arXiv subjects

Man Zhang

Publications and source records attributed to Man Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2024

OpenAnimals: Revisiting Person Re-Identification for Animals Towards Better Generalization

This paper addresses the challenge of animal re-identification, an emerging field that shares similarities with person re-identification but presents unique complexities due to the diverse species, environments and poses. To facilitate research in this domain, we introduce OpenAnimals, a flexible and extensible codebase designed specifically for animal re-identification. We conduct a comprehensive study by revisiting several state-of-the-art person re-identification methods, including BoT, AGW, SBS, and MGN, and evaluate their effectiveness on animal re-identification benchmarks such as HyenaID, LeopardID, SeaTurtleID, and WhaleSharkID. Our findings reveal that while some techniques generalize well, many do not, underscoring the significant differences between the two tasks. To bridge this gap, we propose ARBase, a strong \textbf{Base} model tailored for \textbf{A}nimal \textbf{R}e-identification, which incorporates insights from extensive experiments and introduces simple yet effective animal-oriented designs. Experiments demonstrate that ARBase consistently outperforms existing baselines, achieving state-of-the-art performance across various benchmarks.

cs.CV↗

arXiv2024

Fuzzing Microservices: A Series of User Studies in Industry on Industrial Systems with EvoMaster

With several microservice architectures comprising of thousands of web services, used to serve 630 million customers, companies like Meituan face several challenges in the verification and validation of their software. This paper reports on our experience of integrating EvoMaster (a search-based white-box fuzzer) in the testing processes at Meituan over almost 2 years. Two user studies were carried out in 2021 and in 2023 to evaluate two versions of EvoMaster, respectively, in tackling the test generation for industrial web services which are parts of a large e-commerce microservice system. The two user studies involve in total 321,131 lines of code from five APIs and 27 industrial participants at Meituan. Questionnaires and interviews were carried out in both user studies with employees at Meituan. The two user studies demonstrate clear advantages of EvoMaster (i.e., code coverage and fault detection) and the urgent need to have such a fuzzer in industrial microservices testing. To study how these results could generalize, a follow up user study was done in 2024 with five engineers in the five different companies. Our results show that, besides their clear usefulness, there are still many critical challenges that the research community needs to investigate to improve performance further.

cs.SE↗

arXiv2024

Self-supervised transformer-based pre-training method with General Plant Infection dataset

Pest and disease classification is a challenging issue in agriculture. The performance of deep learning models is intricately linked to training data diversity and quantity, posing issues for plant pest and disease datasets that remain underdeveloped. This study addresses these challenges by constructing a comprehensive dataset and proposing an advanced network architecture that combines Contrastive Learning and Masked Image Modeling (MIM). The dataset comprises diverse plant species and pest categories, making it one of the largest and most varied in the field. The proposed network architecture demonstrates effectiveness in addressing plant pest and disease recognition tasks, achieving notable detection accuracy. This approach offers a viable solution for rapid, efficient, and cost-effective plant pest and disease detection, thereby reducing agricultural production costs. Our code and dataset will be publicly available to advance research in plant pest and disease recognition the GitHub repository at https://github.com/WASSER2545/GPID-22

cs.CV↗

arXiv2024

Experimental evidence of crystal-field, Zeeman splitting, and spin-phonon excitations in the quantum supersolid Na2BaCo(PO4)2

Drawing inspiration from the recent breakthroughs in the \ce{Na_{2}BaCo(PO_{4})_{2}} quantum magnet, renowned for its spin supersolidity phase and its potential for revolutionary cooling applications, our study delves into the intricate interplay among lattice, spin, and orbital degrees of freedom within this intriguing compound. Using meticulous temperature, field, and pressure-dependent Raman scattering techniques, we present compelling experimental evidence revealing pronounced crystal-electric field (CEF) excitations, alongside the interplay of CEF-phonon interactions. Notably, our experiments elucidate all electronic transitions from $j_{1 / 2}$ to $j_{3 / 2}$ and from $j_{1 / 2}$ to $j_{5 / 2}$, with energy level patterns closely aligned with theoretical predictions based on point-charge models. Furthermore, the application of a magnetic field and pressure reveals Zeeman splittings characterized by Landé-g factors as well as the CEF-phonon resonances. The anomalous shift in coupled peak at low temperatures originates from the hybridization of CEF and phonon excitations due to their close energy proximity. These findings constitute a significant step towards unraveling the fundamental properties of this exotic quantum material for future research in fundamental physics or engineering application.

cond-mat.mtrl-sci↗

arXiv2024

RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models

The advent of Large Language Models (LLMs) has paved the way for complex tasks such as role-playing, which enhances user interactions by enabling models to imitate various characters. However, the closed-source nature of state-of-the-art LLMs and their general-purpose training limit role-playing optimization. In this paper, we introduce RoleLLM, a framework to benchmark, elicit, and enhance role-playing abilities in LLMs. RoleLLM comprises four stages: (1) Role Profile Construction for 100 roles; (2) Context-Based Instruction Generation (Context-Instruct) for role-specific knowledge extraction; (3) Role Prompting using GPT (RoleGPT) for speaking style imitation; and (4) Role-Conditioned Instruction Tuning (RoCIT) for fine-tuning open-source models along with role customization. By Context-Instruct and RoleGPT, we create RoleBench, the first systematic and fine-grained character-level benchmark dataset for role-playing with 168,093 samples. Moreover, RoCIT on RoleBench yields RoleLLaMA (English) and RoleGLM (Chinese), significantly enhancing role-playing abilities and even achieving comparable results with RoleGPT (using GPT-4).

cs.CL↗

arXiv2024

Probabilistic Contrastive Learning for Domain Adaptation

Contrastive learning has shown impressive success in enhancing feature discriminability for various visual tasks in a self-supervised manner, but the standard contrastive paradigm (features+$\ell_{2}$ normalization) has limited benefits when applied in domain adaptation. We find that this is mainly because the class weights (weights of the final fully connected layer) are ignored in the domain adaptation optimization process, which makes it difficult for features to cluster around the corresponding class weights. To solve this problem, we propose the \emph{simple but powerful} Probabilistic Contrastive Learning (PCL), which moves beyond the standard paradigm by removing $\ell_{2}$ normalization and replacing the features with probabilities. PCL can guide the probability distribution towards a one-hot configuration, thus minimizing the discrepancy between features and class weights. We conduct extensive experiments to validate the effectiveness of PCL and observe consistent performance gains on five tasks, i.e., Unsupervised/Semi-Supervised Domain Adaptation (UDA/SSDA), Semi-Supervised Learning (SSL), UDA Detection and Semantic Segmentation. Notably, for UDA Semantic Segmentation on SYNTHIA, PCL surpasses the sophisticated CPSL-D by $>\!2\%$ in terms of mean IoU with a much lower training cost (PCL: 1*3090, 5 days v.s. CPSL-D: 4*V100, 11 days). Code is available at https://github.com/ljjcoder/Probabilistic-Contrastive-Learning.

cs.CV↗

arXiv2024

Spectral Prompt Tuning:Unveiling Unseen Classes for Zero-Shot Semantic Segmentation

Recently, CLIP has found practical utility in the domain of pixel-level zero-shot segmentation tasks. The present landscape features two-stage methodologies beset by issues such as intricate pipelines and elevated computational costs. While current one-stage approaches alleviate these concerns and incorporate Visual Prompt Training (VPT) to uphold CLIP's generalization capacity, they still fall short in fully harnessing CLIP's potential for pixel-level unseen class demarcation and precise pixel predictions. To further stimulate CLIP's zero-shot dense prediction capability, we propose SPT-SEG, a one-stage approach that improves CLIP's adaptability from image to pixel. Specifically, we initially introduce Spectral Prompt Tuning (SPT), incorporating spectral prompts into the CLIP visual encoder's shallow layers to capture structural intricacies of images, thereby enhancing comprehension of unseen classes. Subsequently, we introduce the Spectral Guided Decoder (SGD), utilizing both high and low-frequency information to steer the network's spatial focus towards more prominent classification features, enabling precise pixel-level prediction outcomes. Through extensive experiments on two public datasets, we demonstrate the superiority of our method over state-of-the-art approaches, performing well across all classes and particularly excelling in handling unseen classes. Code is available at:https://github.com/clearxu/SPT.

cs.CV↗

arXiv2024

FurniScene: A Large-scale 3D Room Dataset with Intricate Furnishing Scenes

Indoor scene generation has attracted significant attention recently as it is crucial for applications of gaming, virtual reality, and interior design. Current indoor scene generation methods can produce reasonable room layouts but often lack diversity and realism. This is primarily due to the limited coverage of existing datasets, including only large furniture without tiny furnishings in daily life. To address these challenges, we propose FurniScene, a large-scale 3D room dataset with intricate furnishing scenes from interior design professionals. Specifically, the FurniScene consists of 11,698 rooms and 39,691 unique furniture CAD models with 89 different types, covering things from large beds to small teacups on the coffee table. To better suit fine-grained indoor scene layout generation, we introduce a novel Two-Stage Diffusion Scene Model (TSDSM) and conduct an evaluation benchmark for various indoor scene generation based on FurniScene. Quantitative and qualitative evaluations demonstrate the capability of our method to generate highly realistic indoor scenes. Our dataset and code will be publicly available soon.

cs.CV↗

arXiv2024

Recent Advances on Transition-Metal-Based Layered Double Hydroxides Nanosheets for Electrocatalytic Energy Conversion

Transition-metal-based layered double hydroxides (TM-LDHs) nanosheets are promising electrocatalysts in the renewable electrochemical energy conversion system, which are regarded as alternatives to noble metal-based materials. In this review, recent advances on effective and facile strategies to rationally design TM-LDHs nanosheets as electrocatalysts, such as increasing the number of active sties, improving the utilization of active sites (atomic-scale catalysts), modulating the electron configurations, and controlling the lattice facets, are summarized and compared. Then, the utilization of these fabricated TM-LDHs nanosheets for oxygen evolution reaction, hydrogen evolution reaction, urea oxidation reaction, nitrogen reduction reaction, small molecule oxidations, and biomass derivatives upgrading is articulated through systematically discussing the corresponding fundamental design principles and reaction mechanism. Finally, the existing challenges in increasing the density of catalytically active sites and future prospects of TM-LDHs nanosheets-based electrocatalysts in each application are also commented.

physics.app-ph↗

arXiv2024

Green fabrication of nickel-iron layered double hydroxides nanosheets efficient for the enhanced capacitive performance

Rational synthesis of robust layered double hydroxides (LDHs) nanosheets for high-energy supercapacitors is full of challenges. Herein, we reported an ultrasonication-assisted strategy to eco-friendly fabricate NiFe-LDHs nanosheets for the enhanced capacitive behavior. The experimental results combined with different advanced characterization tools document that the utilization of ultrasonication has a profound effect on the morphology and thickness of the as-obtained NiFe-LDHs, alternatively affecting the capacitive behavior. It shows that NiFe-LDHs nanosheets prepared with 2-h ultrasonic treatments display the exceptional capacitive performance because of the synergetic effect of ultrathin thickness, large specific surface area, and high mesoporous volume. The maximum specific capacitance of Ni3Fe1-LDHs nanosheets with the thickness of 7.39 nm and the specific surface area of 77.16 m2 g-1 reached 1923 F g-1, which is competitive with most previously reported values. In addition, the maximum specific energy of the assembled NiFe-LDHs//AC asymmetric supercapacitor achieved 49.13 Wh kg-1 at 400 W kg-1. This work provides a green technology to fabricate LDHs nanosheets, and offers deep insights for understanding the relationship between the morphology/structure and capacitive behavior of LDHs nanosheets, which is helpful for achieving high-performance LDHs-based electrode materials.

physics.app-ph↗

arXiv2024

In situ growth of hydrophilic nickel-cobalt layered double hydroxides nanosheets on biomass waste-derived porous carbon for high-performance hybrid supercapacitors

Rational design and cost-effective fabrication of layered double hydroxides (LDHs) nanosheets with extraordinary electrochemical performance is a key challenge for hybrid supercapacitors (HSCs). Herein, we report a facile in situ growth methodology to eco-friendly synthesize hydrophilic NiCo-LDHs nanosheets on biomass waste-derived porous carbon (BC) for robust high-performance HSC cathode. The in situ growth process under ultrasonication realizes the rational arrangement of NiCo-LDHs nanosheets on the surface of BC, which effectively increases the specific surface area, promotes the electronic conductivity and enhances the wettability of NiCo-LDHs nanosheets without affecting their thickness values. With the beneficial effects of ultrathin thickness of LDHs nanosheets (6.20 nm), large specific surface area (2324.1 m2 g-1), low charge transfer resistance (1.65 ohm), and high wettability with electrolyte (34-35 degree), the obtained Ni2Co1-LDHs/BC50 electrode possesses an ultra-high specific capacitance of 2390 F g-1 (956 C g-1) at 1 A g-1, which is superior to most reported values. Furthermore, an assembled Ni2Co1-LDHs/BC50//YP-80F HSC delivers a maximum specific energy of 52.47 Wh kg-1 at 375 W kg-1, and maintains a high capacitance retention of 75.9% even after 4000 cycles. This work provides a facile approach to fabricate LDHs nanosheets based cathode materials for high-performance HSCs.

physics.app-ph↗

arXiv2024

One-step architecture of bifunctional petal-like oxygen-deficient NiAl-LDHs nanosheets for high-performance hybrid supercapacitors and urea oxidation

Nickel-based layered double hydroxides (LDHs) are promising electrode materials in the fields of energy storage (supercapacitors) and conversion (urea oxidation). The rational construction of atomic and electronic structure is crucial for nickel-based LDHs to realize their satisfactory electrochemical performance. Herein, we report a facile, ecofriendly, one-step synthesis process to construct petal-like oxygen-deficient NiAl-LDH nanosheets for hybrid super-capacitors (HSCs) and urea oxidation reaction (UOR). The asprepared NiAl-LDH nanosheets with rich oxygen vacancies possess a large specific surface area of 216.6 m2 g-1 and a desirable electronic conductivity of 3.45 * 10-4 S cm-1 to deliver an ultra-high specific capacitance of 2801 F g-1 (700 C g-1) at 1 A g-1. Furthermore, high specific energy of 50.0 W h kg-1 at 400 W kg-1 and excellent cycle stability with 91% capacitance retention after 10,000 cycles are achieved by the NiAl-LDHs/CFP (carbon fiber paper) (+)//YP-80F (a commercial activated carbon) (-) HSC. Besides, NiAl-LDH nanosheets also work as an efficient electrocatalyst for UOR, which only requires 1.42 V vs. reversible hydrogen electrode to drive 10 mA cm-2 in 1 mol L-1 KOH with 0.33 mol L-1 urea. This remarkable performance is superior to most reported values of previous candidates owing to the thin structure of NiAl-LDH nanosheets for exposing more active sites and abundant oxygen vacancies. In addition, various reaction parameters are investigated to optimize the electrochemical performance. In general, this work paves a new way for the architecture of multifunctional nanostructured energy materials.

physics.app-ph↗

arXiv2024

Facile synthesis of micro-flower NiCo2O4 assembled by nanosheets efficient for electrocatalysis of water

Effective regulation of the morphology of transition metal spinel structures is crucial for creating efficient and stable bifunctional catalysts for electrocatalysis of water. In this work, micro-flower NiCo2O4 (F-NCO) assembled by nanosheets via a chemical template method for the simultaneous promotion of hydrogen evolution reaction (HER) and oxygen evolution reaction (OER). Electronic microscope analysis revealed that the thickness of the F-NCO catalyst was only 2.7% of that of the NiCo2O4 bulk (B-NCO), and this ultrathin lamellar structure was conducive to further exposure of the active site and improved reaction kinetics. The F-NCO catalyst exhibited superior HER and OER performance (10 = 236 and 310 mV) and robust long-term stability over the B-NCO catalyst in 1.0 M KOH, with a 2.68-fold and 4.16-fold increase in active surface area and a 0.42-fold and 0.61-fold decrease in charge transfer resistance values, respectively. This micro-flower-structured electrode has remarkable electrocatalytic property and long-term durability, providing a novel insight for characterizing cost-effective and high-performance bifunctional electrocatalysts.

physics.chem-ph↗

arXiv2024

QAGait: Revisit Gait Recognition from a Quality Perspective

Gait recognition is a promising biometric method that aims to identify pedestrians from their unique walking patterns. Silhouette modality, renowned for its easy acquisition, simple structure, sparse representation, and convenient modeling, has been widely employed in controlled in-the-lab research. However, as gait recognition rapidly advances from in-the-lab to in-the-wild scenarios, various conditions raise significant challenges for silhouette modality, including 1) unidentifiable low-quality silhouettes (abnormal segmentation, severe occlusion, or even non-human shape), and 2) identifiable but challenging silhouettes (background noise, non-standard posture, slight occlusion). To address these challenges, we revisit gait recognition pipeline and approach gait recognition from a quality perspective, namely QAGait. Specifically, we propose a series of cost-effective quality assessment strategies, including Maxmial Connect Area and Template Match to eliminate background noises and unidentifiable silhouettes, Alignment strategy to handle non-standard postures. We also propose two quality-aware loss functions to integrate silhouette quality into optimization within the embedding space. Extensive experiments demonstrate our QAGait can guarantee both gait reliability and performance enhancement. Furthermore, our quality assessment strategies can seamlessly integrate with existing gait datasets, showcasing our superiority. Code is available at https://github.com/wzb-bupt/QAGait.

cs.CV↗

arXiv2023

Uncertainty-Aware Test Prioritization: Approaches and Empirical Evaluation

Complex software systems, e.g., Cyber-Physical Systems (CPSs), interact with the real world; thus, they often behave unexpectedly in uncertain environments. Testing such systems is challenging due to limited resources, time, complex testing infrastructure setup, and the inherent uncertainties in their operating environment. Devising uncertainty-aware testing solutions supported with test optimization techniques can be considered as a mandate for tackling this challenge. This paper proposes an uncertainty-aware and time-aware test case prioritization approach, named UncerPrio, for optimizing a sequence of tests to execute with a multi-objective search. To guide the prioritization with uncertainty, we identify four uncertainty measures: uncertainty measurement (AUM), uncertainty space (PUS), the number of uncertainties (ANU), and uncertainty coverage (PUU). Based on these measures and their combinations, we proposed 10 uncertainty-aware and multi-objective test case prioritization problems, and each problem was additionally defined with one cost objective (execution cost, PET) to be minimized and one effective measure (model coverage, PTR) to be maximized. Moreover, considering time constraints for test executions (i.e., time-aware), we defined 10 time budgets for all the 10 problems for identifying the best strategy in solving uncertainty-aware test prioritization. In our empirical study, we employed four well-known Multi-Objective Search Algorithms (MuOSAs): NSGA-II, MOCell, SPEA2, and CellDE with five use cases from two industrial CPS subject systems, and used Random Algorithm (RS) as the comparison baseline. Results show that all the MuOSAs significantly outperformed RS. The strategy of Prob.6 f(PET,PTR,AUM,ANU) (i.e., the problem with uncertainty measures AUM and ANU combined) achieved the overall best performance in observing uncertainty when using 100% time budget.

cs.SE↗

arXiv2023

DeepQTest: Testing Autonomous Driving Systems with Reinforcement Learning and Real-world Weather Data

Autonomous driving systems (ADSs) are capable of sensing the environment and making driving decisions autonomously. These systems are safety-critical, and testing them is one of the important approaches to ensure their safety. However, due to the inherent complexity of ADSs and the high dimensionality of their operating environment, the number of possible test scenarios for ADSs is infinite. Besides, the operating environment of ADSs is dynamic, continuously evolving, and full of uncertainties, which requires a testing approach adaptive to the environment. In addition, existing ADS testing techniques have limited effectiveness in ensuring the realism of test scenarios, especially the realism of weather conditions and their changes over time. Recently, reinforcement learning (RL) has demonstrated great potential in addressing challenging problems, especially those requiring constant adaptations to dynamic environments. To this end, we present DeepQTest, a novel ADS testing approach that uses RL to learn environment configurations with a high chance of revealing abnormal ADS behaviors. Specifically, DeepQTest employs Deep Q-Learning and adopts three safety and comfort measures to construct the reward functions. To ensure the realism of generated scenarios, DeepQTest defines a set of realistic constraints and introduces real-world weather conditions into the simulated environment. We employed three comparison baselines, i.e., random, greedy, and a state-of-the-art RL-based approach DeepCOllision, for evaluating DeepQTest on an industrial-scale ADS. Evaluation results show that DeepQTest demonstrated significantly better effectiveness in terms of generating scenarios leading to collisions and ensuring scenario realism compared with the baselines. In addition, among the three reward functions implemented in DeepQTest, Time-To-Collision is recommended as the best design according to our study.

cs.SE↗

arXiv2023

Bidirectional Knowledge Reconfiguration for Lightweight Point Cloud Analysis

Point cloud analysis faces computational system overhead, limiting its application on mobile or edge devices. Directly employing small models may result in a significant drop in performance since it is difficult for a small model to adequately capture local structure and global shape information simultaneously, which are essential clues for point cloud analysis. This paper explores feature distillation for lightweight point cloud models. To mitigate the semantic gap between the lightweight student and the cumbersome teacher, we propose bidirectional knowledge reconfiguration (BKR) to distill informative contextual knowledge from the teacher to the student. Specifically, a top-down knowledge reconfiguration and a bottom-up knowledge reconfiguration are developed to inherit diverse local structure information and consistent global shape knowledge from the teacher, respectively. However, due to the farthest point sampling in most point cloud models, the intermediate features between teacher and student are misaligned, deteriorating the feature distillation performance. To eliminate it, we propose a feature mover's distance (FMD) loss based on optimal transportation, which can measure the distance between unordered point cloud features effectively. Extensive experiments conducted on shape classification, part segmentation, and semantic segmentation benchmarks demonstrate the universality and superiority of our method.

cs.CV↗

arXiv2023

Advanced White-Box Heuristics for Search-Based Fuzzing of REST APIs

Due to its importance and widespread use in industry, automated testing of REST APIs has attracted major interest from the research community in the last few years. However, most of the work in the literature has been focused on black-box fuzzing. Although existing fuzzers have been used to automatically find many faults in existing APIs, there are still several open research challenges that hinder the achievement of better results (e.g., in terms of code coverage and fault finding). For example, under-specified schemas are a major issue for black-box fuzzers. Currently, EvoMaster is the only existing tool that supports white-box fuzzing of REST APIs. In this paper, we provide a series of novel white-box heuristics, including for example how to deal with under-specified constrains in API schemas, as well as under-specified schemas in SQL databases. Our novel techniques are implemented as an extension to our open-source, search-based fuzzer EvoMaster. An empirical study on 14 APIs from the EMB corpus, plus one industrial API, shows clear improvements of the results in some of these APIs.

cs.SE↗