arXiv subjects

Yi Fang

Publications and source records attributed to Yi Fang.

At least 163 records · Page 9Linked to original sources

arXiv2022

WebFormer: The Web-page Transformer for Structure Information Extraction

Structure information extraction refers to the task of extracting structured text fields from web pages, such as extracting a product offer from a shopping page including product title, description, brand and price. It is an important research topic which has been widely studied in document understanding and web search. Recent natural language models with sequence modeling have demonstrated state-of-the-art performance on web information extraction. However, effectively serializing tokens from unstructured web pages is challenging in practice due to a variety of web layout patterns. Limited work has focused on modeling the web layout for extracting the text fields. In this paper, we introduce WebFormer, a Web-page transFormer model for structure information extraction from web documents. First, we design HTML tokens for each DOM node in the HTML by embedding representations from their neighboring tokens through graph attention. Second, we construct rich attention patterns between HTML tokens and text tokens, which leverages the web layout for effective attention weight computation. We conduct an extensive set of experiments on SWDE and Common Crawl benchmarks. Experimental results demonstrate the superior performance of the proposed approach over several state-of-the-art methods.

cs.CL↗

arXiv2021

3D Meta-Segmentation Neural Network

Though deep learning methods have shown great success in 3D point cloud part segmentation, they generally rely on a large volume of labeled training data, which makes the model suffer from unsatisfied generalization abilities to unseen classes with limited data. To address this problem, we present a novel meta-learning strategy that regards the 3D shape segmentation function as a task. By training over a number of 3D part segmentation tasks, our method is capable to learn the prior over the respective 3D segmentation function space which leads to an optimal model that is rapidly adapting to new part segmentation tasks. To implement our meta-learning strategy, we propose two novel modules: meta part segmentation learner and part segmentation learner. During the training process, the part segmentation learner is trained to complete a specific part segmentation task in the few-shot scenario. In the meantime, the meta part segmentation learner is trained to capture the prior from multiple similar part segmentation tasks. Based on the learned information of task distribution, our meta part segmentation learner is able to dynamically update the part segmentation learner with optimal parameters which enable our part segmentation learner to rapidly adapt and have great generalization ability on new part segmentation tasks. We demonstrate that our model achieves superior part segmentation performance with the few-shot setting on the widely used dataset: ShapeNet.

cs.CV↗

arXiv2021

3D Point Cloud Completion with Geometric-Aware Adversarial Augmentation

With the popularity of 3D sensors in self-driving and other robotics applications, extensive research has focused on designing novel neural network architectures for accurate 3D point cloud completion. However, unlike in point cloud classification and reconstruction, the role of adversarial samples in3D point cloud completion has seldom been explored. In this work, we show that training with adversarial samples can improve the performance of neural networks on 3D point cloud completion tasks. We propose a novel approach to generate adversarial samples that benefit both the performance of clean and adversarial samples. In contrast to the PGD-k attack, our method generates adversarial samples that keep the geometric features in clean samples and contain few outliers. In particular, we use principal directions to constrain the adversarial perturbations for each input point. The gradient components in the mean direction of principal directions are taken as adversarial perturbations. In addition, we also investigate the effect of using the minimum curvature direction. Besides, we adopt attack strength accumulation and auxiliary Batch Normalization layers method to speed up the training process and alleviate the distribution mismatch between clean and adversarial samples. Experimental results show that training with the adversarial samples crafted by our method effectively enhances the performance of PCN on the ShapeNet dataset.

cs.CV↗

arXiv2021

ContinuityLearner: Geometric Continuity Feature Learning for Lane Segmentation

Lane segmentation is a challenging issue in autonomous driving system designing because lane marks show weak textural consistency due to occlusion or extreme illumination but strong geometric continuity in traffic images, from which general convolution neural networks (CNNs) are not capable of learning semantic objects. To empower conventional CNNs in learning geometric clues of lanes, we propose a deep network named ContinuityLearner to better learn geometric prior within lane. Specifically, our proposed CNN-based paradigm involves a novel Context-encoding image feature learning network to generate class-dependent image feature maps and a new encoding layer to exploit the geometric continuity feature representation by fusing both spatial and visual information of lane together. The ContinuityLearner, performing on the geometric continuity feature of lanes, is trained to directly predict the lane in traffic scenarios with integrated and continuous instance semantic. The experimental results on the CULane dataset and the Tusimple benchmark demonstrate that our ContinuityLearner has superior performance over other state-of-the-art techniques in lane segmentation.

cs.CV↗

arXiv2021

Performance Analysis of a Two-Hop Relaying LoRa System

The conventional LoRa system is not able to sustain long-range communication over fading channels. To resolve the challenging issue, this paper investigates a two-hop opportunistic amplify-and-forward relaying LoRa system. Based on the best relay-selection protocol, the analytical and asymptotic bit error rate (BER), achievable diversity order, coverage probability, and throughput of the proposed system are derived over the Nakagamim fading channel. Simulative and numerical results show that although the proposed system reduces the throughput compared to the conventional LoRa system, it can significantly improve BER and coverage probability. Hence, the proposed system can be considered as a promising platform for low-power, long-range and highly reliable wireless-communication applications.

cs.IT↗

arXiv2021

Outage-Limit-Approaching Protograph LDPC Codes for Slow-Fading Wireless Communications

Block-fading (BF) channel, also known as slow-fading channel, is a type of simple and practical channel model that can characterize the primary feature of a number of wireless-communication applications with low to moderate mobility. Although the BF channel has received significant research attention in the past twenty years, designing low-complexity outage-limit-approaching error-correction codes (ECCs) is still a challenging issue. For this reason, a novel family of protograph low-density parity-check (LDPC) codes, called root-protograph (RP) LDPC codes, has been conceived recently. The RP codes can not only realize linear-complexity encoding and high-speed decoding with the help of a quasi-cyclic (QC) structure, but also achieve near-outage-limit performance in a variety of BF scenarios. In this article, we briefly review the design guidelines of such protograph codes with the aim of inspiring further research activities in this area.

cs.IT↗

arXiv2021

Irregular-Mapped Protograph LDPC-Coded Modulation: A Bandwidth-Efficient Solution for $5$G Networks with Massive Data-Storage Requirement

The huge amount of data produced in the fifth-generation (5G) networks not only brings new challenges to the reliability and efficiency of mobile devices but also drives rapid development of new storage techniques. With the benefits of fast access speed and high reliability, NAND flash memory has become a promising storage solution for the 5G networks. In this paper, we investigate a protograph-coded bit-interleaved coded modulation with iterative detection and decoding (BICM-ID) utilizing irregular mapping (IM) in the multi-level-cell (MLC) NAND flash-memory systems. First, we propose an enhanced protograph-based extrinsic information transfer (EPEXIT) algorithm to facilitate the analysis of protograph codes in the IM-BICM-ID systems. With the use of EPEXIT algorithm, a simple design method is conceived for the construction of a family of high-rate protograph codes, called irregular-mapped accumulate-repeat-accumulate (IMARA) codes, which possess both excellent decoding thresholds and linear-minimum-distance-growth property. Furthermore, motivated by the voltage-region iterative gain characteristics of IM-BICM-ID systems, a novel read-voltage optimization scheme is developed to acquire accurate read-voltage levels, thus minimizing the decoding thresholds of protograph codes. Theoretical analyses and error-rate simulations indicate that the proposed IMARA-aided IM-BICM-ID scheme and the proposed read-voltage optimization scheme remarkably improve the convergence and decoding performance of flash-memory systems. Thus, the proposed protograph-coded IM-BICM-ID flash-memory systems can be viewed as a reliable and efficient storage solution for the new-generation mobile networks with massive data-storage requirement.

cs.IT↗

arXiv2021

Learn to Learn Metric Space for Few-Shot Segmentation of 3D Shapes

Recent research has seen numerous supervised learning-based methods for 3D shape segmentation and remarkable performance has been achieved on various benchmark datasets. These supervised methods require a large amount of annotated data to train deep neural networks to ensure the generalization ability on the unseen test set. In this paper, we introduce a meta-learning-based method for few-shot 3D shape segmentation where only a few labeled samples are provided for the unseen classes. To achieve this, we treat the shape segmentation as a point labeling problem in the metric space. Specifically, we first design a meta-metric learner to transform input shapes into embedding space and our model learns to learn a proper metric space for each object class based on point embeddings. Then, for each class, we design a metric learner to extract part-specific prototype representations from a few support shapes and our model performs per-point segmentation over the query shapes by matching each point to its nearest prototype in the learned metric space. A metric-based loss function is used to dynamically modify distances between point embeddings thus maximizes in-part similarity while minimizing inter-part similarity. A dual segmentation branch is adopted to make full use of the support information and implicitly encourages consistency between the support and query prototypes. We demonstrate the superior performance of our proposed on the ShapeNet part dataset under the few-shot scenario, compared with well-established baseline and state-of-the-art semi-supervised methods.

cs.CV↗

arXiv2021

Residual Networks as Flows of Velocity Fields for Diffeomorphic Time Series Alignment

Non-linear (large) time warping is a challenging source of nuisance in time-series analysis. In this paper, we propose a novel diffeomorphic temporal transformer network for both pairwise and joint time-series alignment. Our ResNet-TW (Deep Residual Network for Time Warping) tackles the alignment problem by compositing a flow of incremental diffeomorphic mappings. Governed by the flow equation, our Residual Network (ResNet) builds smooth, fluid and regular flows of velocity fields and consequently generates smooth and invertible transformations (i.e. diffeomorphic warping functions). Inspired by the elegant Large Deformation Diffeomorphic Metric Mapping (LDDMM) framework, the final transformation is built by the flow of time-dependent vector fields which are none other than the building blocks of our Residual Network. The latter is naturally viewed as an Eulerian discretization schema of the flow equation (an ODE). Once trained, our ResNet-TW aligns unseen data by a single inexpensive forward pass. As we show in experiments on both univariate (84 datasets from UCR archive) and multivariate time-series (MSR Action-3D, Florence-3D and MSR Daily Activity), ResNet-TW achieves competitive performance in joint alignment and classification.

cs.CV↗

arXiv2021

G-VAE, a Geometric Convolutional VAE for ProteinStructure Generation

Analyzing the structure of proteins is a key part of understanding their functions and thus their role in biology at the molecular level. In addition, design new proteins in a methodical way is a major engineering challenge. In this work, we introduce a joint geometric-neural networks approach for comparing, deforming and generating 3D protein structures. Viewing protein structures as 3D open curves, we adopt the Square Root Velocity Function (SRVF) representation and leverage its suitable geometric properties along with Deep Residual Networks (ResNets) for a joint registration and comparison. Our ResNets handle better large protein deformations while being more computationally efficient. On top of the mathematical framework, we further design a Geometric Variational Auto-Encoder (G-VAE), that once trained, maps original, previously unseen structures, into a low-dimensional (latent) hyper-sphere. Motivated by the spherical structure of the pre-shape space, we naturally adopt the von Mises-Fisher (vMF) distribution to model our hidden variables. We test the effectiveness of our models by generating novel protein structures and predicting completions of corrupted protein structures. Experimental results show that our method is able to generate plausible structures, different from the structures in the training data.

cs.CV↗

arXiv2021

A New Frequency-Bin-Index LoRa System for High-Data-Rate Transmission: Design and Performance Analysis

As an attempt to tackle the low-data-rate issue of the conventional LoRa systems, we propose two novel frequency-bin-index (FBI) LoRa schemes. In scheme I, the indices of starting frequency bins (SFBs) are utilized to carry the information bits. To facilitate the actual implementation, the SFBs of each LoRa signal are divided into several groups prior to the modulation process in the proposed FBI-LoRa system. To further improve the system flexibility, we formulate a generalized modulation scheme and propose scheme II by treating the SFB groups as an additional type of transmission entity. In scheme II, the combination of SFB indices and that of SFB group indices are both exploited to carry the information bits. We derive the theoretical expressions for bit-error-rate (BER) and throughput of the proposed FBI-LoRa system with two modulation schemes over additive white Gaussian noise (AWGN) and Rayleigh fading channels. Theoretical and simulation results show that the proposed FBI-LoRa schemes can significantly increases the transmission throughput compared with the existing LoRa systems at the expense of a slight loss in BER performance. Thanks to the appealing superiorities, the proposed FBI-LoRa system is a promising alternative for high-data-rate Internet of Things (IoT) applications.

eess.SP↗

arXiv2021

Rate-Diverse Gaussian Multiple Access: Efficient Encoder and Decoder Designs

In this work, we develop a pair of rate-diverse encoder and decoder for a two-user Gaussian multiple access channel (GMAC). The proposed scheme enables the users to transmit with the same codeword length but different coding rates under diverse user channel conditions. First, we propose the row-combining (RC) method and row-extending (RE) method to design practical low-density parity-check (LDPC) channel codes for rate-diverse GMAC. Second, we develop an iterative rate-diverse joint user messages decoding (RDJD) algorithm for GMAC, where all user messages are decoded with a single parity-check matrix. In contrast to the conventional network-coded multiple access (NCMA) and compute-forward multiple access (CFMA) schemes that first recover a linear combination of the transmitted codewords and then decode both user messages, this work can decode both the user messages simultaneously. Extrinsic information transfer (EXIT) chart analysis and simulation results indicate that RDJD can achieve gains up to 1.0 dB over NCMA and CFMA in the two-user GMAC. In particular, we show that there exists an optimal rate allocation for the two users to achieve the best decoding performance given the channel conditions and sum rate.

cs.IT↗

arXiv2021

Correction to the photometric magnitudes of the Gaia Early Data Release 3

In this letter, we have carried out an independent validation of the Gaia EDR3 photometry using about 10,000 Landolt standard stars from Clem & Landolt (2013). Using a machine learning technique, the UBVRI magnitudes are converted into the Gaia magnitudes and colors and then compared to those in the EDR3, with the effect of metallicity incorporated. Our result confirms the significant improvements in the calibration process of the Gaia EDR3. Yet modest trends up to 10 mmag with G magnitude are found for all the magnitudes and colors for the 10 < G < 19 mag range, particularly for the bright and faint ends. With the aid of synthetic magnitudes computed on the CALSPEC spectra with the Gaia EDR3 passbands, absolute corrections are further obtained, paving the way for optimal usage of the Gaia EDR3 photometry in high accuracy investigations.

astro-ph.SR↗

arXiv2020

Universal Urban Spreading Pattern of COVID-19 and Its Underlying Mechanism

Currently, the global situation of COVID-19 is aggravating, pressingly calling for efficient control and prevention measures. Understanding spreading pattern of COVID-19 has been widely recognized as a vital step for implementing non-pharmaceutical measures. Previous studies investigated such an issue in large-scale (e.g., inter-country or inter-state) scenarios while urban spreading pattern still remains an open issue. Here, we fill this gap by leveraging the trajectory data of 197,808 smartphone users (including 17,808 anonymous confirmed cases) in 9 cities in China. We find a universal spreading pattern in all cities: the spatial distribution of confirmed cases follows a power-law-like model and the spreading centroid is time-invariant. Moreover, we reveal that human mobility in a city drives the spatialtemporal spreading process: long average travelling distance results in a high growth rate of spreading radius and wide spatial diffusion of confirmed cases. With such insight, we adopt Kendall model to simulate urban spreading of COVID-19 that can well fit the real spreading process. Our results unveil the underlying mechanism behind the spatial-temporal urban evolution of COVID-19, and can be used to evaluate the performance of mobility restriction policies implemented by many governments and to estimate the evolving spreading situation of COVID-19.

physics.soc-ph↗

arXiv2020

Leveraging an Efficient and Semantic Location Embedding to Seek New Ports of Bike Share Services

For short distance traveling in crowded urban areas, bike share services are becoming popular owing to the flexibility and convenience. To expand the service coverage, one of the key tasks is to seek new service ports, which requires to well understand the underlying features of the existing service ports. In this paper, we propose a new model, named for Efficient and Semantic Location Embedding (ESLE), which carries both geospatial and semantic information of the geo-locations. To generate ESLE, we first train a multi-label model with a deep Convolutional Neural Network (CNN) by feeding the static map-tile images and then extract location embedding vectors from the model. Compared to most recent relevant literature, ESLE is not only much cheaper in computation, but also easier to interpret via a systematic semantic analysis. Finally, we apply ESLE to seek new service ports for NTT DOCOMO's bike share services operated in Japan. The initial results demonstrate the effectiveness of ESLE, and provide a few insights that might be difficult to discover by using the conventional approaches.

cs.LG↗

arXiv2020

3D Meta-Registration: Learning to Learn Registration of 3D Point Clouds

Deep learning-based point cloud registration models are often generalized from extensive training over a large volume of data to learn the ability to predict the desired geometric transformation to register 3D point clouds. In this paper, we propose a meta-learning based 3D registration model, named 3D Meta-Registration, that is capable of rapidly adapting and well generalizing to new 3D registration tasks for unseen 3D point clouds. Our 3D Meta-Registration gains a competitive advantage by training over a variety of 3D registration tasks, which leads to an optimized model for the best performance on the distribution of registration tasks including potentially unseen tasks. Specifically, the proposed 3D Meta-Registration model consists of two modules: 3D registration learner and 3D registration meta-learner. During the training, the 3D registration learner is trained to complete a specific registration task aiming to determine the desired geometric transformation that aligns the source point cloud with the target one. In the meantime, the 3D registration meta-learner is trained to provide the optimal parameters to update the 3D registration learner based on the learned task distribution. After training, the 3D registration meta-learner, which is learned with the optimized coverage of distribution of 3D registration tasks, is able to dynamically update 3D registration learners with desired parameters to rapidly adapt to new registration tasks. We tested our model on synthesized dataset ModelNet and FlyingThings3D, as well as real-world dataset KITTI. Experimental results demonstrate that 3D Meta-Registration achieves superior performance over other previous techniques (e.g. FlowNet3D).

cs.CV↗

arXiv2020

3D Meta Point Signature: Learning to Learn 3D Point Signature for 3D Dense Shape Correspondence

Point signature, a representation describing the structural neighborhood of a point in 3D shapes, can be applied to establish correspondences between points in 3D shapes. Conventional methods apply a weight-sharing network, e.g., any kind of graph neural networks, across all neighborhoods to directly generate point signatures and gain the generalization ability by extensive training over a large amount of training samples from scratch. However, these methods lack the flexibility in rapidly adapting to unseen neighborhood structures and thus generalizes poorly on new point sets. In this paper, we propose a novel meta-learning based 3D point signature model, named 3Dmetapointsignature (MEPS) network, that is capable of learning robust point signatures in 3D shapes. By regarding each point signature learning process as a task, our method obtains an optimized model over the best performance on the distribution of all tasks, generating reliable signatures for new tasks, i.e., signatures of unseen point neighborhoods. Specifically, the MEPS consists of two modules: a base signature learner and a meta signature learner. During training, the base-learner is trained to perform specific signature learning tasks. In the meantime, the meta-learner is trained to update the base-learner with optimal parameters. During testing, the meta-learner that is learned with the distribution of all tasks can adaptively change parameters of the base-learner, accommodating to unseen local neighborhoods. We evaluate the MEPS model on two datasets, e.g., FAUST and TOSCA, for dense 3Dshape correspondence. Experimental results demonstrate that our method not only gains significant improvements over the baseline model and achieves state-of-the-art results, but also is capable of handling unseen 3D shapes.

cs.CV↗

arXiv2020

Deep-3DAligner: Unsupervised 3D Point Set Registration Network With Optimizable Latent Vector

Point cloud registration is the process of aligning a pair of point sets via searching for a geometric transformation. Unlike classical optimization-based methods, recent learning-based methods leverage the power of deep learning for registering a pair of point sets. In this paper, we propose to develop a novel model that organically integrates the optimization to learning, aiming to address the technical challenges in 3D registration. More specifically, in addition to the deep transformation decoding network, our framework introduce an optimizable deep \underline{S}patial \underline{C}orrelation \underline{R}epresentation (SCR) feature. The SCR feature and weights of the transformation decoder network are jointly updated towards the minimization of an unsupervised alignment loss. We further propose an adaptive Chamfer loss for aligning partial shapes. To verify the performance of our proposed method, we conducted extensive experiments on the ModelNet40 dataset. The results demonstrate that our method achieves significantly better performance than the previous state-of-the-art approaches in the full/partial point set registration task.

cs.CV↗