arXiv subjects

Yi Lin

Publications and source records attributed to Yi Lin.

At least 73 records · Page 4Linked to original sources

arXiv2024

Enhancing sensitivity of atomic microwave receiver combining laser arrays

Rydberg atom,which exhibits a strong response to weak electric(E) fields,is regarded as a promising atomic receiver to surpass sensitivity of conventional receivers. However, its sensitivity is strongly limited by the noise coming from both classical and quantum levels and how to enhance it significantly remains challenging. Here we experimentally prove that the sensitivity of Rydberg atomic receiver can be increased to 23 nV/cm/Hz1/2 by combining laser arrays. Theoretically, we demonstrate that multiple beams illuminating on a PD perform better than multiple PDs for laser arrays.In our experiment,10 dB SNR enhancement is achieved by utilizing 2 * 2 probe beam arrays, compared to the performance of a laser beam,and it can be enhanced further just by adding a resonator. The results could offer an avenue for the design and optimization of ultrahigh-sensitivity Rydberg atomic receivers and promote applications in cosmology, meteorology, communication, and microwave quantum technology.

physics.atom-ph↗

arXiv2024

Revisiting Deep Ensemble Uncertainty for Enhanced Medical Anomaly Detection

Medical anomaly detection (AD) is crucial in pathological identification and localization. Current methods typically rely on uncertainty estimation in deep ensembles to detect anomalies, assuming that ensemble learners should agree on normal samples while exhibiting disagreement on unseen anomalies in the output space. However, these methods may suffer from inadequate disagreement on anomalies or diminished agreement on normal samples. To tackle these issues, we propose D2UE, a Diversified Dual-space Uncertainty Estimation framework for medical anomaly detection. To effectively balance agreement and disagreement for anomaly detection, we propose Redundancy-Aware Repulsion (RAR), which uses a similarity kernel that remains invariant to both isotropic scaling and orthogonal transformations, explicitly promoting diversity in learners' feature space. Moreover, to accentuate anomalous regions, we develop Dual-Space Uncertainty (DSU), which utilizes the ensemble's uncertainty in input and output spaces. In input space, we first calculate gradients of reconstruction error with respect to input images. The gradients are then integrated with reconstruction outputs to estimate uncertainty for inputs, enabling effective anomaly discrimination even when output space disagreement is minimal. We conduct a comprehensive evaluation of five medical benchmarks with different backbones. Experimental results demonstrate the superiority of our method to state-of-the-art methods and the effectiveness of each component in our framework. Our code is available at https://github.com/Rubiscol/D2UE.

cs.CV↗

arXiv2024

Fine-Grained Building Function Recognition from Street-View Images via Geometry-Aware Semi-Supervised Learning

In this work, we propose a geometry-aware semi-supervised framework for fine-grained building function recognition, utilizing geometric relationships among multi-source data to enhance pseudo-label accuracy in semi-supervised learning, broadening its applicability to various building function categorization systems. Firstly, we design an online semi-supervised pre-training stage, which facilitates the precise acquisition of building facade location information in street-view images. In the second stage, we propose a geometry-aware coarse annotation generation module. This module effectively combines GIS data and street-view data based on the geometric relationships, improving the accuracy of pseudo annotations. In the third stage, we combine the newly generated coarse annotations with the existing labeled dataset to achieve fine-grained functional recognition of buildings across multiple cities at a large scale. Extensive experiments demonstrate that our proposed framework exhibits superior performance in fine-grained functional recognition of buildings. Within the same categorization system, it achieves improvements of 7.6\% and 4.8\% compared to fully-supervised methods and state-of-the-art semi-supervised methods, respectively. Additionally, our method also performs well in cross-city scenarios, i.e., extending the model trained on OmniCity (New York) to new cities (i.e., Los Angeles and Boston) with different building function categorization systems. This study offers a new solution for large-scale multi-city applications with minimal annotation requirements, facilitating more efficient data updates and resource allocation in urban management.

cs.CV↗

arXiv2024

Aligning Medical Images with General Knowledge from Large Language Models

Pre-trained large vision-language models (VLMs) like CLIP have revolutionized visual representation learning using natural language as supervisions, and demonstrated promising generalization ability. In this work, we propose ViP, a novel visual symptom-guided prompt learning framework for medical image analysis, which facilitates general knowledge transfer from CLIP. ViP consists of two key components: a visual symptom generator (VSG) and a dual-prompt network. Specifically, VSG aims to extract explicable visual symptoms from pre-trained large language models, while the dual-prompt network utilizes these visual symptoms to guide the training on two learnable prompt modules, i.e., context prompt and merge prompt, which effectively adapts our framework to medical image analysis via large VLMs. Extensive experimental results demonstrate that ViP can outperform state-of-the-art methods on two challenging datasets.

cs.CV↗

arXiv2024

Riemannian foliations and quasifolds

It is well known that, by the Reeb stability theorem, the leaf space of a Riemannian foliation with compact leaves is an orbifold. We prove that, under mild completeness conditions, the leaf space of a Killing Riemannian foliation is a diffeological quasifold: as a diffeological space, it is locally modelled by quotients of Cartesian space by countable groups acting affinely. Furthermore, we prove that the holonomy groupoid of the foliation is, locally, Morita equivalent to the action groupoid of a countable group acting affinely on Cartesian space.

math.DG↗

arXiv2024

Ultrafast creation of a light induced semimetallic state in strongly excited 1T-TiSe$_2$

Screening, a ubiquitous phenomenon associated with the shielding of electric fields by surrounding charges, has been widely adopted as a means to modify a material's properties. While so far most studies have relied on static changes of screening through doping or gating, here we demonstrate that screening can also drive the onset of distinct quantum states on the ultrafast timescale. By using time and angle-resolved photoemission spectroscopy we show that intense optical excitation can drive 1T-TiSe$_2$, a prototypical charge density wave material, almost instantly from a gapped into a semimetallic state. By systematically comparing changes in bandstructure over time and excitation strength with theoretical calculations we find that the appearance of this state is likely caused by a dramatic reduction of the screening length. In summary, this work showcases how optical excitation enables the screening driven design of a non-equilibrium semimetallic phase in TiSe$_2$, possibly providing a general pathway into highly screened phases in other strongly correlated materials.

cond-mat.mes-hall↗

arXiv2024

ROSE: A Recognition-Oriented Speech Enhancement Framework in Air Traffic Control Using Multi-Objective Learning

Radio speech echo is a specific phenomenon in the air traffic control (ATC) domain, which degrades speech quality and further impacts automatic speech recognition (ASR) accuracy. In this work, a time-domain recognition-oriented speech enhancement (ROSE) framework is proposed to improve speech intelligibility and also advance ASR accuracy based on convolutional encoder-decoder-based U-Net framework, which serves as a plug-and-play tool in ATC scenarios and does not require additional retraining of the ASR model. Specifically, 1) In the U-Net architecture, an attention-based skip-fusion (ABSF) module is applied to mine shared features from encoders using an attention mask, which enables the model to effectively fuse the hierarchical features. 2) A channel and sequence attention (CSAtt) module is innovatively designed to guide the model to focus on informative features in dual parallel attention paths, aiming to enhance the effective representations and suppress the interference noises. 3) Based on the handcrafted features, ASR-oriented optimization targets are designed to improve recognition performance in the ATC environment by learning robust feature representations. By incorporating both the SE-oriented and ASR-oriented losses, ROSE is implemented in a multi-objective learning manner by optimizing shared representations across the two task objectives. The experimental results show that the ROSE significantly outperforms other state-of-the-art methods for both the SE and ASR tasks, in which all the proposed improvements are confirmed by designed experiments. In addition, the proposed approach can contribute to the desired performance improvements on public datasets.

cs.SD↗

arXiv2024

TAKT: Target-Aware Knowledge Transfer for Whole Slide Image Classification

Transferring knowledge from a source domain to a target domain can be crucial for whole slide image classification, since the number of samples in a dataset is often limited due to high annotation costs. However, domain shift and task discrepancy between datasets can hinder effective knowledge transfer. In this paper, we propose a Target-Aware Knowledge Transfer framework, employing a teacher-student paradigm. Our framework enables the teacher model to learn common knowledge from the source and target domains by actively incorporating unlabelled target images into the training of the teacher model. The teacher bag features are subsequently adapted to supervise the training of the student model on the target domain. Despite incorporating the target features during training, the teacher model tends to overlook them under the inherent domain shift and task discrepancy. To alleviate this, we introduce a target-aware feature alignment module to establish a transferable latent relationship between the source and target features by solving the optimal transport problem. Experimental results show that models employing knowledge transfer outperform those trained from scratch, and our method achieves state-of-the-art performance among other knowledge transfer methods on various datasets, including TCGA-RCC, TCGA-NSCLC, and Camelyon16.

cs.CV↗

arXiv2024

Continuous 3D Myocardial Motion Tracking via Echocardiography

Myocardial motion tracking stands as an essential clinical tool in the prevention and detection of cardiovascular diseases (CVDs), the foremost cause of death globally. However, current techniques suffer from incomplete and inaccurate motion estimation of the myocardium in both spatial and temporal dimensions, hindering the early identification of myocardial dysfunction. To address these challenges, this paper introduces the Neural Cardiac Motion Field (NeuralCMF). NeuralCMF leverages implicit neural representation (INR) to model the 3D structure and the comprehensive 6D forward/backward motion of the heart. This method surpasses pixel-wise limitations by offering the capability to continuously query the precise shape and motion of the myocardium at any specific point throughout the cardiac cycle, enhancing the detailed analysis of cardiac dynamics beyond traditional speckle tracking. Notably, NeuralCMF operates without the need for paired datasets, and its optimization is self-supervised through the physics knowledge priors in both space and time dimensions, ensuring compatibility with both 2D and 3D echocardiogram video inputs. Experimental validations across three representative datasets support the robustness and innovative nature of the NeuralCMF, marking significant advantages over existing state-of-the-art methods in cardiac imaging and motion tracking.

eess.IV↗

arXiv2024

A Non-autoregressive Multi-Horizon Flight Trajectory Prediction Framework with Gray Code Representation

Flight Trajectory Prediction (FTP) is an essential task in Air Traffic Control (ATC), which can assist air traffic controllers in managing airspace more safely and efficiently. Existing approaches generally perform multi-horizon FTP tasks in an autoregressive manner, thereby suffering from error accumulation and low-efficiency problems. In this paper, a novel framework, called FlightBERT++, is proposed to i) forecast multi-horizon flight trajectories directly in a non-autoregressive way, and ii) improve the limitation of the binary encoding (BE) representation in the FlightBERT framework. Specifically, the proposed framework is implemented by a generalized encoder-decoder architecture, in which the encoder learns the temporal-spatial patterns from historical observations and the decoder predicts the flight status for the future horizons. Compared to conventional architecture, an innovative horizon-aware contexts generator is dedicatedly designed to consider the prior horizon information, which further enables non-autoregressive multi-horizon prediction. Additionally, the Gray code representation and the differential prediction paradigm are designed to cope with the high-bit misclassifications of the BE representation, which significantly reduces the outliers in the predictions. Moreover, a differential prompted decoder is proposed to enhance the capability of the differential predictions by leveraging the stationarity of the differential sequence. Extensive experiments are conducted to validate the proposed framework on a real-world flight trajectory dataset. The experimental results demonstrated that the proposed framework outperformed the competitive baselines in both FTP performance and computational efficiency.

cs.LG↗

arXiv2024

Dynamic Programming for Symbolic Boolean Realizability and Synthesis

Inspired by recent progress in dynamic programming approaches for weighted model counting, we investigate a dynamic-programming approach in the context of boolean realizability and synthesis, which takes a conjunctive-normal-form boolean formula over input and output variables, and aims at synthesizing witness functions for the output variables in terms of the inputs. We show how graded project-join trees, obtained via tree decomposition, can be used to compute a BDD representing the realizability set for the input formulas in a bottom-up order. We then show how the intermediate BDDs generated during realizability checking phase can be applied to synthesizing the witness functions in a top-down manner. An experimental evaluation of a solver -- DPSynth -- based on these ideas demonstrates that our approach for Boolean realizabilty and synthesis has superior time and space performance over a heuristics-based approach using same symbolic representations. We discuss the advantage on scalability of the new approach, and also investigate our findings on the performance of the DP framework.

cs.FL↗

arXiv2024

DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answering

Retrieval-Augmented Generation (RAG) has recently demonstrated the performance of Large Language Models (LLMs) in the knowledge-intensive tasks such as Question-Answering (QA). RAG expands the query context by incorporating external knowledge bases to enhance the response accuracy. However, it would be inefficient to access LLMs multiple times for each query and unreliable to retrieve all the relevant documents by a single query. We have found that even though there is low relevance between some critical documents and query, it is possible to retrieve the remaining documents by combining parts of the documents with the query. To mine the relevance, a two-stage retrieval framework called Dynamic-Relevant Retrieval-Augmented Generation (DR-RAG) is proposed to improve document retrieval recall and the accuracy of answers while maintaining efficiency. Additionally, a compact classifier is applied to two different selection strategies to determine the contribution of the retrieved documents to answering the query and retrieve the relatively relevant documents. Meanwhile, DR-RAG call the LLMs only once, which significantly improves the efficiency of the experiment. The experimental results on multi-hop QA datasets show that DR-RAG can significantly improve the accuracy of the answers and achieve new progress in QA systems.

cs.LG↗

arXiv2024

WinNet: Make Only One Convolutional Layer Effective for Time Series Forecasting

Deep learning models have recently achieved significant performance improvements in time series forecasting. We present a highly accurate and simply structured CNN-based model with only one convolutional layer, called WinNet, including (i) Sub-window Division block to transform the series into 2D tensor, (ii) Dual-Forecasting mechanism to capture the short- and long-term variations, (iii) Two-dimensional Hybrid Decomposition (TDD) block to decompose the 2D tensor into the trend and seasonal terms to eliminate the non-stationarity, and (iv) Decomposition Correlation Block (DCB) to leverage the correlation between the trend and seasonal terms by the convolution layer. Results on eight benchmark datasets demonstrate that WinNet can achieve SOTA performance and lower computational complexity over CNN-, MLP- and Transformer-based methods. The code will be available at: https://github.com/ouwen18/WinNet.

cs.LG↗

arXiv2024

LocMoE: A Low-Overhead MoE for Large Language Model Training

The Mixtures-of-Experts (MoE) model is a widespread distributed and integrated learning method for large language models (LLM), which is favored due to its ability to sparsify and expand models efficiently. However, the performance of MoE is limited by load imbalance and high latency of All-to-All communication, along with relatively redundant computation owing to large expert capacity. Load imbalance may result from existing routing policies that consistently tend to select certain experts. The frequent inter-node communication in the All-to-All procedure also significantly prolongs the training time. To alleviate the above performance problems, we propose a novel routing strategy that combines load balance and locality by converting partial inter-node communication to that of intra-node. Notably, we elucidate that there is a minimum threshold for expert capacity, calculated through the maximal angular deviation between the gating weights of the experts and the assigned tokens. We port these modifications on the PanGu-Sigma model based on the MindSpore framework with multi-level routing and conduct experiments on Ascend clusters. The experiment results demonstrate that the proposed LocMoE reduces training time per epoch by 12.68% to 22.24% compared to classical routers, such as hash router and switch router, without impacting the model accuracy.

cs.LG↗

arXiv2024

LENAS: Learning-based Neural Architecture Search and Ensemble for 3D Radiotherapy Dose Prediction

Radiation therapy treatment planning requires balancing the delivery of the target dose while sparing normal tissues, making it a complex process. To streamline the planning process and enhance its quality, there is a growing demand for knowledge-based planning (KBP). Ensemble learning has shown impressive power in various deep learning tasks, and it has great potential to improve the performance of KBP. However, the effectiveness of ensemble learning heavily depends on the diversity and individual accuracy of the base learners. Moreover, the complexity of model ensembles is a major concern, as it requires maintaining multiple models during inference, leading to increased computational cost and storage overhead. In this study, we propose a novel learning-based ensemble approach named LENAS, which integrates neural architecture search with knowledge distillation for 3D radiotherapy dose prediction. Our approach starts by exhaustively searching each block from an enormous architecture space to identify multiple architectures that exhibit promising performance and significant diversity. To mitigate the complexity introduced by the model ensemble, we adopt the teacher-student paradigm, leveraging the diverse outputs from multiple learned networks as supervisory signals to guide the training of the student network. Furthermore, to preserve high-level semantic information, we design a hybrid-loss to optimize the student network, enabling it to recover the knowledge embedded within the teacher networks. The proposed method has been evaluated on two public datasets, OpenKBP and AIMIS. Extensive experimental results demonstrate the effectiveness of our method and its superior performance to the state-of-the-art methods.

eess.IV↗

arXiv2024

Tunable Superconducting Magnetic Levitation with Self-Stability

Magnetic levitation based on the flux pinning nature of type II superconductors has the merit of self-stability, making it appealing for applications such as high speed bearings, maglev trains, space generators, etc. However, such levitation systems physically rely on the superconductor pre-capturing magnetic flux (i.e. field cooling process) before establishing the levitation state which is nonadjustable afterwards. Moreover, practical type II superconductors in the levitation system inevitably suffer from various sources of energy losses, leading to continuous levitation force decay. These intrinsic drawbacks make superconducting maglev inflexible and impractical for long term operation. Here we propose and demonstrate a new form of superconducting maglev which is tunable and with self-stability. The maglev system uses a closed-loop type II superconducting coil to lock flux of a magnet, establishing self-stable levitation between the two objects. A flux pump is used to modulate the total magnetic flux of the coil without breaking its superconductivity, thus flexibly tuning levitation force and height meanwhile maintaining self-stability. For the first time, we experimentally demonstrate a self-stable type II superconducting maglev system which is able to: counteract long term levitation force decay, adjust levitation force and equilibrium position, and establish levitation under zero field cooling condition. These breakthroughs may bridge the gap between demonstrations and practical applications of type II superconducting maglevs.

eess.SY↗

arXiv2024

Iterative Online Image Synthesis via Diffusion Model for Imbalanced Classification

Accurate and robust classification of diseases is important for proper diagnosis and treatment. However, medical datasets often face challenges related to limited sample sizes and inherent imbalanced distributions, due to difficulties in data collection and variations in disease prevalence across different types. In this paper, we introduce an Iterative Online Image Synthesis (IOIS) framework to address the class imbalance problem in medical image classification. Our framework incorporates two key modules, namely Online Image Synthesis (OIS) and Accuracy Adaptive Sampling (AAS), which collectively target the imbalance classification issue at both the instance level and the class level. The OIS module alleviates the data insufficiency problem by generating representative samples tailored for online training of the classifier. On the other hand, the AAS module dynamically balances the synthesized samples among various classes, targeting those with low training accuracy. To evaluate the effectiveness of our proposed method in addressing imbalanced classification, we conduct experiments on the HAM10000 and APTOS datasets. The results obtained demonstrate the superiority of our approach over state-of-the-art methods as well as the effectiveness of each component. The source code will be released upon acceptance.

cs.CV↗

arXiv2024

EdgeLeakage: Membership Information Leakage in Distributed Edge Intelligence Systems

In contemporary edge computing systems, decentralized edge nodes aggregate unprocessed data and facilitate data analytics to uphold low transmission latency and real-time data processing capabilities. Recently, these edge nodes have evolved to facilitate the implementation of distributed machine learning models, utilizing their computational resources to enable intelligent decision-making, thereby giving rise to an emerging domain referred to as edge intelligence. However, within the realm of edge intelligence, susceptibility to numerous security and privacy threats against machine learning models becomes evident. This paper addresses the issue of membership inference leakage in distributed edge intelligence systems. Specifically, our focus is on an autonomous scenario wherein edge nodes collaboratively generate a global model. The utilization of membership inference attacks serves to elucidate the potential data leakage in this particular context. Furthermore, we delve into the examination of several defense mechanisms aimed at mitigating the aforementioned data leakage problem. Experimental results affirm that our approach is effective in detecting data leakage within edge intelligence systems, and the implementation of our defense methods proves instrumental in alleviating this security threat. Consequently, our findings contribute to safeguarding data privacy in the context of edge intelligence systems.

cs.CR↗