arXiv subjects

Yu Lin

Publications and source records attributed to Yu Lin.

At least 37 records · Page 2Linked to original sources

arXiv2025

RDG-GS: Relative Depth Guidance with Gaussian Splatting for Real-time Sparse-View 3D Rendering

Efficiently synthesizing novel views from sparse inputs while maintaining accuracy remains a critical challenge in 3D reconstruction. While advanced techniques like radiance fields and 3D Gaussian Splatting achieve rendering quality and impressive efficiency with dense view inputs, they suffer from significant geometric reconstruction errors when applied to sparse input views. Moreover, although recent methods leverage monocular depth estimation to enhance geometric learning, their dependence on single-view estimated depth often leads to view inconsistency issues across different viewpoints. Consequently, this reliance on absolute depth can introduce inaccuracies in geometric information, ultimately compromising the quality of scene reconstruction with Gaussian splats. In this paper, we present RDG-GS, a novel sparse-view 3D rendering framework with Relative Depth Guidance based on 3D Gaussian Splatting. The core innovation lies in utilizing relative depth guidance to refine the Gaussian field, steering it towards view-consistent spatial geometric representations, thereby enabling the reconstruction of accurate geometric structures and capturing intricate textures. First, we devise refined depth priors to rectify the coarse estimated depth and insert global and fine-grained scene information to regular Gaussians. Building on this, to address spatial geometric inaccuracies from absolute depth, we propose relative depth guidance by optimizing the similarity between spatially correlated patches of depth and images. Additionally, we also directly deal with the sparse areas challenging to converge by the adaptive sampling for quick densification. Across extensive experiments on Mip-NeRF360, LLFF, DTU, and Blender, RDG-GS demonstrates state-of-the-art rendering quality and efficiency, making a significant advancement for real-world application.

cs.CV↗

arXiv2024

Transient Upstream Mesoscale Structures: Drivers of Solar-Quiet Space Weather

In recent years, it has become increasingly clear that space weather disturbances can be triggered by transient upstream mesoscale structures (TUMS), independently of the occurrence of large-scale solar wind (SW) structures, such as interplanetary coronal mass ejections and stream interaction regions. Different types of magnetospheric pulsations, transient perturbations of the geomagnetic field and auroral structures are often observed during times when SW monitors indicate quiet conditions, and have been found to be associated to TUMS. In this mini-review we describe the space weather phenomena that have been associated with four of the largest-scale and the most energetic TUMS, namely hot flow anomalies, foreshock bubbles, travelling foreshocks and foreshock compressional boundaries. The space weather phenomena associated with TUMS tend to be more localized and less intense compared to geomagnetic storms. However, the quiet time space weather may occur more often since, especially during solar minima, quiet SW periods prevail over the perturbed times.

astro-ph.SR↗

arXiv2024

A Robust Anchor-based Method for Multi-Camera Pedestrian Localization

This paper addresses the problem of vision-based pedestrian localization, which estimates a pedestrian's location using images and camera parameters. In practice, however, calibrated camera parameters often deviate from the ground truth, leading to inaccuracies in localization. To address this issue, we propose an anchor-based method that leverages fixed-position anchors to reduce the impact of camera parameter errors. We provide a theoretical analysis that demonstrates the robustness of our approach. Experiments conducted on simulated, real-world, and public datasets show that our method significantly improves localization accuracy and remains resilient to noise in camera parameters, compared to methods without anchors.

cs.CV↗

arXiv2024

Simulation Models for Exploring Magnetic Reconnection

Simulations have played a critical role in the advancement of our knowledge of magnetic reconnection. However, due to the inherently multiscale nature of reconnection, it is impossible to simulate all physics at all scales. For this reason, a wide range of simulation methods have been crafted to study particular aspects and consequences of magnetic reconnection. This chapter reviews many of these methods, laying out critical assumptions, numerical techniques, and giving examples of scientific results. Plasma models described include magnetohydrodynamics (MHD), Hall MHD, Hybrid, kinetic particle-in-cell (PIC), kinetic Vlasov, Fluid models with embedded PIC, Fluid models with direct feedback from energetic populations, and the Rice Convection Model (RCM).

physics.plasm-ph↗

arXiv2024

Momentum-resolved electronic structures and strong electronic correlations in graphene-like nitride superconductors

Although transition-metal nitrides have been widely applied for several decades, experimental investigations of their high-resolution electronic band structures are rare due to the lack of high-quality single-crystalline samples. Here, we report on the first momentum-resolved electronic band structures of titanium nitride (TiN) films, a remarkable nitride superconductor. The measurements of crystal structures and electrical transport properties confirmed the high quality of these films. More importantly, with a combination of high-resolution angle-resolved photoelectron spectroscopy and the first-principles calculations, the extracted Coulomb interaction strength of TiN films can be as large as 8.5 eV, whereas resonant photoemission spectroscopy yields a value of 6.26 eV. These large values of Coulomb interaction strength indicate that superconducting TiN is a strongly correlated system. Our results uncover the unexpected electronic correlations in transition-metal nitrides, potentially providing a perspective not only to understand their emergent quantum states but also to develop their applications in quantum devices.

cond-mat.mtrl-sci↗

arXiv2024

Self-Supervised Generative Models for Crystal Structures

Drawing inspiration from the achievements of natural language processing, we adopt self-supervised learning and utilize an equivariant graph neural network to develop a unified platform designed for training generative models capable of generating crystal structures, as well as efficiently adapting to downstream tasks in material property prediction. To mitigate the challenge of incorporating large-scale assessment on the reliability of generated structures into the training process, we utilize the generative adversarial network (GAN) with its discriminator being a cost-effective evaluator for the generated structures, resulting in notable improvements in model performance. We demonstrate the utility of our model in finding the optimal crystal structure under predefined conditions. Without reliance on properties acquired experimentally or numerically, our model further displays its capability to comprehend the mechanism of crystal structure formation through its ability to grouping chemically similar elements. Therefore, this paper extends an invitation to explore deeper into the scientific understanding of material structures through generative models, offering a fresh perspective on broadening the scope and efficacy of machine learning in material science.

cond-mat.mtrl-sci↗

arXiv2024

MedM2G: Unifying Medical Multi-Modal Generation via Cross-Guided Diffusion with Visual Invariant

Medical generative models, acknowledged for their high-quality sample generation ability, have accelerated the fast growth of medical applications. However, recent works concentrate on separate medical generation models for distinct medical tasks and are restricted to inadequate medical multi-modal knowledge, constraining medical comprehensive diagnosis. In this paper, we propose MedM2G, a Medical Multi-Modal Generative framework, with the key innovation to align, extract, and generate medical multi-modal within a unified model. Extending beyond single or two medical modalities, we efficiently align medical multi-modal through the central alignment approach in the unified space. Significantly, our framework extracts valuable clinical knowledge by preserving the medical visual invariant of each imaging modal, thereby enhancing specific medical information for multi-modal generation. By conditioning the adaptive cross-guided parameters into the multi-flow diffusion framework, our model promotes flexible interactions among medical multi-modal for generation. MedM2G is the first medical generative model that unifies medical generation tasks of text-to-image, image-to-text, and unified generation of medical modalities (CT, MRI, X-ray). It performs 5 medical generation tasks across 10 datasets, consistently outperforming various state-of-the-art works.

eess.IV↗

arXiv2024

SeqTrack3D: Exploring Sequence Information for Robust 3D Point Cloud Tracking

3D single object tracking (SOT) is an important and challenging task for the autonomous driving and mobile robotics. Most existing methods perform tracking between two consecutive frames while ignoring the motion patterns of the target over a series of frames, which would cause performance degradation in the scenes with sparse points. To break through this limitation, we introduce Sequence-to-Sequence tracking paradigm and a tracker named SeqTrack3D to capture target motion across continuous frames. Unlike previous methods that primarily adopted three strategies: matching two consecutive point clouds, predicting relative motion, or utilizing sequential point clouds to address feature degradation, our SeqTrack3D combines both historical point clouds and bounding box sequences. This novel method ensures robust tracking by leveraging location priors from historical boxes, even in scenes with sparse points. Extensive experiments conducted on large-scale datasets show that SeqTrack3D achieves new state-of-the-art performances, improving by 6.00% on NuScenes and 14.13% on Waymo dataset. The code will be made public at https://github.com/aron-lin/seqtrack3d.

cs.CV↗

arXiv2023

Motion-to-Matching: A Mixed Paradigm for 3D Single Object Tracking

3D single object tracking with LiDAR points is an important task in the computer vision field. Previous methods usually adopt the matching-based or motion-centric paradigms to estimate the current target status. However, the former is sensitive to the similar distractors and the sparseness of point cloud due to relying on appearance matching, while the latter usually focuses on short-term motion clues (eg. two frames) and ignores the long-term motion pattern of target. To address these issues, we propose a mixed paradigm with two stages, named MTM-Tracker, which combines motion modeling with feature matching into a single network. Specifically, in the first stage, we exploit the continuous historical boxes as motion prior and propose an encoder-decoder structure to locate target coarsely. Then, in the second stage, we introduce a feature interaction module to extract motion-aware features from consecutive point clouds and match them to refine target movement as well as regress other target states. Extensive experiments validate that our paradigm achieves competitive performance on large-scale datasets (70.9% in KITTI and 51.70% in NuScenes). The code will be open soon at https://github.com/LeoZhiheng/MTM-Tracker.git.

cs.CV↗

arXiv2023

UniDCP: Unifying Multiple Medical Vision-language Tasks via Dynamic Cross-modal Learnable Prompts

Medical vision-language pre-training (Med-VLP) models have recently accelerated the fast-growing medical diagnostics application. However, most Med-VLP models learn task-specific representations independently from scratch, thereby leading to great inflexibility when they work across multiple fine-tuning tasks. In this work, we propose UniDCP, a Unified medical vision-language model with Dynamic Cross-modal learnable Prompts, which can be plastically applied to multiple medical vision-language tasks. Specifically, we explicitly construct a unified framework to harmonize diverse inputs from multiple pretraining tasks by leveraging cross-modal prompts for unification, which accordingly can accommodate heterogeneous medical fine-tuning tasks. Furthermore, we conceive a dynamic cross-modal prompt optimizing strategy that optimizes the prompts within the shareable space for implicitly processing the shareable clinic knowledge. UniDCP is the first Med-VLP model capable of performing all 8 medical uni-modal and cross-modal tasks over 14 corresponding datasets, consistently yielding superior results over diverse state-of-the-art methods.

cs.CV↗

arXiv2023

Triggering the magnetopause reconnection by solar wind discontinuities

Magnetic reconnection is one of the most universal processes in space plasma that is responsible for charged particle acceleration, mixing and heating of plasma populations. In this paper we consider a triggering process of reconnection that is driven by interaction of two discontinuities: solar wind rotational discontinuity and tangential discontinuity at the Earth's magnetospheric boundary, magnetopause. Combining the multispacecraft measurements and global hybrid simulations, we show that solar wind discontinuities may drive the magnetopause reconnection and cause the mixing of the solar wind and magnetosphere plasmas around the magnetopause, well downstream of the solar wind flow. Since large-amplitude discontinuities are frequently observed in the solar wind and predicted for various stellar winds, our results of reconnection driven by the discontinuity-discontinuity interaction may have a broad application beyond the magnetosphere.

physics.space-ph↗

arXiv2023

Double-Flow-based Steganography without Embedding for Image-to-Image Hiding

As an emerging concept, steganography without embedding (SWE) hides a secret message without directly embedding it into a cover. Thus, SWE has the unique advantage of being immune to typical steganalysis methods and can better protect the secret message from being exposed. However, existing SWE methods are generally criticized for their poor payload capacity and low fidelity of recovered secret messages. In this paper, we propose a novel steganography-without-embedding technique, named DF-SWE, which addresses the aforementioned drawbacks and produces diverse and natural stego images. Specifically, DF-SWE employs a reversible circulation of double flow to build a reversible bijective transformation between the secret image and the generated stego image. Hence, it provides a way to directly generate stego images from secret images without a cover image. Besides leveraging the invertible property, DF-SWE can invert a secret image from a generated stego image in a nearly lossless manner and increases the fidelity of extracted secret images. To the best of our knowledge, DF-SWE is the first SWE method that can hide large images and multiple images into one image with the same size, significantly enhancing the payload capacity. According to the experimental results, the payload capacity of DF-SWE achieves 24-72 BPP is 8000-16000 times compared to its competitors while producing diverse images to minimize the exposure risk. Importantly, DF-SWE can be applied in the steganography of secret images in various domains without requiring training data from the corresponding domains. This domain-agnostic property suggests that DF-SWE can 1) be applied to hiding private data and 2) be deployed in resource-limited systems.

cs.CV↗

arXiv2023

PrivateLoRA For Efficient Privacy Preserving LLM

End users face a choice between privacy and efficiency in current Large Language Model (LLM) service paradigms. In cloud-based paradigms, users are forced to compromise data locality for generation quality and processing speed. Conversely, edge device paradigms maintain data locality but fail to deliver satisfactory performance. In this work, we propose a novel LLM service paradigm that distributes privacy-sensitive computation on edge devices and shared computation in the cloud. Only activations are transmitted between the central cloud and edge devices to ensure data locality. Our core innovation, PrivateLoRA, addresses the challenging communication overhead by exploiting the low rank of residual activations, achieving over 95% communication reduction. Consequently, PrivateLoRA effectively maintains data locality and is extremely resource efficient. Under standard 5G networks, PrivateLoRA achieves throughput over 300% of device-only solutions for 7B models and over 80% of an A100 GPU for 33B models. PrivateLoRA also provides tuning performance comparable to LoRA for advanced personalization. Our approach democratizes access to state-of-the-art generative AI for edge devices, paving the way for more tailored LLM experiences for the general public. To our knowledge, our proposed framework is the first efficient and privacy-preserving LLM solution in the literature.

cs.AI↗

arXiv2023

MultiLoRA: Democratizing LoRA for Better Multi-Task Learning

LoRA achieves remarkable resource efficiency and comparable performance when adapting LLMs for specific tasks. Since ChatGPT demonstrated superior performance on various tasks, there has been a growing desire to adapt one model for all tasks. However, the explicit low-rank of LoRA limits the adaptation performance in complex multi-task scenarios. LoRA is dominated by a small number of top singular vectors while fine-tuning decomposes into a set of less important unitary transforms. In this paper, we propose MultiLoRA for better multi-task adaptation by reducing the dominance of top singular vectors observed in LoRA. MultiLoRA scales LoRA modules horizontally and change parameter initialization of adaptation matrices to reduce parameter dependency, thus yields more balanced unitary subspaces. We unprecedentedly construct specialized training data by mixing datasets of instruction follow, natural language understanding, world knowledge, to cover semantically and syntactically different samples. With only 2.5% of additional parameters, MultiLoRA outperforms single LoRA counterparts and fine-tuning on multiple benchmarks and model scales. Further investigation into weight update matrices of MultiLoRA exhibits reduced dependency on top singular vectors and more democratic unitary transform contributions.

cs.LG↗

arXiv2023

Engineering of energy band and its impact on light transmission in non-reciprocal Hermitian hourglass lattice

We study a quasi-one-dimensional non-reciprocal Hermitian hourglass photonic lattice that can accomplish multiple functions. Under the effect of non-reciprocal coupling, this lattice can produce an energy isolation effect, two kinds of flat bands, and energy band inversion. The excitation and propagation of a single energy band and multiple energy bands can be realized; in the flat band condition, the system has compact localized states, and the flat bands can be excited by a straightforward method. In addition, we investigate the edge states under the open boundary condition; a double edge state appears by using a defect in the system. Our findings advance the theory of energy band regulation in artificial photonic lattices.

physics.optics↗

arXiv2023

An Algorithm for Modelling Escalator Fixed Loss Energy for PHM and sustainable energy usage

Prognostic Health Management (PHM) is designed to assess and monitor the health status of systems, anticipate the onset of potential failure, and prevent unplanned downtime. In recent decades, collecting massive amounts of real-time sensor data enabled condition monitoring (CM) and consequently, detection of abnormalities to support maintenance decision-making. Additionally, the utilization of PHM techniques can support energy sustainability efforts by optimizing energy usage and identifying opportunities for energy-saving measures. Escalators are efficient machines for transporting people and goods, and measuring energy consumption in time can facilitate PHM of escalators. Fixed loss energy, or no-load energy, of escalators denotes the energy consumption by an unloaded escalator. Fixed loss energy varies over time indicating varying operating conditions. In this paper, we propose to use escalators' fixed loss energy for PHM. We propose an approach to compute daily fixed loss energy based on energy consumption sensor data. The proposed approach is validated using a set of experimental data. The advantages and disadvantages of each approach are also presented, and recommendations are given. Finally, to illustrate PHM, we set up an EWMA chart for monitoring the fixed loss over time and demonstrate the potential in reducing energy costs associated with escalator operation.

stat.AP↗

arXiv2023

An LSTM-Based Predictive Monitoring Method for Data with Time-varying Variability

The recurrent neural network and its variants have shown great success in processing sequences in recent years. However, this deep neural network has not aroused much attention in anomaly detection through predictively process monitoring. Furthermore, the traditional statistic models work on assumptions and hypothesis tests, while neural network (NN) models do not need that many assumptions. This flexibility enables NN models to work efficiently on data with time-varying variability, a common inherent aspect of data in practice. This paper explores the ability of the recurrent neural network structure to monitor processes and proposes a control chart based on long short-term memory (LSTM) prediction intervals for data with time-varying variability. The simulation studies provide empirical evidence that the proposed model outperforms other NN-based predictive monitoring methods for mean shift detection. The proposed method is also applied to time series sensor data, which confirms that the proposed method is an effective technique for detecting abnormalities.

cs.LG↗

arXiv2023

MMF-Track: Multi-modal Multi-level Fusion for 3D Single Object Tracking

3D single object tracking plays a crucial role in computer vision. Mainstream methods mainly rely on point clouds to achieve geometry matching between target template and search area. However, textureless and incomplete point clouds make it difficult for single-modal trackers to distinguish objects with similar structures. To overcome the limitations of geometry matching, we propose a Multi-modal Multi-level Fusion Tracker (MMF-Track), which exploits the image texture and geometry characteristic of point clouds to track 3D target. Specifically, we first propose a Space Alignment Module (SAM) to align RGB images with point clouds in 3D space, which is the prerequisite for constructing inter-modal associations. Then, in feature interaction level, we design a Feature Interaction Module (FIM) based on dual-stream structure, which enhances intra-modal features in parallel and constructs inter-modal semantic associations. Meanwhile, in order to refine each modal feature, we introduce a Coarse-to-Fine Interaction Module (CFIM) to realize the hierarchical feature interaction at different scales. Finally, in similarity fusion level, we propose a Similarity Fusion Module (SFM) to aggregate geometry and texture clues from the target. Experiments show that our method achieves state-of-the-art performance on KITTI (39% Success and 42% Precision gains against previous multi-modal method) and is also competitive on NuScenes.

cs.CV↗