arXiv subjects

Zhenyu Chen

Publications and source records attributed to Zhenyu Chen.

At least 145 records · Page 8Linked to original sources

arXiv2023

Benchmarking Robustness of AI-Enabled Multi-sensor Fusion Systems: Challenges and Opportunities

Multi-Sensor Fusion (MSF) based perception systems have been the foundation in supporting many industrial applications and domains, such as self-driving cars, robotic arms, and unmanned aerial vehicles. Over the past few years, the fast progress in data-driven artificial intelligence (AI) has brought a fast-increasing trend to empower MSF systems by deep learning techniques to further improve performance, especially on intelligent systems and their perception systems. Although quite a few AI-enabled MSF perception systems and techniques have been proposed, up to the present, limited benchmarks that focus on MSF perception are publicly available. Given that many intelligent systems such as self-driving cars are operated in safety-critical contexts where perception systems play an important role, there comes an urgent need for a more in-depth understanding of the performance and reliability of these MSF systems. To bridge this gap, we initiate an early step in this direction and construct a public benchmark of AI-enabled MSF-based perception systems including three commonly adopted tasks (i.e., object detection, object tracking, and depth completion). Based on this, to comprehensively understand MSF systems' robustness and reliability, we design 14 common and realistic corruption patterns to synthesize large-scale corrupted datasets. We further perform a systematic evaluation of these systems through our large-scale evaluation. Our results reveal the vulnerability of the current AI-enabled MSF perception systems, calling for researchers and practitioners to take robustness and reliability into account when designing AI-enabled MSF.

cs.SE↗

arXiv2023

Pre-trained Model-based Automated Software Vulnerability Repair: How Far are We?

Various approaches are proposed to help under-resourced security researchers to detect and analyze software vulnerabilities. It is still incredibly time-consuming and labor-intensive for security researchers to fix vulnerabilities. The time lag between reporting and fixing a vulnerability causes software systems to suffer from significant exposure to possible attacks. Recently, some techniques have proposed applying pre-trained models to fix security vulnerabilities and have proved their success in improving repair accuracy. However, the effectiveness of existing pre-trained models has not been systematically analyzed, and little is known about their advantages and disadvantages. To bridge this gap, we perform the first extensive study on applying various pre-trained models to vulnerability repair. The results show that studied pre-trained models consistently outperform the state-of-the-art technique VRepair with a prediction accuracy of 32.94%~44.96%. We also investigate the impact of major phases in the vulnerability repair workflow. Surprisingly, a simplistic approach adopting transfer learning improves the prediction accuracy of pre-trained models by 9.40% on average. Besides, we provide additional discussion to illustrate the capacity and limitations of pre-trained models. Finally, we further pinpoint various practical guidelines for advancing pre-trained model-based vulnerability repair. Our study highlights the promising future of adopting pre-trained models to patch real-world vulnerabilities.

cs.SE↗

arXiv2023

Tracking Anything in High Quality

Visual object tracking is a fundamental video task in computer vision. Recently, the notably increasing power of perception algorithms allows the unification of single/multiobject and box/mask-based tracking. Among them, the Segment Anything Model (SAM) attracts much attention. In this report, we propose HQTrack, a framework for High Quality Tracking anything in videos. HQTrack mainly consists of a video multi-object segmenter (VMOS) and a mask refiner (MR). Given the object to be tracked in the initial frame of a video, VMOS propagates the object masks to the current frame. The mask results at this stage are not accurate enough since VMOS is trained on several closeset video object segmentation (VOS) datasets, which has limited ability to generalize to complex and corner scenes. To further improve the quality of tracking masks, a pretrained MR model is employed to refine the tracking results. As a compelling testament to the effectiveness of our paradigm, without employing any tricks such as test-time data augmentations and model ensemble, HQTrack ranks the 2nd place in the Visual Object Tracking and Segmentation (VOTS2023) challenge. Code and models are available at https://github.com/jiawen-zhu/HQTrack.

cs.CV↗

arXiv2023

Impact of nuclear structure on longitudinal flow decorrelations in high-energy isobar collisions

Fluctuations of harmonic flow along pseudorapidity, known as flow decorrelations, are an important probe of the initial state geometry of the quark-gluon plasma. The flow decorrelations are shown to be sensitive to the collective structure of the colliding nuclei, as revealed clearly by comparing collisions of isobars, $^{96}$Ru+$^{96}$Ru and $^{96}$Zr+$^{96}$Zr, which have different nuclear structures. The flow decorrelations in central collisions are mostly sensitive to nuclear deformations, while those in the mid-central collisions are primarily sensitive to differences in skin thickness between $^{96}$Ru and $^{96}$Zr. Longitudinal flow decorrelations in heavy-ion collisions are a new tool to probe the structure of colliding nuclei.

nucl-th↗

arXiv2023

Impact of nuclear structure on longitudinal flow decorrelations in high-energy isobar collisions

nucl-th↗

arXiv2023

Mobile App Crowdsourced Test Report Consistency Detection via Deep Image-and-Text Fusion Understanding

Crowdsourced testing, as a distinct testing paradigm, has attracted much attention in software testing, especially in mobile application (app) testing field. Compared with in-house testing, crowdsourced testing shows superiority with the diverse testing environments when faced with the mobile testing fragmentation problem. However, crowdsourced testing also encounters the low-quality test report problem caused by unprofessional crowdworkers involved with different expertise. In order to handle the submitted reports of uneven quality, app developers have to distinguish high-quality reports from low-quality ones to help the bug inspection. One kind of typical low-quality test report is inconsistent test reports, which means the textual descriptions are not focusing on the attached bug-occurring screenshots. According to our empirical survey, only 18.07% crowdsourced test reports are consistent. Inconsistent reports cause waste on mobile app testing. To solve the inconsistency problem, we propose ReCoDe to detect the consistency of crowdsourced test reports via deep image-and-text fusion understanding. ReCoDe is a two-stage approach that first classifies the reports based on textual descriptions into different categories according to the bug feature. In the second stage, ReCoDe has a deep understanding of the GUI image features of the app screenshots and then applies different strategies to handle different types of bugs to detect the consistency of the crowdsourced test reports. We conduct an experiment on a dataset with over 22k test reports to evaluate ReCoDe, and the results show the effectiveness of ReCoDe in detecting the consistency of crowdsourced test reports. Besides, a user study is conducted to prove the practical value of ReCoDe in effectively helping app developers improve the efficiency of reviewing the crowdsourced test reports.

cs.SE↗

arXiv2023

3rd Place Solution for PVUW2023 VSS Track: A Large Model for Semantic Segmentation on VSPW

In this paper, we introduce 3rd place solution for PVUW2023 VSS track. Semantic segmentation is a fundamental task in computer vision with numerous real-world applications. We have explored various image-level visual backbones and segmentation heads to tackle the problem of video semantic segmentation. Through our experimentation, we find that InternImage-H as the backbone and Mask2former as the segmentation head achieves the best performance. In addition, we explore two post-precessing methods: CascadePSP and Segment Anything Model (SAM). Ultimately, our approach obtains 62.60\% and 64.84\% mIoU on the VSPW test set1 and final test set, respectively, securing the third position in the PVUW2023 VSS track.

cs.CV↗

arXiv2023

Automatic Code Summarization via ChatGPT: How Far Are We?

To support software developers in understanding and maintaining programs, various automatic code summarization techniques have been proposed to generate a concise natural language comment for a given code snippet. Recently, the emergence of large language models (LLMs) has led to a great boost in the performance of natural language processing tasks. Among them, ChatGPT is the most popular one which has attracted wide attention from the software engineering community. However, it still remains unclear how ChatGPT performs in (automatic) code summarization. Therefore, in this paper, we focus on evaluating ChatGPT on a widely-used Python dataset called CSN-Python and comparing it with several state-of-the-art (SOTA) code summarization models. Specifically, we first explore an appropriate prompt to guide ChatGPT to generate in-distribution comments. Then, we use such a prompt to ask ChatGPT to generate comments for all code snippets in the CSN-Python test set. We adopt three widely-used metrics (including BLEU, METEOR, and ROUGE-L) to measure the quality of the comments generated by ChatGPT and SOTA models (including NCS, CodeBERT, and CodeT5). The experimental results show that in terms of BLEU and ROUGE-L, ChatGPT's code summarization performance is significantly worse than all three SOTA models. We also present some cases and discuss the advantages and disadvantages of ChatGPT in code summarization. Based on the findings, we outline several open challenges and opportunities in ChatGPT-based code summarization.

cs.SE↗

arXiv2023

Local-to-Global Panorama Inpainting for Locale-Aware Indoor Lighting Prediction

Predicting panoramic indoor lighting from a single perspective image is a fundamental but highly ill-posed problem in computer vision and graphics. To achieve locale-aware and robust prediction, this problem can be decomposed into three sub-tasks: depth-based image warping, panorama inpainting and high-dynamic-range (HDR) reconstruction, among which the success of panorama inpainting plays a key role. Recent methods mostly rely on convolutional neural networks (CNNs) to fill the missing contents in the warped panorama. However, they usually achieve suboptimal performance since the missing contents occupy a very large portion in the panoramic space while CNNs are plagued by limited receptive fields. The spatially-varying distortion in the spherical signals further increases the difficulty for conventional CNNs. To address these issues, we propose a local-to-global strategy for large-scale panorama inpainting. In our method, a depth-guided local inpainting is first applied on the warped panorama to fill small but dense holes. Then, a transformer-based network, dubbed PanoTransformer, is designed to hallucinate reasonable global structures in the large holes. To avoid distortion, we further employ cubemap projection in our design of PanoTransformer. The high-quality panorama recovered at any locale helps us to capture spatially-varying indoor illumination with physically-plausible global structures and fine details.

cs.CV↗

arXiv2022

Certifying Unknown Genuine Multipartite Entanglement by Neural Networks

Suppose we have an unknown multipartite quantum state, how can we experimentally find out whether it is genuine multipartite entangled or not? Recall that even for a bipartite quantum state whose density matrix is known, it is already NP-Hard to determine whether it is entangled or not. Therefore, it is hard to efficiently solve the above problem generally. However, since genuine multipartite entanglement is such a fundamental concept that plays a crucial role in many-body physics and quantum information processing tasks, finding realistic approaches to certify genuine multipartite entanglement is undoubtedly necessary. In this work, we show that neural networks can provide a nice solution to this problem, where measurement statistics data produced by measuring involved quantum states with local measurement devices serve as input features of neural networks. By testing our models on many specific multipartite quantum states, we show that they can certify genuine multipartite entanglement very accurately, which even include some new results unknown before. We also exhibit a possible way to improve the efficiency of our models by reducing the size of features. Lastly, we show that our models enjoy remarkable robustness against flaws in measurement devices, implying that they are very experiment-friendly.

quant-ph↗

arXiv2022

Selectively Combining Multiple Coverage Goals in Search-Based Unit Test Generation

Unit testing is a critical part of software development process, ensuring the correctness of basic programming units in a program (e.g., a method). Search-based software testing (SBST) is an automated approach to generating test cases. SBST generates test cases with genetic algorithms by specifying the coverage criterion (e.g., branch coverage). However, a good test suite must have different properties, which cannot be captured by using an individual coverage criterion. Therefore, the state-of-the-art approach combines multiple criteria to generate test cases. As combining multiple coverage criteria brings multiple objectives for optimization, it hurts the test suites' coverage for certain criteria compared with using the single criterion. To cope with this problem, we propose a novel approach named \textbf{smart selection}. Based on the coverage correlations among criteria and the coverage goals' subsumption relationships, smart selection selects a subset of coverage goals to reduce the number of optimization objectives and avoid missing any properties of all criteria. We conduct experiments to evaluate smart selection on $400$ Java classes with three state-of-the-art genetic algorithms. On average, smart selection outperforms combining all goals on $65.1\%$ of the classes having significant differences between the two approaches.

cs.SE↗

arXiv2022

PSP: Million-level Protein Sequence Dataset for Protein Structure Prediction

Proteins are essential component of human life and their structures are important for function and mechanism analysis. Recent work has shown the potential of AI-driven methods for protein structure prediction. However, the development of new models is restricted by the lack of dataset and benchmark training procedure. To the best of our knowledge, the existing open source datasets are far less to satisfy the needs of modern protein sequence-structure related research. To solve this problem, we present the first million-level protein structure prediction dataset with high coverage and diversity, named as PSP. This dataset consists of 570k true structure sequences (10TB) and 745k complementary distillation sequences (15TB). We provide in addition the benchmark training procedure for SOTA protein structure prediction model on this dataset. We validate the utility of this dataset for training by participating CAMEO contest in which our model won the first place. We hope our PSP dataset together with the training benchmark can enable a broader community of AI/biology researchers for AI-driven protein related research.

q-bio.BM↗

arXiv2022

Quantifying Unknown Quantum Entanglement via a Hybrid Quantum-Classical Machine Learning Framework

Quantifying unknown quantum entanglement experimentally is a difficult task, but also becomes more and more necessary because of the fast development of quantum engineering. Machine learning provides practical solutions to this fundamental problem, where one has to train a proper machine learning model to predict entanglement measures of unknown quantum states based on experimentally measurable data, say moments or correlation data produced by local measurements. In this paper, we compare the performance of these two different machine learning approaches systematically. Particularly, we first show that the approach based on moments enjoys a remarkable advantage over that based on correlation data, though the cost of measuring moments is much higher. Next, since correlation data is much easier to obtain experimentally, we try to better its performance by proposing a hybrid quantum-classical machine learning framework for this problem, where the key is to train optimal local measurements to generate more informative correlation data. Our numerical simulations show that the new framework brings us comparable performance with the approach based on moments to quantify unknown entanglement. Our work implies that it is already practical to fulfill such tasks on near-term quantum devices.

quant-ph↗

arXiv2022

Deep Graph Learning for Spatially-Varying Indoor Lighting Prediction

Lighting prediction from a single image is becoming increasingly important in many vision and augmented reality (AR) applications in which shading and shadow consistency between virtual and real objects should be guaranteed. However, this is a notoriously ill-posed problem, especially for indoor scenarios, because of the complexity of indoor luminaires and the limited information involved in 2D images. In this paper, we propose a graph learning-based framework for indoor lighting estimation. At its core is a new lighting model (dubbed DSGLight) based on depth-augmented Spherical Gaussians (SG) and a Graph Convolutional Network (GCN) that infers the new lighting representation from a single LDR image of limited field-of-view. Our lighting model builds 128 evenly distributed SGs over the indoor panorama, where each SG encoding the lighting and the depth around that node. The proposed GCN then learns the mapping from the input image to DSGLight. Compared with existing lighting models, our DSGLight encodes both direct lighting and indirect environmental lighting more faithfully and compactly. It also makes network training and inference more stable. The estimated depth distribution enables temporally stable shading and shadows under spatially-varying lighting. Through thorough experiments, we show that our method obviously outperforms existing methods both qualitatively and quantitatively.

cs.CV↗

arXiv2021

Machine Learning-Assisted High-Throughput Semi-empirical Search of OFET Molecular Materials

Machine learning has been widely verified and applied in chemoinformatics, and have achieved outstanding results in the prediction, modification, and optimization of luminescence, magnetism, and electrode materials. Here, we propose a deepth first search traversal (DFST) approach combined with lightGBM machine learning model to search the classic Organic field-effect transistor (OFET) functional molecules chemical space, which is simple but effective. Totally 2820588 molecules of different structure within two certain types of skeletons are generated successfully, which shows the searching efficiency of the DFST strategy. With the simplified molecular-input line-entry system (SMILES) utilized, the generation of alphanumeric strings that describe molecules directly tackle the inverse design problem, for the generation set has 100% chemical validity. Light Gradient Boosting Machine (LightGBM) model's intrinsic Distributed and efficient features enables much faster training process and higher training efficiency, which means better model performance with less amount of data. 184 out of 2.8 million molecules are finally screened out with density functional theory (DFT) calculation carried out to verify the accuracy of the prediction.

cond-mat.mtrl-sci↗

arXiv2021

Quantifying Unknown Entanglement by Neural Networks

Quantum entanglement plays a crucial role in quantum information processing tasks and quantum mechanics, hence quantifying unknown entanglement is a fundamental task. However, this is also challenging, as entanglement cannot be measured by any observables directly. In this paper, we train neural networks to quantify unknown entanglement, where the input features of neural networks are the outcome statistics data produced by locally measuring target quantum states, and the training labels are well-chosen quantities. For bipartite quantum states, this quantity is coherent information, which is a lower bound for the entanglement of formation and the entanglement of distillation. For multipartite quantum states, we choose this quantity as the geometric measure of entanglement. It turns out that the neural networks we train have very good performance in quantifying unknown quantum states, and can beat previous approaches like semi-device-independent protocols for this problem easily in both precision and application range. We also observe a surprising phenomenon that on quantum states with stronger quantum nonlocality, the neural networks tend to have better performance, though we do not provide them any knowledge on quantum nonlocality.

quant-ph↗

arXiv2021

Graph-Based Fuzz Testing for Deep Learning Inference Engine

With the wide use of Deep Learning (DL) systems, academy and industry begin to pay attention to their quality. Testing is one of the major methods of quality assurance. However, existing testing techniques focus on the quality of DL models but lacks attention to the core underlying inference engines (i.e., frameworks and libraries). Inspired by the success stories of fuzz testing, we design a graph-based fuzz testing method to improve the quality of DL inference engines. This method is naturally followed by the graph structure of DL models. A novel operator-level coverage criterion based on graph theory is introduced and six different mutations are implemented to generate diversified DL models by exploring combinations of model structures, parameters, and data inputs. The Monte Carlo Tree Search (MCTS) is used to drive DL model generation without a training process. The experimental results show that the MCTS outperforms the random method in boosting operator-level coverage and detecting exceptions. Our method has discovered more than 40 different exceptions in three types of undesired behaviors: model conversion failure, inference failure, output comparison failure. The mutation strategies are useful to generate new valid test inputs, by up to 8.2% more operator-level coverage on average and 8.6 more exceptions captured.

cs.SE↗

arXiv2021

Prioritize Crowdsourced Test Reports via Deep Screenshot Understanding

Crowdsourced testing is increasingly dominant in mobile application (app) testing, but it is a great burden for app developers to inspect the incredible number of test reports. Many researches have been proposed to deal with test reports based only on texts or additionally simple image features. However, in mobile app testing, texts contained in test reports are condensed and the information is inadequate. Many screenshots are included as complements that contain much richer information beyond texts. This trend motivates us to prioritize crowdsourced test reports based on a deep screenshot understanding. In this paper, we present a novel crowdsourced test report prioritization approach, namely DeepPrior. We first represent the crowdsourced test reports with a novelly introduced feature, namely DeepFeature, that includes all the widgets along with their texts, coordinates, types, and even intents based on the deep analysis of the app screenshots, and the textual descriptions in the crowdsourced test reports. DeepFeature includes the Bug Feature, which directly describes the bugs, and the Context Feature, which depicts the thorough context of the bug. The similarity of the DeepFeature is used to represent the test reports' similarity and prioritize the crowdsourced test reports. We formally define the similarity as DeepSimilarity. We also conduct an empirical experiment to evaluate the effectiveness of the proposed technique with a large dataset group. The results show that DeepPrior is promising, and it outperforms the state-of-the-art approach with less than half the overhead.

cs.SE↗