Searcharxiv⌕ Search

arXiv subjects

Di Huang

Publications and source records attributed to Di Huang.

At least 235 records · Page 13Linked to original sources
arXiv2021

Pixel Sampling for Style Preserving Face Pose Editing

The existing auto-encoder based face pose editing methods primarily focus on modeling the identity preserving ability during pose synthesis, but are less able to preserve the image style properly, which refers to the color, brightness, saturation, etc. In this paper, we take advantage of the well-known frontal/profile optical illusion and present a novel two-stage approach to solve the aforementioned dilemma, where the task of face pose manipulation is cast into face inpainting. By selectively sampling pixels from the input face and slightly adjust their relative locations with the proposed ``Pixel Attention Sampling" module, the face editing result faithfully keeps the identity information as well as the image style unchanged. By leveraging high-dimensional embedding at the inpainting stage, finer details are generated. Further, with the 3D facial landmarks as guidance, our method is able to manipulate face pose in three degrees of freedom, i.e., yaw, pitch, and roll, resulting in more flexible face pose editing than merely controlling the yaw angle as usually achieved by the current state-of-the-art. Both the qualitative and quantitative evaluations validate the superiority of the proposed approach.

cs.CV↗
arXiv2021

Search for Light Dark Matter-Electron Scatterings in the PandaX-II Experiment

We report constraints on light dark matter through its interactions with shell electrons in the PandaX-II liquid xenon detector with a total 46.9 tonne$\cdot$day exposure. To effectively search for these very low energy electron recoils, ionization-only signals are selected from the data. 1821 candidates are identified within ionization signal range between 50 to 75 photoelectrons, corresponding to a mean electronic recoil energy from 0.08 to 0.15 keV. The 90% C.L. exclusion limit on the scattering cross section between the dark matter and electron is calculated based on Poisson statistics. Under the assumption of point interaction, we provide the world's most stringent limit within the dark matter mass range from 15 to 30 $\rm MeV/c^2$, with the corresponding cross section from $2.5\times10^{-37}$ to $3.1\times10^{-38}$ cm$^2$.

hep-ex↗
arXiv2021

Magnifying Subtle Facial Motions for Effective 4D Expression Recognition

In this paper, an effective pipeline to automatic 4D Facial Expression Recognition (4D FER) is proposed. It combines two growing but disparate ideas in Computer Vision -- computing the spatial facial deformations using tools from Riemannian geometry and magnifying them using temporal filtering. The flow of 3D faces is first analyzed to capture the spatial deformations based on the recently-developed Riemannian approach, where registration and comparison of neighboring 3D faces are led jointly. Then, the obtained temporal evolution of these deformations are fed into a magnification method in order to amplify the facial activities over the time. The latter, main contribution of this paper, allows revealing subtle (hidden) deformations which enhance the emotion classification performance. We evaluated our approach on BU-4DFE dataset, the state-of-art 94.18% average performance and an improvement that exceeds 10% in classification accuracy, after magnifying extracted geometric features (deformations), are achieved.

cs.CV↗
arXiv2021

Determination of responses of liquid xenon to low energy electron and nuclear recoils using the PandaX-II detector

We report a systematic determination of the responses of PandaX-II, a dual phase xenon time projection chamber detector, to low energy recoils. The electron recoil (ER) and nuclear recoil (NR) responses are calibrated, respectively, with injected tritiated methane or $^{220}$Rn source, and with $^{241}$Am-Be neutron source, within an energy range from $1-25$ keV (ER) and $4-80$ keV (NR), under the two drift fields of 400 and 317 V/cm. An empirical model is used to fit the light yield and charge yield for both types of recoils. The best fit models can well describe the calibration data. The systematic uncertainties of the fitted models are obtained via statistical comparison against the data.

physics.ins-det↗
arXiv2021

Internal Calibration of the PandaX-II Detector with Radon Gaseous Sources

We have developed a low-energy electron recoil (ER) calibration method with $^{220}$Rn for the PandaX-II detector. $^{220}$Rn, emanated from natural thorium compounds, was fed into the detector through the xenon purification system. From 2017 to 2019, we performed three dedicated calibration campaigns with different radon sources. We studied the detector response to $α$, $β$, and $γ$ particles with focus on low energy ER events. During the runs in 2017 and 2018, the amount of radioactivity of $^{222}$Rn were on the order of 1\% of that of $^{220}$Rn and thorium particulate contamination was negligible, especially in 2018. We also measured the background contribution from $^{214}$Pb for the first time in PandaX-II with the help from a $^{222}$Rn injection. Calibration strategy with $^{220}$Rn and $^{222}$Rn will be implemented in the upcoming PandaX-4T experiment and can be useful for other xenon-based detectors as well.

physics.ins-det↗
arXiv2021

Results of Dark Matter Search using the Full PandaX-II Exposure

We report the dark matter search results obtained using the full 132 ton$\cdot$day exposure of the PandaX-II experiment, including all data from March 2016 to August 2018. No significant excess of events is identified above the expected background. Upper limits are set on the spin-independent dark matter-nucleon interactions. The lowest 90% confidence level exclusion on the spin-independent cross section is $2.2\times 10^{-46}$ cm$^2$ at a WIMP mass of 30 GeV/$c^2$.

astro-ph.CO↗
arXiv2020

PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection

LiDAR-based 3D object detection is an important task for autonomous driving and current approaches suffer from sparse and partial point clouds of distant and occluded objects. In this paper, we propose a novel two-stage approach, namely PC-RGNN, dealing with such challenges by two specific solutions. On the one hand, we introduce a point cloud completion module to recover high-quality proposals of dense points and entire views with original structures preserved. On the other hand, a graph neural network module is designed, which comprehensively captures relations among points through a local-global attention mechanism as well as multi-scale graph based context aggregation, substantially strengthening encoded features. Extensive experiments on the KITTI benchmark show that the proposed approach outperforms the previous state-of-the-art baselines by remarkable margins, highlighting its effectiveness.

cs.CV↗
arXiv2020

An improved design of the readout base board of the photomultiplier tube for future PandaX dark matter experiments

The PandaX project consists of a series of xenon-based experiments that are used to search for dark matter (DM) particles and to study the fundamental properties of neutrinos. The next DM experiment PandaX-4T will be using 4 ton liquid xenon in the sensitive volume, which is nearly a factor of seven larger than that of the previous experiment PandaX-II. Due to the increasing target mass, the sensitivity of searching for both DM and neutrinoless double-beta decay ($0νββ$) signals in the same detector will be significantly improved. However, the typical energy of interest for $0νββ$ signals is at the MeV scale, which is much higher than that of most popular DM signals. In the baseline readout scheme of the photomultiplier tubes (PMTs), the dynamic range is very limited. Signals from the majority of PMTs in the top array of the detector are heavily saturated at MeV energies. This deteriorates the $0νββ$ search sensitivity. In this paper we report a new design of the readout base board of the PMTs for future PandaX DM experiments and present its improved performance on the dynamic range.

physics.ins-det↗
arXiv2020

Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels

Performing controlled experiments on noisy data is essential in understanding deep learning across noise levels. Due to the lack of suitable datasets, previous research has only examined deep learning on controlled synthetic label noise, and real-world label noise has never been studied in a controlled setting. This paper makes three contributions. First, we establish the first benchmark of controlled real-world label noise from the web. This new benchmark enables us to study the web label noise in a controlled setting for the first time. The second contribution is a simple but effective method to overcome both synthetic and real noisy labels. We show that our method achieves the best result on our dataset as well as on two public benchmarks (CIFAR and WebVision). Third, we conduct the largest study by far into understanding deep neural networks trained on noisy labels across different noise levels, noise types, network architectures, and training settings. The data and code are released at the following link: http://www.lujiang.info/cnlw.html

cs.LG↗
arXiv2020

Improving Object Detection with Selective Self-supervised Self-training

We study how to leverage Web images to augment human-curated object detection datasets. Our approach is two-pronged. On the one hand, we retrieve Web images by image-to-image search, which incurs less domain shift from the curated data than other search methods. The Web images are diverse, supplying a wide variety of object poses, appearances, their interactions with the context, etc. On the other hand, we propose a novel learning method motivated by two parallel lines of work that explore unlabeled data for image classification: self-training and self-supervised learning. They fail to improve object detectors in their vanilla forms due to the domain gap between the Web images and curated datasets. To tackle this challenge, we propose a selective net to rectify the supervision signals in Web images. It not only identifies positive bounding boxes but also creates a safe zone for mining hard negative boxes. We report state-of-the-art results on detecting backpacks and chairs from everyday scenes, along with other challenging object classes.

cs.CV↗
arXiv2020

Multi-Scale Positive Sample Refinement for Few-Shot Object Detection

Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances, and is useful when manual annotation is time-consuming or data acquisition is limited. Unlike previous attempts that exploit few-shot classification techniques to facilitate FSOD, this work highlights the necessity of handling the problem of scale variations, which is challenging due to the unique sample distribution. To this end, we propose a Multi-scale Positive Sample Refinement (MPSR) approach to enrich object scales in FSOD. It generates multi-scale positive samples as object pyramids and refines the prediction at various scales. We demonstrate its advantage by integrating it as an auxiliary branch to the popular architecture of Faster R-CNN with FPN, delivering a strong FSOD solution. Several experiments are conducted on PASCAL VOC and MS COCO, and the proposed approach achieves state of the art results and significantly outperforms other counterparts, which shows its effectiveness. Code is available at https://github.com/jiaxi-wu/MPSR.

cs.CV↗
arXiv2020

ArduCode: Predictive Framework for Automation Engineering

Automation engineering is the task of integrating, via software, various sensors, actuators, and controls for automating a real-world process. Today, automation engineering is supported by a suite of software tools including integrated development environments (IDE), hardware configurators, compilers, and runtimes. These tools focus on the automation code itself, but leave the automation engineer unassisted in their decision making. This can lead to increased time for software development because of imperfections in decision making leading to multiple iterations between software and hardware. To address this, this paper defines multiple challenges often faced in automation engineering and propose solutions using machine learning to assist engineers tackle such challenges. We show that machine learning can be leveraged to assist the automation engineer in classifying automation, finding similar code snippets, and reasoning about the hardware selection of sensors and actuators. We validate our architecture on two real datasets consisting of 2,927 Arduino projects, and 683 Programmable Logic Controller (PLC) projects. Our results show that paragraph embedding techniques can be utilized to classify automation using code snippets with precision close to human annotation, giving an F1-score of 72%. Further, we show that such embedding techniques can help us find similar code snippets with high accuracy. Finally, we use autoencoder models for hardware recommendation and achieve a p@3 of 0.79 and p@5 of 0.95.

cs.SE↗
arXiv2020

Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation

Recent years have witnessed great progress in deep learning based object detection. However, due to the domain shift problem, applying off-the-shelf detectors to an unseen domain leads to significant performance drop. To address such an issue, this paper proposes a novel coarse-to-fine feature adaptation approach to cross-domain object detection. At the coarse-grained stage, different from the rough image-level or instance-level feature alignment used in the literature, foreground regions are extracted by adopting the attention mechanism, and aligned according to their marginal distributions via multi-layer adversarial learning in the common feature space. At the fine-grained stage, we conduct conditional distribution alignment of foregrounds by minimizing the distance of global prototypes with the same category but from different domains. Thanks to this coarse-to-fine feature adaptation, domain knowledge in foreground regions can be effectively transferred. Extensive experiments are carried out in various cross-domain detection scenarios. The results are state-of-the-art, which demonstrate the broad applicability and effectiveness of the proposed approach.

cs.CV↗
arXiv2020

DWM: A Decomposable Winograd Method for Convolution Acceleration

Winograd's minimal filtering algorithm has been widely used in Convolutional Neural Networks (CNNs) to reduce the number of multiplications for faster processing. However, it is only effective on convolutions with kernel size as 3x3 and stride as 1, because it suffers from significantly increased FLOPs and numerical accuracy problem for kernel size larger than 3x3 and fails on convolution with stride larger than 1. In this paper, we propose a novel Decomposable Winograd Method (DWM), which breaks through the limitation of original Winograd's minimal filtering algorithm to a wide and general convolutions. DWM decomposes kernels with large size or large stride to several small kernels with stride as 1 for further applying Winograd method, so that DWM can reduce the number of multiplications while keeping the numerical accuracy. It enables the fast exploring of larger kernel size and larger stride value in CNNs for high performance and accuracy and even the potential for new CNNs. Comparing against the original Winograd, the proposed DWM is able to support all kinds of convolutions with a speedup of ~2, without affecting the numerical accuracy.

cs.LG↗
arXiv2019

A Feasible Framework for Arbitrary-Shaped Scene Text Recognition

Deep learning based methods have achieved surprising progress in Scene Text Recognition (STR), one of classic problems in computer vision. In this paper, we propose a feasible framework for multi-lingual arbitrary-shaped STR, including instance segmentation based text detection and language model based attention mechanism for text recognition. Our STR algorithm not only recognizes Latin and Non-Latin characters, but also supports arbitrary-shaped text recognition. Our method wins the championship on Scene Text Spotting Task (Latin Only, Latin and Chinese) of ICDAR2019 Robust Reading Challenge on ArbitraryShaped Text Competition. Code is available at https://github.com/zhang0jhon/AttentionOCR.

cs.CV↗
arXiv2019

Distraction-Aware Feature Learning for Human Attribute Recognition via Coarse-to-Fine Attention Mechanism

Recently, Human Attribute Recognition (HAR) has become a hot topic due to its scientific challenges and application potentials, where localizing attributes is a crucial stage but not well handled. In this paper, we propose a novel deep learning approach to HAR, namely Distraction-aware HAR (Da-HAR). It enhances deep CNN feature learning by improving attribute localization through a coarse-to-fine attention mechanism. At the coarse step, a self-mask block is built to roughly discriminate and reduce distractions, while at the fine step, a masked attention branch is applied to further eliminate irrelevant regions. Thanks to this mechanism, feature learning is more accurate, especially when heavy occlusions and complex backgrounds exist. Extensive experiments are conducted on the WIDER-Attribute and RAP databases, and state-of-the-art results are achieved, demonstrating the effectiveness of the proposed approach.

cs.CV↗
arXiv2019

Substrate dopant induced electronic inhomogeneity in epitaxial bilayer graphene

Two-dimensional (2D) materials have become a new territory for exploring novel properties and functionalities because of their superior tunability. The unprecedented tunability of 2D materials is also accompanied by many and equally great challenges, as they are susceptible to defects and disorders. The presence of defects and disorders induces the inhomogeneity of electronic states, often making it difficult to directly probe the intrinsic properties of materials. Therefore, many efforts have been devoted to improve the electronic homogeneity, for example, by reducing the density of defects and disorders in the materials and at the interface. However, little attention is paid to the disorders embedded in underlying substrates. Here we investigate how individual dopants in substrate interact with 2D materials and give rise to the electron-hole puddles by low temperature scanning tunneling microscopy (STM) and spectroscopy (STS). Specifically, we take the epitaxial bilayer graphene grown on nitrogen doped silicon carbide (SiC) substrates as a model system, which has played the essential roles in many applications and fundamental studies. The nitrogen dopants inside SiC substrate were imaged over the epitaxial graphene by STM for the first time. The charged nitrogen dopants from the substrate induce the electron-lack puddles in graphene with a diameter of ~2 nm, via Coulomb interaction. The Fermi level with respect to the Dirac point is modulated by the puddles with an amplitude of ~40 meV, causing the electronic inhomogeneity of epitaxial graphene. Our findings on this prototype material are expected to facilitate the quality improvement of graphene and other 2D materials in general.

cond-mat.mes-hall↗