Searcharxiv⌕ Search

arXiv subjects

Yan Zhang

Publications and source records attributed to Yan Zhang.

At least 361 records · Page 20Linked to original sources
arXiv2024

Attention-based Efficient Classification for 3D MRI Image of Alzheimer's Disease

Early diagnosis of Alzheimer Diagnostics (AD) is a challenging task due to its subtle and complex clinical symptoms. Deep learning-assisted medical diagnosis using image recognition techniques has become an important research topic in this field. The features have to accurately capture main variations of anatomical brain structures. However, time-consuming is expensive for feature extraction by deep learning training. This study proposes a novel Alzheimer's disease detection model based on Convolutional Neural Networks. The model utilizes a pre-trained ResNet network as the backbone, incorporating post-fusion algorithm for 3D medical images and attention mechanisms. The experimental results indicate that the employed 2D fusion algorithm effectively improves the model's training expense. And the introduced attention mechanism accurately weights important regions in images, further enhancing the model's diagnostic accuracy.

eess.IV↗
arXiv2024

Feature Denoising Diffusion Model for Blind Image Quality Assessment

Blind Image Quality Assessment (BIQA) aims to evaluate image quality in line with human perception, without reference benchmarks. Currently, deep learning BIQA methods typically depend on using features from high-level tasks for transfer learning. However, the inherent differences between BIQA and these high-level tasks inevitably introduce noise into the quality-aware features. In this paper, we take an initial step towards exploring the diffusion model for feature denoising in BIQA, namely Perceptual Feature Diffusion for IQA (PFD-IQA), which aims to remove noise from quality-aware features. Specifically, (i) We propose a {Perceptual Prior Discovery and Aggregation module to establish two auxiliary tasks to discover potential low-level features in images that are used to aggregate perceptual text conditions for the diffusion model. (ii) We propose a Perceptual Prior-based Feature Refinement strategy, which matches noisy features to predefined denoising trajectories and then performs exact feature denoising based on text conditions. Extensive experiments on eight standard BIQA datasets demonstrate the superior performance to the state-of-the-art BIQA methods, i.e., achieving the PLCC values of 0.935 ( vs. 0.905 in KADID) and 0.922 ( vs. 0.894 in LIVEC).

cs.CV↗
arXiv2024

Understanding and Facilitating Mental Health Help-Seeking of Young Adults: A Socio-technical Ecosystem Framework

Prior research on young adults' mental health help-seeking mostly focuses on one particular resource such as a mobile app or digital platform, paying less attention to their lived experiences interacting with the ecosystem of resources. We conducted in-depth interviews with 18 participants about their help-seeking and non-help-seeking experiences. Guided by Social Ecological Theory, we proposed a Socio-technical Ecosystem Framework for mental health care, consisting of four levels of resources, including technological-, interpersonal-, community-, and societal level resources. Using this framework, we identified two types of support systems for help-seeking, single-resource support system and multi-resource support system. These resources support young adults' help-seeking via three mechanisms, \textit{care-giving}, \textit{care-mediating}, and \textit{care-outreaching}, forming various pathways to care. We then pointed out the barriers to resource use at each level and the general challenges in finding a support system. Our findings contributed to a conceptual framework to categorize mental health care. It also serves as a practical framework to identify challenges in the pathways to care and discover design implications.

cs.HC↗
arXiv2024

Robust Tiny Object Detection in Aerial Images amidst Label Noise

Precise detection of tiny objects in remote sensing imagery remains a significant challenge due to their limited visual information and frequent occurrence within scenes. This challenge is further exacerbated by the practical burden and inherent errors associated with manual annotation: annotating tiny objects is laborious and prone to errors (i.e., label noise). Training detectors for such objects using noisy labels often leads to suboptimal performance, with networks tending to overfit on noisy labels. In this study, we address the intricate issue of tiny object detection under noisy label supervision. We systematically investigate the impact of various types of noise on network training, revealing the vulnerability of object detectors to class shifts and inaccurate bounding boxes for tiny objects. To mitigate these challenges, we propose a DeNoising Tiny Object Detector (DN-TOD), which incorporates a Class-aware Label Correction (CLC) scheme to address class shifts and a Trend-guided Learning Strategy (TLS) to handle bounding box noise. CLC mitigates inaccurate class supervision by identifying and filtering out class-shifted positive samples, while TLS reduces noisy box-induced erroneous supervision through sample reweighting and bounding box regeneration. Additionally, Our method can be seamlessly integrated into both one-stage and two-stage object detection pipelines. Comprehensive experiments conducted on synthetic (i.e., noisy AI-TOD-v2.0 and DOTA-v2.0) and real-world (i.e., AI-TOD) noisy datasets demonstrate the robustness of DN-TOD under various types of label noise. Notably, when applied to the strong baseline RFLA, DN-TOD exhibits a noteworthy performance improvement of 4.9 points under 40% mixed noise. Datasets, codes, and models will be made publicly available.

cs.CV↗
arXiv2024

Prompt Decoupling for Text-to-Image Person Re-identification

Text-to-image person re-identification (TIReID) aims to retrieve the target person from an image gallery via a textual description query. Recently, pre-trained vision-language models like CLIP have attracted significant attention and have been widely utilized for this task due to their robust capacity for semantic concept learning and rich multi-modal knowledge. However, recent CLIP-based TIReID methods commonly rely on direct fine-tuning of the entire network to adapt the CLIP model for the TIReID task. Although these methods show competitive performance on this topic, they are suboptimal as they necessitate simultaneous domain adaptation and task adaptation. To address this issue, we attempt to decouple these two processes during the training stage. Specifically, we introduce the prompt tuning strategy to enable domain adaptation and propose a two-stage training approach to disentangle domain adaptation from task adaptation. In the first stage, we freeze the two encoders from CLIP and solely focus on optimizing the prompts to alleviate domain gap between the original training data of CLIP and downstream tasks. In the second stage, we maintain the fixed prompts and fine-tune the CLIP model to prioritize capturing fine-grained information, which is more suitable for TIReID task. Finally, we evaluate the effectiveness of our method on three widely used datasets. Compared to the directly fine-tuned approach, our method achieves significant improvements.

cs.CV↗
arXiv2023

An integrated framework for accelerating reactive flow simulation using GPU and machine learning models

Recent progress in artificial intelligence (AI) and high-performance computing (HPC) have brought potentially game-changing opportunities in accelerating reactive flow simulations. In this study, we introduce an open-source computational fluid dynamics (CFD) framework that integrates the strengths of machine learning (ML) and graphics processing unit (GPU) to demonstrate their combined capability. Within this framework, all computational operations are solely executed on GPU, including ML-accelerated chemistry integration, fully-implicit solving of PDEs, and computation of thermal and transport properties, thereby eliminating the CPU-GPU memory copy overhead. Optimisations both within the kernel functions and during the kernel launch process are conducted to enhance computational performance. Strategies such as static data reorganisation and dynamic data allocation are adopted to reduce the GPU memory footprint. The computational performance is evaluated in two turbulent flame benchmarks using quasi-DNS and LES modelling, respectively. Remarkably, while maintaining a similar level of accuracy to the conventional CPU/CVODE-based solver, the GPU/ML-accelerated approach shows an overall speedup of over two orders of magnitude for both cases. This result highlights that high-fidelity turbulent combustion simulation with finite-rate chemistry that requires normally hundreds of CPUs can now be performed on portable devices such as laptops with a medium-end GPU.

cs.CE↗
arXiv2023

DiffAIL: Diffusion Adversarial Imitation Learning

Imitation learning aims to solve the problem of defining reward functions in real-world decision-making tasks. The current popular approach is the Adversarial Imitation Learning (AIL) framework, which matches expert state-action occupancy measures to obtain a surrogate reward for forward reinforcement learning. However, the traditional discriminator is a simple binary classifier and doesn't learn an accurate distribution, which may result in failing to identify expert-level state-action pairs induced by the policy interacting with the environment. To address this issue, we propose a method named diffusion adversarial imitation learning (DiffAIL), which introduces the diffusion model into the AIL framework. Specifically, DiffAIL models the state-action pairs as unconditional diffusion models and uses diffusion loss as part of the discriminator's learning objective, which enables the discriminator to capture better expert demonstrations and improve generalization. Experimentally, the results show that our method achieves state-of-the-art performance and significantly surpasses expert demonstration on two benchmark tasks, including the standard state-action setting and state-only settings. Our code can be available at the link https://github.com/ML-Group-SDU/DiffAIL.

cs.LG↗
arXiv2023

LEAD: Liberal Feature-based Distillation for Dense Retrieval

Knowledge distillation is often used to transfer knowledge from a strong teacher model to a relatively weak student model. Traditional methods include response-based methods and feature-based methods. Response-based methods are widely used but suffer from lower upper limits of performance due to their ignorance of intermediate signals, while feature-based methods have constraints on vocabularies, tokenizers and model architectures. In this paper, we propose a liberal feature-based distillation method (LEAD). LEAD aligns the distribution between the intermediate layers of teacher model and student model, which is effective, extendable, portable and has no requirements on vocabularies, tokenizers, or model architectures. Extensive experiments show the effectiveness of LEAD on widely-used benchmarks, including MS MARCO Passage Ranking, TREC 2019 DL Track, MS MARCO Document Ranking and TREC 2020 DL Track. Our code is available in https://github.com/microsoft/SimXNS/tree/main/LEAD.

cs.IR↗
arXiv2023

Joint User Association, Interference Cancellation and Power Control for Multi-IRS Assisted UAV Communications

Intelligent reflecting surface (IRS)-assisted unmanned aerial vehicle (UAV) communications are expected to alleviate the load of ground base stations in a cost-effective way. Existing studies mainly focus on the deployment and resource allocation of a single IRS instead of multiple IRSs, whereas it is extremely challenging for joint multi-IRS multi-user association in UAV communications with constrained reflecting resources and dynamic scenarios. To address the aforementioned challenges, we propose a new optimization algorithm for joint IRS-user association, trajectory optimization of UAVs, successive interference cancellation (SIC) decoding order scheduling and power allocation to maximize system energy efficiency. We first propose an inverse soft-Q learning-based algorithm to optimize multi-IRS multi-user association. Then, SCA and Dinkelbach-based algorithm are leveraged to optimize UAV trajectory followed by the optimization of SIC decoding order scheduling and power allocation. Finally, theoretical analysis and performance results show significant advantages of the designed algorithm in convergence rate and energy efficiency.

cs.IT↗
arXiv2023

Edge computing service deployment and task offloading based on multi-task high-dimensional multi-objective optimization

The Mobile Edge Computing (MEC) system located close to the client allows mobile smart devices to offload their computations onto edge servers, enabling them to benefit from low-latency computing services. Both cloud service providers and users seek more comprehensive solutions, necessitating judicious decisions in service deployment and task offloading while balancing multiple objectives. This study investigates service deployment and task offloading challenges in a multi-user environment, framing them as a multi-task high-dimensional multi-objective optimization (MT-HD-MOO) problem within an edge environment. To ensure stable service provisioning, beyond considering latency, energy consumption, and cost as deployment objectives, network reliability is also incorporated. Furthermore, to promote equitable usage of edge servers, load balancing is introduced as a fourth task offloading objective, in addition to latency, energy consumption, and cost. Additionally, this paper designs a MT-HD-MOO algorithm based on a multi-selection strategy to address this model and its solution. By employing diverse selection strategies, an environment selection strategy pool is established to enhance population diversity within the high-dimensional objective space. Ultimately, the algorithm's effectiveness is verified through simulation experiments.

cs.NE↗
arXiv2023

Less is More: Learning Reference Knowledge Using No-Reference Image Quality Assessment

Image Quality Assessment (IQA) with reference images have achieved great success by imitating the human vision system, in which the image quality is effectively assessed by comparing the query image with its pristine reference image. However, for the images in the wild, it is quite difficult to access accurate reference images. We argue that it is possible to learn reference knowledge under the No-Reference Image Quality Assessment (NR-IQA) setting, which is effective and efficient empirically. Concretely, by innovatively introducing a novel feature distillation method in IQA, we propose a new framework to learn comparative knowledge from non-aligned reference images. And then, to achieve fast convergence and avoid overfitting, we further propose an inductive bias regularization. Such a framework not only solves the congenital defects of NR-IQA but also improves the feature extraction framework, enabling it to express more abundant quality information. Surprisingly, our method utilizes less input while obtaining a more significant improvement compared to the teacher models. Extensive experiments on eight standard NR-IQA datasets demonstrate the superior performance to the state-of-the-art NR-IQA methods, i.e., achieving the PLCC values of 0.917 (vs. 0.884 in LIVEC) and 0.686 (vs. 0.661 in LIVEFB).

cs.CV↗
arXiv2023

How does spatial structure affect psychological restoration? A method based on Graph Neural Networks and Street View Imagery

The Attention Restoration Theory (ART) presents a theoretical framework with four essential indicators (being away, extent, fascinating, and compatibility) for comprehending urban and natural restoration quality. However, previous studies relied on non-sequential data and non-spatial dependent methods, which overlooks the impact of spatial structure defined here as the positional relationships between scene entities on restoration quality. The past methods also make it challenging to measure restoration quality on an urban scale. In this work, a spatial-dependent graph neural networks (GNNs) approach is proposed to reveal the relation between spatial structure and restoration quality on an urban scale. Specifically, we constructed two different types of graphs at the street and city levels. The street-level graphs, using sequential street view images (SVIs) of road segments to capture position relationships between entities, were used to represent spatial structure. The city-level graph, modeling the topological relationships of roads as non-Euclidean data structures and embedding urban features (including Perception-features, Spatial-features, and Socioeconomic-features), was used to measure restoration quality. The results demonstrate that: 1) spatial-dependent GNNs model outperforms traditional methods (Acc = 0.735, F1 = 0.732); 2) spatial structure portrayed through sequential SVIs data significantly influences restoration quality; 3) spaces with the same restoration quality exhibited distinct spatial structures patterns. This study clarifies the association between spatial structure and restoration quality, providing a new perspective to improve urban well-being in the future.

cs.CV↗
arXiv2023

Flexible generation of structured terahertz fields via programmable exchange-biased spintronic emitters

Structured light, particularly in the terahertz frequency range, holds considerable potential for a diverse range of applications. However, the generation and control of structured terahertz radiation pose major challenges. In this work, we demonstrate a novel programmable spintronic emitter that can flexibly generate a variety of structured terahertz waves. This is achieved through the precise and high-resolution programming of the magnetization pattern on the emitter surface, utilizing laser-assisted local field cooling of an exchange-biased ferromagnetic heterostructure. Moreover, we outline a generic design strategy for realizing specific complex structured terahertz fields in the far field. Our device successfully demonstrates the generation of terahertz waves with diverse structured polarization states, including spatially separated circular polarizations, azimuthal or radial polarization states, and a full Poincare beam. This innovation opens a new avenue for designing and generating structured terahertz radiations, with potential applications in terahertz microscopy, communication, quantum information, and light-matter interactions.

physics.optics↗
arXiv2023

A Survey on Off-chain Networks: Frameworks, Technologies, Solutions and Challenges

Blockchain has received increasing attention in academia and industry. However, the increasing transaction volumes and limited on-chain storage underscore scalability as a key challenge hindering the widespread adoption of blockchain. Fortunately, off-chain networks that enable transactions outside the blockchain show promising potential to mitigate the scalability challenge. Off-chain solutions that address blockchain scalability hurdles, such as payment channel networks, facilitate secure and fast off-chain transactions, thus relieving the main chain's strain. In this article, we provide a comprehensive review of key technologies, solutions, and challenges of off-chain networks. First, we introduce the background of off-chain networks encompassing design motivation, framework, overview, and application scenarios. We then review the key issues and technologies associated with off-chain networks. Subsequently, we summarize the mainstream solutions for the corresponding key issues. Finally, we discuss some research challenges and open issues in this area.

cs.CR↗
arXiv2023

Data Augmentations in Deep Weight Spaces

Learning in weight spaces, where neural networks process the weights of other deep neural networks, has emerged as a promising research direction with applications in various fields, from analyzing and editing neural fields and implicit neural representations, to network pruning and quantization. Recent works designed architectures for effective learning in that space, which takes into account its unique, permutation-equivariant, structure. Unfortunately, so far these architectures suffer from severe overfitting and were shown to benefit from large datasets. This poses a significant challenge because generating data for this learning setup is laborious and time-consuming since each data sample is a full set of network weights that has to be trained. In this paper, we address this difficulty by investigating data augmentations for weight spaces, a set of techniques that enable generating new data examples on the fly without having to train additional input weight space elements. We first review several recently proposed data augmentation schemes %that were proposed recently and divide them into categories. We then introduce a novel augmentation scheme based on the Mixup method. We evaluate the performance of these techniques on existing benchmarks as well as new benchmarks we generate, which can be valuable for future studies.

cs.LG↗
arXiv2023

How Well Do Text Embedding Models Understand Syntax?

Text embedding models have significantly contributed to advancements in natural language processing by adeptly capturing semantic properties of textual data. However, the ability of these models to generalize across a wide range of syntactic contexts remains under-explored. In this paper, we first develop an evaluation set, named \textbf{SR}, to scrutinize the capability for syntax understanding of text embedding models from two crucial syntactic aspects: Structural heuristics, and Relational understanding among concepts, as revealed by the performance gaps in previous studies. Our findings reveal that existing text embedding models have not sufficiently addressed these syntactic understanding challenges, and such ineffectiveness becomes even more apparent when evaluated against existing benchmark datasets. Furthermore, we conduct rigorous analysis to unearth factors that lead to such limitations and examine why previous evaluations fail to detect such ineffectiveness. Lastly, we propose strategies to augment the generalization ability of text embedding models in diverse syntactic scenarios. This study serves to highlight the hurdles associated with syntactic generalization and provides pragmatic guidance for boosting model performance across varied syntactic contexts.

cs.CL↗
arXiv2023

Meta-Reinforcement Learning for Timely and Energy-efficient Data Collection in Solar-powered UAV-assisted IoT Networks

Unmanned aerial vehicles (UAVs) have the potential to greatly aid Internet of Things (IoT) networks in mission-critical data collection, thanks to their flexibility and cost-effectiveness. However, challenges arise due to the UAV's limited onboard energy and the unpredictable status updates from sensor nodes (SNs), which impact the freshness of collected data. In this paper, we investigate the energy-efficient and timely data collection in IoT networks through the use of a solar-powered UAV. Each SN generates status updates at stochastic intervals, while the UAV collects and subsequently transmits these status updates to a central data center. Furthermore, the UAV harnesses solar energy from the environment to maintain its energy level above a predetermined threshold. To minimize both the average age of information (AoI) for SNs and the energy consumption of the UAV, we jointly optimize the UAV trajectory, SN scheduling, and offloading strategy. Then, we formulate this problem as a Markov decision process (MDP) and propose a meta-reinforcement learning algorithm to enhance the generalization capability. Specifically, the compound-action deep reinforcement learning (CADRL) algorithm is proposed to handle the discrete decisions related to SN scheduling and the UAV's offloading policy, as well as the continuous control of UAV flight. Moreover, we incorporate meta-learning into CADRL to improve the adaptability of the learned policy to new tasks. To validate the effectiveness of our proposed algorithms, we conduct extensive simulations and demonstrate their superiority over other baseline algorithms.

cs.IT↗
arXiv2023

"Tell me about that church": Exploring the Design and User Experience of In-Vehicle Multi-modal Intuitive Interface in the Context of Driving Scenario

Intuitive interaction has long been seen as a highly user-friendly method. There are attempts to implement intuitive interfaces in vehicles in both research and industrial, such as voice commands. However, there is a lack of exploration in the in-vehicle multi-modal intuitive interaction, especially under a dynamic driving scenario. In this research, we conducted a design workshop (N=6) to understand user's needs and designers' considerations on the in-vehicle multi-modal intuitive interface, based on which we implemented our design on both a simulator and a real autonomous vehicle using Wizard-of-Oz. We conducted a user experiment (N=12) on the simulator to explore determinants of users' acceptance, experience, and behavior. We figured that acceptance was significantly influenced by six determinants. Drivers' behavior has an obvious pattern of change. Drivers have been proven to have less workload but distractions were also reported. Our findings offered empirical evidence which could give insights into future vehicle design.

cs.HC↗