Search Results for author:
Found 68 papers, 19 papers with code
TA-MoE: Topology-Aware Large Scale Mixture-of-Expert Training
In this paper, we propose TA-MoE, a topology-aware routing strategy for large-scale MoE trainging, from a model-system co-design perspective, which can dynamically adjust the MoE dispatch pattern according to the network topology.
R2FD2: Fast and Robust Matching of Multimodal Remote Sensing Image via Repeatable Feature Detector and Rotation-invariant Feature Descriptor
Automatically identifying feature correspondences between multimodal images is facing enormous challenges because of the significant differences both in radiation and geometry.
Multi-view Multi-label Anomaly Network Traffic Classification based on MLP-Mixer Neural Network
In this paper, we propose a MLP-Mixer based multi-view multi-label neural network for network traffic classification.
Research on Multi-Objective Planning of Electric Vehicle Charging Stations Considering the Condition of Urban Traffic Network
How to weigh various factors to construct a reasonable model of charging station location and capacity has become a major difficulty in the field of electric vehicle charging facility planning.
Privacy Preservation by Local Design in Cooperative Networked Control Systems
In this paper, we study the privacy preservation problem in a cooperative networked control system working for the task of LQG control.
GUIM -- General User and Item Embedding with Mixture of Representation in E-commerce
Our goal is to build general representation (embedding) for each user and each product item across Alibaba's businesses, including Taobao and Tmall which are among the world's biggest e-commerce websites.
WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit
Recently, we made available WeNet, a production-oriented end-to-end speech recognition toolkit, which introduces a unified two-pass (U2) framework and a built-in runtime to address the streaming and non-streaming decoding modes in a single model.
A Robust Multimodal Remote Sensing Image Registration Method and System Using Steerable Filters with First- and Second-order Gradients
In this paper, a robust matching method based on the Steerable filters is proposed consisting of two critical steps.
Sim2Real Object-Centric Keypoint Detection and Description
Keypoint detection and description play a central role in computer vision.
DAS-PINNs: A deep adaptive sampling method for solving high-dimensional partial differential equations
In this work we propose a deep adaptive sampling (DAS) method for solving partial differential equations (PDEs), where deep neural networks are utilized to approximate the solutions of PDEs and deep generative models are employed to generate new collocation points that refine the training set.
End-to-end Adaptive Distributed Training on PaddlePaddle
The experiments demonstrate that our framework can satisfy various requirements from the diversity of applications and the heterogeneity of resources with highly competitive performance.
A rank-adaptive higher-order orthogonal iteration algorithm for truncated Tucker decomposition
We propose a novel rank-adaptive higher-order orthogonal iteration (HOOI) algorithm to compute the truncated Tucker decomposition of higher-order tensors with a given error tolerance, and prove that the method is locally optimal and monotonically convergent.
WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition
In this paper, we present WenetSpeech, a multi-domain Mandarin corpus consisting of 10000+ hours high-quality labeled speech, 2400+ hours weakly labeled speech, and about 10000 hours unlabeled speech, with 22400+ hours in total.
Ranked #4 on
Speech Recognition
on WenetSpeech
A review of computational tools for generating metagenome-assembled genomes from metagenomic sequencing data
Metagenomics has equipped us with new avenues of investigating the microbiome, from studying a single species to a complex community in a dynamic ecosystem.
Economic Dispatch of an Integrated Microgrid Based on the Dynamic Process of CCGT Plant
Intra-day economic dispatch of an integrated microgrid is a fundamental requirement to integrate distributed generators.
Adapting Off-the-Shelf Source Segmenter for Target Medical Image Segmentation
To alleviate this, in this work, we target source free UDA for segmentation, and propose to adapt an ``off-the-shelf" segmentation model pre-trained in the source domain to the target domain, with an adaptive batch-wise normalization statistics adaptation framework.
SAS: Self-Augmentation Strategy for Language Model Pre-training
In this paper, we propose a self-augmentation strategy (SAS) where a single network is utilized for both regular pre-training and contextualized data augmentation for the training in later epochs.
U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition
On the experiment of AISHELL-1, we achieve a 4. 63\% character error rate (CER) with a non-streaming setup and 5. 05\% with a streaming setup with 320ms latency by U2++.
Composite Localization for Human Pose Estimation
This work proposes a novel deep learning framework for human pose estimation called composite localization to divide the complex learning objective into two simpler ones: a sparse heatmap to find the keypoint's approximate location and two short-distance offsetmaps to obtain its final precise coordinates.
FDNet: A Deep Learning Approach with Two Parallel Cross Encoding Pathways for Precipitation Nowcasting
To the best of our knowledge, this is the first network architecture with flow and deformation separation to model the evolution of radar echoes for precipitation nowcasting.
Randomized Algorithms for Scientific Computing (RASC)
Randomized algorithms have propelled advances in artificial intelligence and represent a foundational research area in advancing AI for Science.
WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit
In this paper, we propose an open source, production first, and production ready speech recognition toolkit called WeNet in which a new two-pass approach is implemented to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model.
Symmetric-Constrained Irregular Structure Inpainting for Brain MRI Registration with Tumor Pathology
Deformable registration of magnetic resonance images between patients with brain tumors and healthy subjects has been an important tool to specify tumor geometry through location alignment and facilitate pathological analysis.
VoxelHop: Successive Subspace Learning for ALS Disease Classification Using Structural MRI
Deep learning has great potential for accurate detection and classification of diseases with medical imaging data, but the performance is often limited by the number of training datasets and memory requirements.
Learning content and context with language bias for Visual Question Answering
Many works concentrate on how to reduce language bias which makes models answer questions ignoring visual content and language context.
PPGN: Phrase-Guided Proposal Generation Network For Referring Expression Comprehension
Reference expression comprehension (REC) aims to find the location that the phrase refer to in a given image.
Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition
In this paper, we present a novel two-pass approach to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model.
Ranked #5 on
Speech Recognition
on AISHELL-1
PEDNet: A Persona Enhanced Dual Alternating Learning Network for Conversational Response Generation
However, generating personalized responses is still a challenging task since the leverage of predefined persona information is often insufficient.
METNet: A Mutual Enhanced Transformation Network for Aspect-based Sentiment Analysis
Aspect-based sentiment analysis (ABSA) aims to determine the sentiment polarity of each specific aspect in a given sentence.
Aspect-Based Sentiment Analysis (ABSA)
Representation Learning
CoRe: An Efficient Coarse-refined Training Framework for BERT
In the second phase, we transform the trained relaxed BERT model into the original BERT and further retrain the model.
Progressively Stacking 2.0: A Multi-stage Layerwise Training Method for BERT Training Speedup
In BERT training, the backward computation is much more time-consuming than the forward computation, especially in the distributed training setting in which the backward computation time further includes the communication time for gradient synchronization.
Fault-Aware Robust Control via Adversarial Reinforcement Learning
Robots have limited adaptation ability compared to humans and animals in the case of damage.
a-Tucker: Input-Adaptive and Matricization-Free Tucker Decomposition for Dense Tensors on CPUs and GPUs
A mode-wise flexible Tucker decomposition algorithm is proposed to enable the switch of different solvers for the factor matrices and core tensor, and a machine-learning adaptive solver selector is applied to automatically cope with the variations of both the input data and the hardware.
Gated Res2Net for Multivariate Time Series Analysis
Through the utilization of gated mechanism, the network can control the process of information sending hence can better capture and utilize the both the temporal information and the correlations between the feature maps.
Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations
We use CNN features from the deep and shallow layers of the encoder to represent structures and textures of an input image, respectively.
AUTO3D: Novel view synthesis through unsupervisely learned variational viewpoint and global 3D representation
This paper targets on learning-based novel view synthesis from a single or limited 2D images without the pose supervision.
On the Efficient Evaluation of the Exchange Correlation Potential on Graphics Processing Unit Clusters
We demonstrate the performance and scalability of the implementation of the purposed method in the NWChemEx software package by comparing to the existing scalable CPU XC integration in NWChem.
Computational Physics Distributed, Parallel, and Cluster Computing Chemical Physics
Improving Co-registration for Sentinel-1 SAR and Sentinel-2 Optical images
Finally, the obtained correspondences are employed to measure the misregistration shifts between the images.
Fast and Robust Registration of Aerial Images and LiDAR data Based on Structrual Features and 3D Phase Correlation
Subsequently, a robust structural feature descriptor is build based on dense gradient features, and the 3D phase correlation is used to detect control points (CPs) between aerial images and LiDAR data in the frequency domain, where the image matching is accelerated by the 3D Fast Fourier Transform (FFT).
PFNN: A Penalty-Free Neural Network Method for Solving a Class of Second-Order Boundary-Value Problems on Complex Geometries
We present PFNN, a penalty-free neural network method, to efficiently solve a class of second-order boundary-value problems on complex geometries.
Efficient Alternating Least Squares Algorithms for Low Multilinear Rank Approximation of Tensors
In this paper, we propose a new class of truncated HOSVD algorithms based on alternating least squares (ALS) for efficiently computing the low multilinear rank approximation of tensors.
One-Shot Domain Adaptation For Face Generation
To generate images of the same distribution, we introduce a style-mixing technique that transfers the low-level statistics from the target to faces randomly generated with the model.
One-Stage Inpainting with Bilateral Attention and Pyramid Filling Block
However, the two-stage architecture is time-consuming, the contextual information lack high-level semantics and ignores both the semantic relevance and distance information of hole's feature patches, these limitations result in blurry textures and distorted structures of final result.
Unconstrained Facial Expression Transfer using Style-based Generator
Given two face images, our method can create plausible results that combine the appearance of one image and the expression of the other.
Towards Disentangled Representations for Human Retargeting by Multi-view Learning
We study the problem of learning disentangled representations for data across multiple domains and its applications in human retargeting.
Boundary-Aware Salient Object Detection via Recurrent Two-Stream Guided Refinement Network
Recent deep learning based salient object detection methods which utilize both saliency and boundary features have achieved remarkable performance.
Constrained R-CNN: A general image manipulation detection model
Finally, the coarse localization information guides the model to further learn the finer local features and segment out the tampered region.
Reinforcement Learning from Imperfect Demonstrations under Soft Expert Guidance
In this paper, we study Reinforcement Learning from Demonstrations (RLfD) that improves the exploration efficiency of Reinforcement Learning (RL) by providing expert demonstrations.
Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement
This paper studies Learning from Observations (LfO) for imitation learning with access to state-only demonstrations.
Context-Integrated and Feature-Refined Network for Lightweight Object Parsing
The core components of CIFReNet are the Long-skip Refinement Module (LRM) and the Multi-scale Context Integration Module (MCIM).
Dependency-aware Attention Control for Unconstrained Face Recognition with Image Sets
This paper targets the problem of image set-based face verification and identification.
Coherent Semantic Attention for Image Inpainting
The latest deep learning-based approaches have shown promising results for the challenging task of inpainting missing regions of an image.
Ranked #1 on
Image Inpainting
on Paris StreetView
Deep learning: Extrapolation tool for ab initio nuclear theory
The NCSM and other approaches require an extrapolation of the results obtained in a finite basis space to the infinite basis space limit and assessment of the uncertainty of those extrapolations.
A Survey on Deep Transfer Learning
As a new classification platform, deep learning has recently received increasing attention from researchers and has been successfully applied to many domains.
PortraitGAN for Flexible Portrait Manipulation
Previous methods have dealt with discrete manipulation of facial attributes such as smile, sad, angry, surprise etc, out of canonical expressions and they are not scalable, operating in single modality.
Show, Attend and Translate: Unsupervised Image Translation with Self-Regularization and Attention
It has been applied to numerous domains, such as data augmentation, domain adaptation, and unsupervised training.
SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting
In this paper, we focus on image inpainting task, aiming at recovering the missing area of an incomplete image given the context information.
Image Inpainting using Block-wise Procedural Training with Annealed Adversarial Counterpart
We present a new approach to address the difficulty of training a very deep generative model to synthesize high-quality photo-realistic inpainting.
Deep Learning: A Tool for Computational Nuclear Physics
In recent years, several successful applications of the Artificial Neural Networks (ANNs) have emerged in nuclear physics and high-energy physics, as well as in biology, chemistry, meteorology, and other fields of science.
Computational Physics Nuclear Theory
Contextual-based Image Inpainting: Infer, Match, and Translate
We study the task of image inpainting, which is to fill in the missing region of an incomplete image with plausible contents.
Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networks
The 3D-ED-GAN is a 3D convolutional neural network trained with a generative adversarial paradigm to fill missing 3D data in low-resolution.
Realistic Dynamic Facial Textures From a Single Image Using GANs
By retargeting the PCA expression geometry from the source, as well as using the newly inferred texture, we can both animate the face and perform video face replacement on the source video using the target appearance.
High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis
Recent advances in deep learning have shown exciting promise in filling large holes in natural images with semantically plausible and context aware details, impacting fundamental image manipulation tasks such as object removal.
Symmetry-aware Depth Estimation using Deep Neural Networks
Due to the abundance of 2D product images from the Internet, developing efficient and scalable algorithms to recover the missing depth information is central to many applications.
Exact Hybrid Covariance Thresholding for Joint Graphical Lasso
This paper proposes a novel hybrid covariance thresholding algorithm that can effectively identify zero entries in the precision matrices and split a large joint graphical lasso problem into small subproblems.
Low-rank SIFT: An Affine Invariant Feature for Place Recognition
As an extension of SIFT, our method seeks to add prior to solve the ill-posed affine parameter estimation problem and normalizes them directly, and is applicable to objects with regular structures.
Feature selection for classification with class-separability strategy and data envelopment analysis
In this paper, a novel feature selection method is presented, which is based on Class-Separability (CS) strategy and Data Envelopment Analysis (DEA).
