arXiv subjects

Ying Chen

Publications and source records attributed to Ying Chen.

At least 271 records · Page 15Linked to original sources

arXiv2023

Rethinking Dimensionality Reduction in Grid-based 3D Object Detection

Bird's eye view (BEV) is widely adopted by most of the current point cloud detectors due to the applicability of well-explored 2D detection techniques. However, existing methods obtain BEV features by simply collapsing voxel or point features along the height dimension, which causes the heavy loss of 3D spatial information. To alleviate the information loss, we propose a novel point cloud detection network based on a Multi-level feature dimensionality reduction strategy, called MDRNet. In MDRNet, the Spatial-aware Dimensionality Reduction (SDR) is designed to dynamically focus on the valuable parts of the object during voxel-to-BEV feature transformation. Furthermore, the Multi-level Spatial Residuals (MSR) is proposed to fuse the multi-level spatial information in the BEV feature maps. Extensive experiments on nuScenes show that the proposed method outperforms the state-of-the-art methods. The code will be available upon publication.

cs.CV↗

arXiv2023

AdaptSLAM: Edge-Assisted Adaptive SLAM with Resource Constraints via Uncertainty Minimization

Edge computing is increasingly proposed as a solution for reducing resource consumption of mobile devices running simultaneous localization and mapping (SLAM) algorithms, with most edge-assisted SLAM systems assuming the communication resources between the mobile device and the edge server to be unlimited, or relying on heuristics to choose the information to be transmitted to the edge. This paper presents AdaptSLAM, an edge-assisted visual (V) and visual-inertial (VI) SLAM system that adapts to the available communication and computation resources, based on a theoretically grounded method we developed to select the subset of keyframes (the representative frames) for constructing the best local and global maps in the mobile device and the edge server under resource constraints. We implemented AdaptSLAM to work with the state-of-the-art open-source V- and VI-SLAM ORB-SLAM3 framework, and demonstrated that, under constrained network bandwidth, AdaptSLAM reduces the tracking error by 62% compared to the best baseline method.

eess.SY↗

arXiv2022

Single-state semiquantum private comparison based on Bell states

In this paper, a novel semiquantum private comparison (SQPC) protocol based on single kind of Bell states is proposed, which allows two classical parties to judge the equality of their private inputs securely and correctly under the help of a semi-honest third party (TP) who possesses complete quantum capabilities. TP is allowed to misbehave on her own but cannot conspire with anyone else. Our protocol needs none of unitary operations, quantum entanglement swapping or the reordering operations. Moreover, our protocol only needs to prepare single kind of Bell states as initial quantum resource. Detailed security analysis turns out that our protocol is secure against various outside and participant attacks. Compared with most of the existing SQPC protocols based on Bell states, our protocol is more feasible in practice.

quant-ph↗

arXiv2022

Semiquantum secret sharing by using x-type states

In this paper, a semiquantum secret sharing (SQSS) protocol based on x-type states is proposed, which can accomplish the goal that only when two classical communicants cooperate together can they extract the shared secret key of a quantum communicant. Detailed security analysis turns out that this protocol is completely robust against an eavesdropper. This protocol has some merits: (1) it only requires one kind of quantum entangled state as the initial quantum resource; (2) it doesn't employ quantum entanglement swapping or unitary operations; and (3) it needn't share private keys among different participants beforehand.

quant-ph↗

arXiv2022

$α$-cluster decay from $^{24}$Mg resonances produced in $^{12}$C($^{16}$O,$^{24}$Mg)$α$ reaction

A transfer reaction and cluster-decay experiment, $^{12}$C($^{16}$O,$^{24}$Mg$\rightarrow$$α$+$^{20}$Ne)$α$, was performed at a beam energy of 96 MeV. Both recoil and decay $α$ particles were detected in coincidence, allowing us to deduce the energy-momentum of a $^{20}$Ne fragment. A number of resonant states of $^{24}$Mg were reconstructed up to an excitation energy of approximately 30 MeV. Owing to the experimentally achieved excellent resolutions of the $Q$-value and excitation-energy spectra, the relative decay widths for each resonant state in $^{24}$Mg to various final states of $^{20}$Ne were extracted, alone with the total decay width. The obtained results provide good testing ground for theoretical descriptions of the multiple clustering configurations in $^{24}$Mg.

nucl-ex↗

arXiv2022

Semi-Supervised Heterogeneous Graph Learning with Multi-level Data Augmentation

In recent years, semi-supervised graph learning with data augmentation (DA) is currently the most commonly used and best-performing method to enhance model robustness in sparse scenarios with few labeled samples. Differing from homogeneous graph, DA in heterogeneous graph has greater challenges: heterogeneity of information requires DA strategies to effectively handle heterogeneous relations, which considers the information contribution of different types of neighbors and edges to the target nodes. Furthermore, over-squashing of information is caused by the negative curvature that formed by the non-uniformity distribution and strong clustering in complex graph. To address these challenges, this paper presents a novel method named Semi-Supervised Heterogeneous Graph Learning with Multi-level Data Augmentation (HG-MDA). For the problem of heterogeneity of information in DA, node and topology augmentation strategies are proposed for the characteristics of heterogeneous graph. And meta-relation-based attention is applied as one of the indexes for selecting augmented nodes and edges. For the problem of over-squashing of information, triangle based edge adding and removing are designed to alleviate the negative curvature and bring the gain of topology. Finally, the loss function consists of the cross-entropy loss for labeled data and the consistency regularization for unlabeled data. In order to effectively fuse the prediction results of various DA strategies, the sharpening is used. Existing experiments on public datasets, i.e., ACM, DBLP, OGB, and industry dataset MB show that HG-MDA outperforms current SOTA models. Additionly, HG-MDA is applied to user identification in internet finance scenarios, helping the business to add 30% key users, and increase loans and balances by 3.6%, 11.1%, and 9.8%.

cs.LG↗

arXiv2022

A Dynamic Equivalent Method for PMSG-WTG Based Wind Farms Considering wind Speeds and Fault Severities

The dynamic security assessment of power systems needs to scan contingencies in a preselected set through time-domain simulations. With more and more inverter-based-generation, such as wind and solar power generation, integrated into power systems, electro-magnetic transient simulation is adopted. However, the complexity of simulation will increase greatly if inverter-based-generation units are modeled in detail. In order to reduce the complexity of simulation of power systems including large-scale wind farms, it is critical to develop dynamic equivalent methods for wind farms which are applicable to the expected contingency analysis. The dynamic response characteristics of permanent magnet synchronous generator-wind turbine generators (PMSG-WTGs) are not only influenced by their control strategies, but also by the operating wind speeds and the fault severities. Thus, this paper proposes a dynamic equivalent method for PMSG-WTG based wind farms considering the wind speeds and the fault severities. Firstly, this paper analyzes all possible response characteristics of a PMSG-WTG and proposes a clustering method based on the operating wind speed and the terminal voltage of each PMSG-WTG at the end of the fault. Then, a single-machine equivalent method is introduced for each group of PMSG-WTGs. For the group of PMSG-WTGs with active power ramp recovery process, an equivalent model with segmented ramp rate limitation for active current is designed. In order to obtain the clustering indicators, a simulation-based iterative method is put forward to calculate the voltage at point of common connection (PCC) of the wind farm, and a PMSG-WTG terminal voltage calculation method is further presented. Eventually, the efficiency and accuracy of the proposed method are verified by the simulation results.

eess.SY↗

arXiv2022

DuReader_retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine

In this paper, we present DuReader_retrieval, a large-scale Chinese dataset for passage retrieval. DuReader_retrieval contains more than 90K queries and over 8M unique passages from a commercial search engine. To alleviate the shortcomings of other datasets and ensure the quality of our benchmark, we (1) reduce the false negatives in development and test sets by manually annotating results pooled from multiple retrievers, and (2) remove the training queries that are semantically similar to the development and testing queries. Additionally, we provide two out-of-domain testing sets for cross-domain evaluation, as well as a set of human translated queries for for cross-lingual retrieval evaluation. The experiments demonstrate that DuReader_retrieval is challenging and a number of problems remain unsolved, such as the salient phrase mismatch and the syntactic mismatch between queries and paragraphs. These experiments also show that dense retrievers do not generalize well across domains, and cross-lingual retrieval is essentially challenging. DuReader_retrieval is publicly available at https://github.com/baidu/DuReader/tree/master/DuReader-Retrieval.

cs.CL↗

arXiv2022

A Fine-grained Interpretability Evaluation Benchmark for Neural NLP

While there is increasing concern about the interpretability of neural models, the evaluation of interpretability remains an open problem, due to the lack of proper evaluation datasets and metrics. In this paper, we present a novel benchmark to evaluate the interpretability of both neural models and saliency methods. This benchmark covers three representative NLP tasks: sentiment analysis, textual similarity and reading comprehension, each provided with both English and Chinese annotated data. In order to precisely evaluate the interpretability, we provide token-level rationales that are carefully annotated to be sufficient, compact and comprehensive. We also design a new metric, i.e., the consistency between the rationales before and after perturbations, to uniformly evaluate the interpretability on different types of tasks. Based on this benchmark, we conduct experiments on three typical models with three saliency methods, and unveil their strengths and weakness in terms of interpretability. We will release this benchmark https://www.luge.ai/#/luge/task/taskDetail?taskId=15 and hope it can facilitate the research in building trustworthy systems.

cs.CL↗

arXiv2022

BYHE: A Simple Framework for Boosting End-to-end Video-based Heart Rate Measurement Network

Heart rate measuring based on remote photoplethysmography (rPPG) plays an important role in health caring, which estimates heart rate from facial video in a non-contact, less-constrained way. End-to-end neural network is a main branch of rPPG-based heart rate estimation methods, whose trait is recovering rPPG signal containing sufficient heart rate message from original facial video directly. However, there exists some easily neglected problems on relevant datasets which thwarting the efficient training of end-to-end methods, such as uncertain temporal delay and indefinite envelope shape of label waves. Although many novel and powerful networks are proposed, hitherto there are no systematic research digging into these problems. In this paper, from perspective of common intrinsic rhythm periodical self-similarity results from cardiac activities, we propose a comprehensive methodology, Boost Your Heartbeat Estimation (BYHE), including new label representations, corresponding network adjustments and loss functions. BYHE can be easily grafted on current end-to-end network and boost its training efficiency. By applying our methodology, we can save tremendous time without conducting laborious handworks, such as label wave alignment which is necessary for previous end-to-end methods, and meanwhile enhance the utilization on datasets. According to our experiments, BYHE can leverage classical end-to-end network to reach competitive performance against those state-of-the-art methods on mostly used datasets. Such improvement indicates selecting perspicuous and efficient label representation is also a promising direction towards better remote physiological signal measurement.

cs.CV↗

arXiv2022

VizBelle: A Design Space of Embellishments for Data Visualization

Visual embellishments, as a form of non-linguistic rhetorical figures, are used to help convey abstract concepts or attract readers' attention. Creating data visualizations with appropriate and visually pleasing embellishments is challenging since this process largely depends on the experience and the aesthetic taste of designers. To help facilitate designers in the ideation and creation process, we propose a design space, VizBelle, based on the analysis of 361 classified visualizations from online sources. VizBelle consists of four dimensions, namely, communication goal to fit user intention, object to select the target area, strategy and technique to offer potential approaches. We further provide a website to present detailed explanations and examples of various techniques. We conducted a within-subject study with 20 professional and amateur design enthusiasts to evaluate the effectiveness of our design space. Results show that our design space is illuminating and useful for designers to create data visualizations with embellishments.

cs.HC↗

arXiv2022

Scatter Points in Space: 3D Detection from Multi-view Monocular Images

3D object detection from monocular image(s) is a challenging and long-standing problem of computer vision. To combine information from different perspectives without troublesome 2D instance tracking, recent methods tend to aggregate multiview feature by sampling regular 3D grid densely in space, which is inefficient. In this paper, we attempt to improve multi-view feature aggregation by proposing a learnable keypoints sampling method, which scatters pseudo surface points in 3D space, in order to keep data sparsity. The scattered points augmented by multi-view geometric constraints and visual features are then employed to infer objects location and shape in the scene. To make up the limitations of single frame and model multi-view geometry explicitly, we further propose a surface filter module for noise suppression. Experimental results show that our method achieves significantly better performance than previous works in terms of 3D detection (more than 0.1 AP improvement on some categories of ScanNet). The code will be publicly available.

cs.CV↗

arXiv2022

$T_{cc}^{+}(3875)$ relevant $DD^*$ scattering from $N_f=2$ lattice QCD

The $S$-wave $DD^*$ scattering in the isospin $I=0,1$ channels is studied in $N_f=2$ lattice QCD at $m_π\approx 350$ MeV. It is observed that the $DD^*$ interaction is repulsive in the $I=1$ channel when the $DD^*$ energy is near the $DD^*$ threshold. In contrast, the $DD^*$ interaction in the $I=0$ channel is definitely attractive in a wide range of the $DD^*$ energy. This is consistent with the isospin assignment $I=0$ for $T_{cc}^+(3875)$. By analyzing the components of the $DD^*$ correlation functions, it turns out that the quark diagram responsible for the different properties of $I=0,1$ $DD^*$ interactions can be understood as the charged $ρ$ meson exchange effect. This observation provides direct information on the internal dynamics of $T_{cc}^+(3875)$.

hep-lat↗

arXiv2022

Single-state multi-party semiquantum key agreement protocol based on multi-particle GHZ entangled states

In this paper, we put forward a novel single-state three-party semiquantum key agreement (SQKA) protocol with three-particle GHZ entangled states first. Different with previous quantum key agreement (QKA) protocols, the proposed single-state three-party SQKA protocol can realize the goal that a quantum party and two classical parties who only possess limited quantum capabilities equally contribute to the generation of a shared private key over quantum channels. Detailed security analysis turns out that the proposed single-state three-party SQKA protocol is secure against several famous attacks from an outside eavesdropper, such as the Trojan horse attack, the entangle-measure attack, the measure-resend attack and the intercept-resend attack. Moreover, it can resist the participant attack, which means that the shared private key cannot be determined fully by any nontrivial subset of three parties. The proposed single-state three-party SQKA protocol has the following nice features: (1) it only employs one kind of three-particle GHZ entangled states as initial quantum resource; (2) it doesn't need pre-shared keys among different parties; (3) it doesn't need unitary operations or quantum entanglement swapping. Finally, we generalize the proposed single-state three-party SQKA protocol into the case of N-party by only employing one kind of N-particle GHZ entangled states as initial quantum resource, which inherits the nice features of its three-party counterpart.

quant-ph↗

arXiv2022

An Interpretability Evaluation Benchmark for Pre-trained Language Models

While pre-trained language models (LMs) have brought great improvements in many NLP tasks, there is increasing attention to explore capabilities of LMs and interpret their predictions. However, existing works usually focus only on a certain capability with some downstream tasks. There is a lack of datasets for directly evaluating the masked word prediction performance and the interpretability of pre-trained LMs. To fill in the gap, we propose a novel evaluation benchmark providing with both English and Chinese annotated data. It tests LMs abilities in multiple dimensions, i.e., grammar, semantics, knowledge, reasoning and computation. In addition, it provides carefully annotated token-level rationales that satisfy sufficiency and compactness. It contains perturbed instances for each original instance, so as to use the rationale consistency under perturbations as the metric for faithfulness, a perspective of interpretability. We conduct experiments on several widely-used pre-trained LMs. The results show that they perform very poorly on the dimensions of knowledge and computation. And their plausibility in all dimensions is far from satisfactory, especially when the rationale is short. In addition, the pre-trained LMs we evaluated are not robust on syntax-aware data. We will release this evaluation benchmark at \url{http://xyz}, and hope it can facilitate the research progress of pre-trained LMs.

cs.CL↗

arXiv2022

SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement

Image-adaptive lookup tables (LUTs) have achieved great success in real-time image enhancement tasks due to their high efficiency for modeling color transforms. However, they embed the complete transform, including the color component-independent and the component-correlated parts, into only a single type of LUTs, either 1D or 3D, in a coupled manner. This scheme raises a dilemma of improving model expressiveness or efficiency due to two factors. On the one hand, the 1D LUTs provide high computational efficiency but lack the critical capability of color components interaction. On the other, the 3D LUTs present enhanced component-correlated transform capability but suffer from heavy memory footprint, high training difficulty, and limited cell utilization. Inspired by the conventional divide-and-conquer practice in the image signal processor, we present SepLUT (separable image-adaptive lookup table) to tackle the above limitations. Specifically, we separate a single color transform into a cascade of component-independent and component-correlated sub-transforms instantiated as 1D and 3D LUTs, respectively. In this way, the capabilities of two sub-transforms can facilitate each other, where the 3D LUT complements the ability to mix up color components, and the 1D LUT redistributes the input colors to increase the cell utilization of the 3D LUT and thus enable the use of a more lightweight 3D LUT. Experiments demonstrate that the proposed method presents enhanced performance on photo retouching benchmark datasets than the current state-of-the-art and achieves real-time processing on both GPUs and CPUs.

cs.CV↗

arXiv2022

Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting

End-to-end text spotting has attached great attention recently due to its benefits on global optimization and high maintainability for real applications. However, the input scale has always been a tough trade-off since recognizing a small text instance usually requires enlarging the whole image, which brings high computational costs. In this paper, to address this problem, we propose a novel cost-efficient Dynamic Low-resolution Distillation (DLD) text spotting framework, which aims to infer images in different small but recognizable resolutions and achieve a better balance between accuracy and efficiency. Concretely, we adopt a resolution selector to dynamically decide the input resolutions for different images, which is constraint by both inference accuracy and computational cost. Another sequential knowledge distillation strategy is conducted on the text recognition branch, making the low-res input obtains comparable performance to a high-res image. The proposed method can be optimized end-to-end and adopted in any current text spotting framework to improve the practicability. Extensive experiments on several text spotting benchmarks show that the proposed method vastly improves the usability of low-res models. The code is available at https://github.com/hikopensource/DAVAR-Lab-OCR/.

cs.CV↗

arXiv2022

DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding

This paper presents DavarOCR, an open-source toolbox for OCR and document understanding tasks. DavarOCR currently implements 19 advanced algorithms, covering 9 different task forms. DavarOCR provides detailed usage instructions and the trained models for each algorithm. Compared with the previous opensource OCR toolbox, DavarOCR has relatively more complete support for the sub-tasks of the cutting-edge technology of document understanding. In order to promote the development and application of OCR technology in academia and industry, we pay more attention to the use of modules that different sub-domains of technology can share. DavarOCR is publicly released at https://github.com/hikopensource/Davar-Lab-OCR.

cs.CV↗