found in modern manufacturing settings. However, manually designing a robot controller is considered hard for traditional control methods as the controller requires an effective combination of modalities and vastly different characteristics. In this paper, we firstly consider incorporating operational space visual and haptic information into reinforcement learning(RL) methods to solve the target uncertainty problem in unstructured environments. Moreover, we propose a novel idea of introducing a proactive action to solve the partially observable Markov decision process problem. Together with these two ideas, our method can either adapt to reasonable variations in unstructured environments and improve the sample efficiency of policy learning. We evaluated our method on a task that involved inserting a random-access memory using a torque-controlled robot, and we tested the success rates of the different baselines used in the traditional methods. We proved that our method is robust and can tolerate environmental variations very well.

cs.RO↗

arXiv2020

Robust Robotic Pouring using Audition and Haptics

Robust and accurate estimation of liquid height lies as an essential part of pouring tasks for service robots. However, vision-based methods often fail in occluded conditions while audio-based methods cannot work well in a noisy environment. We instead propose a multimodal pouring network (MP-Net) that is able to robustly predict liquid height by conditioning on both audition and haptics input. MP-Net is trained on a self-collected multimodal pouring dataset. This dataset contains 300 robot pouring recordings with audio and force/torque measurements for three types of target containers. We also augment the audio data by inserting robot noise. We evaluated MP-Net on our collected dataset and a wide variety of robot experiments. Both network training results and robot experiments demonstrate that MP-Net is robust against noise and changes to the task and environment. Moreover, we further combine the predicted height and force data to estimate the shape of the target container.

cs.RO↗

arXiv2020

Cascade Convolutional Neural Network for Image Super-Resolution

With the development of the super-resolution convolutional neural network (SRCNN), deep learning technique has been widely applied in the field of image super-resolution. Previous works mainly focus on optimizing the structure of SRCNN, which have been achieved well performance in speed and restoration quality for image super-resolution. However, most of these approaches only consider a specific scale image during the training process, while ignoring the relationship between different scales of images. Motivated by this concern, in this paper, we propose a cascaded convolution neural network for image super-resolution (CSRCNN), which includes three cascaded Fast SRCNNs and each Fast SRCNN can process a specific scale image. Images of different scales can be trained simultaneously and the learned network can make full use of the information resided in different scales of images. Extensive experiments show that our network can achieve well performance for image SR.

cs.CV↗

arXiv2020

Controllable Multi-Interest Framework for Recommendation

Recently, neural networks have been widely used in e-commerce recommender systems, owing to the rapid development of deep learning. We formalize the recommender system as a sequential recommendation problem, intending to predict the next items that the user might be interacted with. Recent works usually give an overall embedding from a user's behavior sequence. However, a unified user embedding cannot reflect the user's multiple interests during a period. In this paper, we propose a novel controllable multi-interest framework for the sequential recommendation, called ComiRec. Our multi-interest module captures multiple interests from user behavior sequences, which can be exploited for retrieving candidate items from the large-scale item pool. These items are then fed into an aggregation module to obtain the overall recommendation. The aggregation module leverages a controllable factor to balance the recommendation accuracy and diversity. We conduct experiments for the sequential recommendation on two real-world datasets, Amazon and Taobao. Experimental results demonstrate that our framework achieves significant improvements over state-of-the-art models. Our framework has also been successfully deployed on the offline Alibaba distributed cloud platform.

cs.IR↗