arXiv subjects

Hao Chen

Publications and source records attributed to Hao Chen.

At least 1,081 records · Page 60Linked to original sources

arXiv2023

AIDA: Legal Judgment Predictions for Non-Professional Fact Descriptions via Partial-and-Imbalanced Domain Adaptation

In this paper, we study the problem of legal domain adaptation problem from an imbalanced source domain to a partial target domain. The task aims to improve legal judgment predictions for non-professional fact descriptions. We formulate this task as a partial-and-imbalanced domain adaptation problem. Though deep domain adaptation has achieved cutting-edge performance in many unsupervised domain adaptation tasks. However, due to the negative transfer of samples in non-shared classes, it is hard for current domain adaptation model to solve the partial-and-imbalanced transfer problem. In this work, we explore large-scale non-shared but related classes data in the source domain with a hierarchy weighting adaptation to tackle this limitation. We propose to embed a novel pArtial Imbalanced Domain Adaptation technique (AIDA) in the deep learning model, which can jointly borrow sibling knowledge from non-shared classes to shared classes in the source domain and further transfer the shared classes knowledge from the source domain to the target domain. Experimental results show that our model outperforms the state-of-the-art algorithms.

cs.CL↗

arXiv2023

Squeeze Training for Adversarial Robustness

The vulnerability of deep neural networks (DNNs) to adversarial examples has attracted great attention in the machine learning community. The problem is related to non-flatness and non-smoothness of normally obtained loss landscapes. Training augmented with adversarial examples (a.k.a., adversarial training) is considered as an effective remedy. In this paper, we highlight that some collaborative examples, nearly perceptually indistinguishable from both adversarial and benign examples yet show extremely lower prediction loss, can be utilized to enhance adversarial training. A novel method is therefore proposed to achieve new state-of-the-arts in adversarial robustness. Code: https://github.com/qizhangli/ST-AT.

cs.LG↗

arXiv2023

Identifying Hadronic Molecular States with a Neural Network

Neural networks are trained to judge whether or not an exotic state is a hadronic molecule of a given channel according its line-shapes. This method performs well in both trainings and validation tests. As applications, it is applied to study $X(3872)$, $X(4260)$ and $Z_c(3900)$. The results show that $Z_c(3900)$ should be regarded as a $\bar{D}^* D$ molecular state but $X(3872)$ not. As for $X(4260)$, it can not be a molecular state of $χ_{c0}ω$. Some discussions on $X_1(2900)$ are also provided.

hep-ph↗

arXiv2023

FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning

Semi-supervised Learning (SSL) has witnessed great success owing to the impressive performances brought by various methods based on pseudo labeling and consistency regularization. However, we argue that existing methods might fail to utilize the unlabeled data more effectively since they either use a pre-defined / fixed threshold or an ad-hoc threshold adjusting scheme, resulting in inferior performance and slow convergence. We first analyze a motivating example to obtain intuitions on the relationship between the desirable threshold and model's learning status. Based on the analysis, we hence propose FreeMatch to adjust the confidence threshold in a self-adaptive manner according to the model's learning status. We further introduce a self-adaptive class fairness regularization penalty to encourage the model for diverse predictions during the early training stage. Extensive experiments indicate the superiority of FreeMatch especially when the labeled data are extremely rare. FreeMatch achieves 5.78%, 13.59%, and 1.28% error rate reduction over the latest state-of-the-art method FlexMatch on CIFAR-10 with 1 label per class, STL-10 with 4 labels per class, and ImageNet with 100 labels per class, respectively. Moreover, FreeMatch can also boost the performance of imbalanced SSL. The codes can be found at https://github.com/microsoft/Semi-supervised-learning.

cs.LG↗

arXiv2023

Significant Light Extraction and Power Efficiency Enhancement of Organic Light Emitting Diodes by Subwavelength Dielectric-Nanomesh Using Large-area Nanoimprint

To improve the power efficiency of light emitting diodes (OLEDs), we developed a novel OLED structure, termed Dielectric-Nanomesh OLED (DNM-OLED), fabricated by large-area nanoimprint lithography (NIL). A dielectric-nanomesh substrate with a subwavelength nanomesh grating patterned into glass releases the photons trapped in ITO and organic layers by guided modes into leaky modes. And the dielectric-nanomesh substrate modifies the entire OLED layers into a corrugated configuration, which further lowers the parasitic resistance and hence the operating voltage. For a red phosphorescent OLED in our demonstration, with the DNM-OLED structure, the light extraction efficiency was enhanced by 1.33 fold and the operating voltage was lowered by 46%, acting together, leading to a 1.8-fold enhancement in power efficiency. Besides red OELDs, the DNM-OLED structure was also shown to be able to work for green and blue OELDs and achieved enhanced light extraction efficiency (1.31 fold for green light, 1.45 fold for blue light) without further structure modification, which demonstrated the light extraction enhancement by the DNM-OLED is broadband.

physics.optics↗

arXiv2023

Over 100% Light Extraction Enhancement of Organic Light Emitting Diodes Using Flat Moire Micro-Lens Array Fabricated by Double Nanoimprint Lithography Over a Large Area

To improve the light extraction efficiency of organic light emitting diodes (OLEDs), we developed a novel substrate, i.e., a metamaterial based flat Moire micro-lens array formed using double nanoimprint, termed Mlens-array, consisting of a hexagonal moiré pattern pillar array. By choosing a low refractive index dielectric material for the pillar array and a high refractive index dielectric material for the layer capped on top of the pillar array, we fabricated the Mlens-array behaving as a conventional convex optical micro-lens array. The Mlens-array was fabricated on a 4-inch wafer-size glass substrate by double-cycle compositional nanoimprint lithography (NIL) which is easy for achieving high throughput fabrication in large-scale. Applying the Mlens-array substrate in a typical green-emitting OLED, the light extraction efficiency was enhanced by over 100% (2.08-fold) compared to a control device fabricated on the conventional planar glass substrate.

physics.optics↗

arXiv2023

Enhancing Light Extraction of Organic Light Emitting Diodes by Deep-Groove High-index Dielectric Nanomesh Using Large-area Nanoimprint

To solve the conventional conflict between maintaining good charge transport property and achieving high light extraction efficiency when using micro/nanostructure patterned substrates to extract light from organic light emitting diodes (OLEDs), we developed a novel OLED structure, termed High-index Deep-Groove Dielectric Nanomesh OLED (HDNM-OLED), fabricated by large-area nanoimprint lithography (NIL). The key component is a nanostructure-patterned substrate embedded with a high-index deep-groove nanomesh and capped with a low-index planarization layer. The high-index and deep-groove nanomesh efficiently releases the tapped photons to achieve significantly enhanced light extraction. And the planarization layer helps to maintain the good charge transport property of the organic active layers deposited on top of it. For a green phosphorescent OLED in our demonstration, with the HDNM-OLED structure, compared to planar conventional ITO-OLED structure, the external quantum efficiency (EQE) was enhanced by 1.85-fold from 26% to 48% and power efficiency was enhanced by 1.86-fold from 42lm/W to 79lm/W. Besides green OELDs, the HDNM-OLED structure was also shown to be able to work for red and blue-emitting OELDs and achieved enhanced light extraction efficiency (1.58-fold for red light, 1.86-fold for blue light) without further structure modification, which demonstrated the light extraction enhancement by the HDNM-OLED is broadband.

physics.optics↗

arXiv2023

Dynamic Point Cloud Geometry Compression Using Multiscale Inter Conditional Coding

This work extends the Multiscale Sparse Representation (MSR) framework developed for static Point Cloud Geometry Compression (PCGC) to support the dynamic PCGC through the use of multiscale inter conditional coding. To this end, the reconstruction of the preceding Point Cloud Geometry (PCG) frame is progressively downscaled to generate multiscale temporal priors which are then scale-wise transferred and integrated with lower-scale spatial priors from the same frame to form the contextual information to improve occupancy probability approximation when processing the current PCG frame from one scale to another. Following the Common Test Conditions (CTC) defined in the standardization committee, the proposed method presents State-Of-The-Art (SOTA) compression performance, yielding 78% lossy BD-Rate gain to the latest standard-compliant V-PCC and 45% lossless bitrate reduction to the latest G-PCC. Even for recently-emerged learning-based solutions, our method still shows significant performance gains.

cs.CV↗

arXiv2023

Generalized Singleton Type Upper Bounds

In this paper, we give upper bounds on the sizes of $(d, L)$ list-decodable codes in the Hamming metric space from covering codes with the covering radius smaller than or equal to $d$. When the list size $L$ is $1$, this gives many new Singleton type upper bounds on the sizes of codes with a given minimum Hamming distance. These upper bounds are stronger than the Griesmer bound when the lengths of codes are large. Some upper bounds on the lengths of general small Singleton defect codes or list-decodable codes attaining the generalized Singleton bound are given. As an application of our generalized Singleton type upper bounds on Hamming metric error-correcting codes, the generalized Singleton type upper bounds on insertion-deletion codes are given, which are much stronger than the direct Singleton bound for insertion-deletion codes when the lengths are large. We also give upper bounds on the lengths of small dimension optimal locally recoverable codes and small dimension optimal $(r, δ)$ locally recoverable codes with any fixed given minimum distance.

cs.IT↗

arXiv2023

Power Corrections to Energy Flow Correlations from Large Spin Perturbation

Dynamics of high energy scattering in Quantum Chromodynamics (QCD) are primarily probed through detector energy flow correlations. One important example is the Energy-Energy Correlator (EEC), whose back-to-back limit probes correlations of QCD on the lightcone and can be described by a transverse-momentum dependent factorization formula in the leading power approximation. In this work, we develop a systematic method to go beyond this approximation. We identify the origin of logarithmically enhanced contributions in the back-to-back limit as the exchange of operators with low twists and large spins in the local operator product expansion. Using techniques from the conformal bootstrap, the large logarithms beyond leading power can be resummed to all orders in the perturbative coupling. As an illustration of this method, we perform an all-order resummation of the leading and next-to-leading logarithms beyond the leading power in ${\cal N} = 4$ Super Yang-Mills theory.

hep-ph↗

arXiv2023

Practical and powerful kernel-based change-point detection

Change-point analysis plays a significant role in various fields to reveal discrepancies in distribution in a sequence of observations. While a number of algorithms have been proposed for high-dimensional data, kernel-based methods have not been well explored due to difficulties in controlling false discoveries and mediocre performance. In this paper, we propose a new kernel-based framework that makes use of an important pattern of data in high dimensions to boost power. Analytic approximations to the significance of the new statistics are derived and fast tests based on the asymptotic results are proposed, offering easy off-the-shelf tools for large datasets. The new tests show superior performance for a wide range of alternatives when compared with other state-of-the-art methods. We illustrate these new approaches through an analysis of a phone-call network data. All proposed methods are implemented in an R package KerSeg.

stat.ME↗

arXiv2023

Automatically Prepare Training Data for YOLO Using Robotic In-Hand Observation and Synthesis

Deep learning methods have recently exhibited impressive performance in object detection. However, such methods needed much training data to achieve high recognition accuracy, which was time-consuming and required considerable manual work like labeling images. In this paper, we automatically prepare training data using robots. Considering the low efficiency and high energy consumption in robot motion, we proposed combining robotic in-hand observation and data synthesis to enlarge the limited data set collected by the robot. We first used a robot with a depth sensor to collect images of objects held in the robot's hands and segment the object pictures. Then, we used a copy-paste method to synthesize the segmented objects with rack backgrounds. The collected and synthetic images are combined to train a deep detection neural network. We conducted experiments to compare YOLOv5x detectors trained with images collected using the proposed method and several other methods. The results showed that combined observation and synthetic images led to comparable performance to manual data preparation. They provided a good guide on optimizing data configurations and parameter settings for training detectors. The proposed method required only a single process and was a low-cost way to produce the combined data. Interested readers may find the data sets and trained models from the following GitHub repository: github.com/wrslab/tubedet

cs.CV↗

arXiv2023

Transformer in Transformer as Backbone for Deep Reinforcement Learning

Designing better deep networks and better reinforcement learning (RL) algorithms are both important for deep RL. This work focuses on the former. Previous methods build the network with several modules like CNN, LSTM and Attention. Recent methods combine the Transformer with these modules for better performance. However, it requires tedious optimization skills to train a network composed of mixed modules, making these methods inconvenient to be used in practice. In this paper, we propose to design \emph{pure Transformer-based networks} for deep RL, aiming at providing off-the-shelf backbones for both the online and offline settings. Specifically, the Transformer in Transformer (TIT) backbone is proposed, which cascades two Transformers in a very natural way: the inner one is used to process a single observation, while the outer one is responsible for processing the observation history; combining both is expected to extract spatial-temporal representations for good decision-making. Experiments show that TIT can achieve satisfactory performance in different settings consistently.

cs.LG↗

arXiv2023

Study of the $ω$/$ω_3$, $ρ$/$ρ_3$ and the newly observed $ω$-like state $X(2220)$

We study the excited states of $ω$ and $ω_3$ by comparison with the $ρ$ and $ρ_3$ families, and discuss the possibility of $X(2220)$ as $ω$ excitation by analyzing the mass spectra and strong decay behaviors. In addition, we predict the masses and widths of $ω(2D)$ and $ω_3$and $ρ_3(4D)$, $ρ_3(1G)$, $ω_3$ and $ρ_3(2G)$ and $ω_3(3G)$ and $ρ_3(3G)$. The abundant information of their two-body strong decays predicted in this work will be helpful to further study of these $ω$ and $ω_3$ and $ρ$ and $ρ_3$ states in experiment and theory.

hep-ph↗

arXiv2023

Learning Invariance from Generated Variance for Unsupervised Person Re-identification

This work focuses on unsupervised representation learning in person re-identification (ReID). Recent self-supervised contrastive learning methods learn invariance by maximizing the representation similarity between two augmented views of a same image. However, traditional data augmentation may bring to the fore undesirable distortions on identity features, which is not always favorable in id-sensitive ReID tasks. In this paper, we propose to replace traditional data augmentation with a generative adversarial network (GAN) that is targeted to generate augmented views for contrastive learning. A 3D mesh guided person image generator is proposed to disentangle a person image into id-related and id-unrelated features. Deviating from previous GAN-based ReID methods that only work in id-unrelated space (pose and camera style), we conduct GAN-based augmentation on both id-unrelated and id-related features. We further propose specific contrastive losses to help our network learn invariance from id-unrelated and id-related augmentations. By jointly training the generative and the contrastive modules, our method achieves new state-of-the-art unsupervised person ReID performance on mainstream large-scale benchmarks.

cs.CV↗

arXiv2022

Deep Multimodal Fusion for Generalizable Person Re-identification

Person re-identification plays a significant role in realistic scenarios due to its various applications in public security and video surveillance. Recently, leveraging the supervised or semi-unsupervised learning paradigms, which benefits from the large-scale datasets and strong computing performance, has achieved a competitive performance on a specific target domain. However, when Re-ID models are directly deployed in a new domain without target samples, they always suffer from considerable performance degradation and poor domain generalization. To address this challenge, we propose a Deep Multimodal Fusion network to elaborate rich semantic knowledge for assisting in representation learning during the pre-training. Importantly, a multimodal fusion strategy is introduced to translate the features of different modalities into the common space, which can significantly boost generalization capability of Re-ID model. As for the fine-tuning stage, a realistic dataset is adopted to fine-tune the pre-trained model for better distribution alignment with real-world data. Comprehensive experiments on benchmarks demonstrate that our method can significantly outperform previous domain generalization or meta-learning methods with a clear margin. Our source code will also be publicly available at https://github.com/JeremyXSC/DMF.

cs.CV↗

arXiv2022

Data-Driven Transferred Energy Management Strategy for Hybrid Electric Vehicles via Deep Reinforcement Learning

Real-time applications of energy management strategies (EMSs) in hybrid electric vehicles (HEVs) are the harshest requirements for researchers and engineers. Inspired by the excellent problem-solving capabilities of deep reinforcement learning (DRL), this paper proposes a real-time EMS via incorporating the DRL method and transfer learning (TL). The related EMSs are derived from and evaluated on the real-world collected driving cycle dataset from Transportation Secure Data Center (TSDC). The concrete DRL algorithm is proximal policy optimization (PPO) belonging to the policy gradient (PG) techniques. For specification, many source driving cycles are utilized for training the parameters of deep network based on PPO. The learned parameters are transformed into the target driving cycles under the TL framework. The EMSs related to the target driving cycles are estimated and compared in different training conditions. Simulation results indicate that the presented transfer DRL-based EMS could effectively reduce time consumption and guarantee control performance.

eess.SP↗

arXiv2022

Observation of Flat Band, Dirac Nodal Lines and Topological Surface States in Kagome Superconductor CsTi$_3$Bi$_5$

A kagome lattice of 3d transition metals hosts flat bands, Dirac fermions and saddle points. It provides a versatile platform for achieving topological superconductivity, anomalous Hall effect, unconventional density wave order and quantum spin liquid when the strong correlation, spin-orbit coupling or magnetic order are involved in such a lattice. Here, using laser-based angle-resolved photoemission spectroscopy in combination with density functional theory calculations, we investigate the electronic structure of the newly discovered kagome superconductor CsTi$_3$Bi$_5$, which is isostructural to the AV$_3$Sb$_5$ (A=K, Rb or Cs) kagome superconductors and possesses a perfect two-dimensional kagome network of Titanium. We directly observed a strikingly flat band derived from the local destructive interferences of Bloch wave functions within the kagome lattices. We also identify the type-II Dirac nodal loops around the Brillouin zone center, the type-III Dirac nodal loops around the zone corners and type-III Dirac nodal lines along the k$_z$ direction. In addition, around the Brillouin zone center, Z2 nontrivial topological surface states are also observed which is formed from the band inversion due to strong spin orbital coupling. The simultaneous existence of such multi-sets of nontrivial band structures in one kagome superconductor not only provides good opportunities to study related physics in the kagome lattice but also makes CsTi$_3$Bi$_5$ an ideal system to realize noval quantum phenomena by manipulating its chemical potential with chemical doping or pressure.

cond-mat.supr-con↗