Searcharxiv⌕ Search

arXiv subjects

Yuan Liu

Publications and source records attributed to Yuan Liu.

At least 325 records · Page 18Linked to original sources
arXiv2024

G-EvoNAS: Evolutionary Neural Architecture Search Based on Network Growth

The evolutionary paradigm has been successfully applied to neural network search(NAS) in recent years. Due to the vast search complexity of the global space, current research mainly seeks to repeatedly stack partial architectures to build the entire model or to seek the entire model based on manually designed benchmark modules. The above two methods are attempts to reduce the search difficulty by narrowing the search space. To efficiently search network architecture in the global space, this paper proposes another solution, namely a computationally efficient neural architecture evolutionary search framework based on network growth (G-EvoNAS). The complete network is obtained by gradually deepening different Blocks. The process begins from a shallow network, grows and evolves, and gradually deepens into a complete network, reducing the search complexity in the global space. Then, to improve the ranking accuracy of the network, we reduce the weight coupling of each network in the SuperNet by pruning the SuperNet according to elite groups at different growth stages. The G-EvoNAS is tested on three commonly used image classification datasets, CIFAR10, CIFAR100, and ImageNet, and compared with various state-of-the-art algorithms, including hand-designed networks and NAS networks. Experimental results demonstrate that G-EvoNAS can find a neural network architecture comparable to state-of-the-art designs in 0.2 GPU days.

cs.NE↗
arXiv2024

Closing the AI generalization gap by adjusting for dermatology condition distribution differences across clinical settings

Recently, there has been great progress in the ability of artificial intelligence (AI) algorithms to classify dermatological conditions from clinical photographs. However, little is known about the robustness of these algorithms in real-world settings where several factors can lead to a loss of generalizability. Understanding and overcoming these limitations will permit the development of generalizable AI that can aid in the diagnosis of skin conditions across a variety of clinical settings. In this retrospective study, we demonstrate that differences in skin condition distribution, rather than in demographics or image capture mode are the main source of errors when an AI algorithm is evaluated on data from a previously unseen source. We demonstrate a series of steps to close this generalization gap, requiring progressively more information about the new source, ranging from the condition distribution to training data enriched for data less frequently seen during training. Our results also suggest comparable performance from end-to-end fine tuning versus fine tuning solely the classification layer on top of a frozen embedding model. Our approach can inform the adaptation of AI algorithms to new settings, based on the information and resources available.

eess.IV↗
arXiv2024

Extreme Two-View Geometry From Object Poses with Diffusion Models

Human has an incredible ability to effortlessly perceive the viewpoint difference between two images containing the same object, even when the viewpoint change is astonishingly vast with no co-visible regions in the images. This remarkable skill, however, has proven to be a challenge for existing camera pose estimation methods, which often fail when faced with large viewpoint differences due to the lack of overlapping local features for matching. In this paper, we aim to effectively harness the power of object priors to accurately determine two-view geometry in the face of extreme viewpoint changes. In our method, we first mathematically transform the relative camera pose estimation problem to an object pose estimation problem. Then, to estimate the object pose, we utilize the object priors learned from a diffusion model Zero123 to synthesize novel-view images of the object. The novel-view images are matched to determine the object pose and thus the two-view camera pose. In experiments, our method has demonstrated extraordinary robustness and resilience to large viewpoint changes, consistently estimating two-view poses with exceptional generalization ability across both synthetic and real-world datasets. Code will be available at https://github.com/scy639/Extreme-Two-View-Geometry-From-Object-Poses-with-Diffusion-Models.

cs.CV↗
arXiv2024

Intrinsic Gaussian Processes on Manifolds and Their Accelerations by Symmetry

Amidst the growing interest in nonparametric regression, we address a significant challenge in Gaussian processes(GP) applied to manifold-based predictors. Existing methods primarily focus on low dimensional constrained domains for heat kernel estimation, limiting their effectiveness in higher-dimensional manifolds. Our research proposes an intrinsic approach for constructing GP on general manifolds such as orthogonal groups, unitary groups, Stiefel manifolds and Grassmannian manifolds. Our methodology estimates the heat kernel by simulating Brownian motion sample paths using the exponential map, ensuring independence from the manifold's embedding. The introduction of our strip algorithm, tailored for manifolds with extra symmetries, and the ball algorithm, designed for arbitrary manifolds, constitutes our significant contribution. Both algorithms are rigorously substantiated through theoretical proofs and numerical testing, with the strip algorithm showcasing remarkable efficiency gains over traditional methods. This intrinsic approach delivers several key advantages, including applicability to high dimensional manifolds, eliminating the requirement for global parametrization or embedding. We demonstrate its practicality through regression case studies (torus knots and eight dimensional projective spaces) and by developing binary classifiers for real world datasets (gorilla skulls planar images and diffusion tensor images). These classifiers outperform traditional methods, particularly in limited data scenarios.

math.OC↗
arXiv2024

An Introduction to Isomorphic Mathematical Analysis System

This paper is to build a primitive framework for a new possible extended system of real mathematical analysis - the Isomorphic Mathematical Analysis System (IMAS). It is based on some new concepts: e.g. isomorphic frame, dual-variable-isomorphic function, and isomorphic coordinate system. More concepts are introduced to constitute the whole IMAS framework. This IMAS attempts to provide current MA with new implements, which include isomorphic frame, thereby effectively putting the MA to work as well in some unevenly distributed coordinate spaces, realized by the isomorphic coordinate system. With these implements, many existing MA concepts are extended and incorporated into the new IMAS.

math.GM↗
arXiv2023

Ground Calibration Result of the Lobster Eye Imager for Astronomy

We report on results of the on-ground X-ray calibration of the Lobster Eye Imager for Astronomy (LEIA), an experimental space wide-field (18.6*18.6 square degrees) X-ray telescope built from novel lobster eye mirco-pore optics. LEIA was successfully launched on July 27, 2022 onboard the SATech-01 satellite. To achieve full characterisation of its performance before launch, a series of tests and calibrations have been carried out at different levels of devices, assemblies and the complete module. In this paper, we present the results of the end-to-end calibration campaign of the complete module carried out at the 100-m X-ray Test Facility at IHEP. The PSF, effective area and energy response of the detectors were measured in a wide range of incident directions at several X-ray line energies. The distributions of the PSF and effective areas are roughly uniform across the FoV, in large agreement with the prediction of lobster-eye optics. The mild variations and deviations from the prediction of idealized lobster-eye optics can be understood to be caused by the imperfect shapes and alignment of the micro-pores as well as the obscuration by the supporting frames, which can be well reproduced by MC simulations. The spatial resolution of LEIA defined by the FWHM of the focal spot ranges from 4-8 arcmin with a median of 5.7. The measured effective areas are in range of 2-3 $cm^2$ at ~1.25 keV across the entire FoV, and its dependence on photon energy is in large agreement with simulations. The gains of the CMOS sensors are in range of 6.5-6.9 eV/DN, and the energy resolutions in the range of ~120-140 eV at 1.25 keV and ~170-190 eV at 4.5 keV. These results have been ingested into the calibration database and applied to the analysis of the scientific data acquired by LEIA. This work paves the way for the calibration of the Wide-field X-Ray Telescope modules of the Einstein Probe mission.

astro-ph.IM↗
arXiv2023

Adaptive Multi-band Modulation for Robust and Low-complexity Faster-than-Nyquist Non-Orthogonal FDM IM-DD System

Faster-than-Nyquist non-orthogonal frequency-division multiplexing (FTN-NOFDM) is robust against the steep frequency roll-off by saving signal bandwidth. Among the FTN-NOFDM techniques, the non-orthogonal matrix precoding (NOM-p) based FTN has high compatibility with the conventional orthogonal frequency division multiplexing (OFDM), in terms of the advanced digital signal processing already used in OFDM. In this work, by dividing the single band into multiple sub-bands in the NOM-p-based FTN-NOFDM system, we propose a novel FTN-NOFDM scheme with adaptive multi-band modulation. The proposed scheme assigns different quadrature amplitude modulation (QAM) levels to different sub-bands, effectively utilizing the low-pass-like channel and reducing the complexity. The impacts of sub-band number and bandwidth compression factor on the bit-error-rate (BER) performance and implementation complexity are experimentally analyzed with a 32.23-Gb/s and 20-km intensity modulation-direct detection (IM-DD) optical transmission system. Results show that the proposed scheme with proper sub-band numbers can lower BER and greatly reduce the complexity compared to the conventional single-band way.

eess.SP↗
arXiv2023

Combining Kernelized Autoencoding and Centroid Prediction for Dynamic Multi-objective Optimization

Evolutionary algorithms face significant challenges when dealing with dynamic multi-objective optimization because Pareto optimal solutions and/or Pareto optimal fronts change. This paper proposes a unified paradigm, which combines the kernelized autoncoding evolutionary search and the centriod-based prediction (denoted by KAEP), for solving dynamic multi-objective optimization problems (DMOPs). Specifically, whenever a change is detected, KAEP reacts effectively to it by generating two subpopulations. The first subpoulation is generated by a simple centriod-based prediction strategy. For the second initial subpopulation, the kernel autoencoder is derived to predict the moving of the Pareto-optimal solutions based on the historical elite solutions. In this way, an initial population is predicted by the proposed combination strategies with good convergence and diversity, which can be effective for solving DMOPs. The performance of our proposed method is compared with five state-of-the-art algorithms on a number of complex benchmark problems. Empirical results fully demonstrate the superiority of our proposed method on most test instances.

cs.NE↗
arXiv2023

FoldExplorer: Fast and Accurate Protein Structure Search with Sequence-Enhanced Graph Embedding

The advent of highly accurate protein structure prediction methods has fueled an exponential expansion of the protein structure database. Consequently, there is a rising demand for rapid and precise structural homolog search. Traditional alignment-based methods are dedicated to precise comparisons between pairs, exhibiting high accuracy. However, their sluggish processing speed is no longer adequate for managing the current massive volume of data. In response to this challenge, we propose a novel deep-learning approach FoldExplorer. It harnesses the powerful capabilities of graph attention neural networks and protein large language models for protein structures and sequences data processing to generate embeddings for protein structures. The structural embeddings can be used for fast and accurate protein search. The embeddings also provide insights into the protein space. FoldExplorer demonstrates a substantial performance improvement of 5% to 8% over the current state-of-the-art algorithm on the benchmark datasets. Meanwhile, FoldExplorer does not compromise on search speed and excels particularly in searching on a large-scale dataset.

q-bio.BM↗
arXiv2023

SparseDC: Depth Completion from sparse and non-uniform inputs

We propose SparseDC, a model for Depth Completion of Sparse and non-uniform depth inputs. Unlike previous methods focusing on completing fixed distributions on benchmark datasets (e.g., NYU with 500 points, KITTI with 64 lines), SparseDC is specifically designed to handle depth maps with poor quality in real usage. The key contributions of SparseDC are two-fold. First, we design a simple strategy, called SFFM, to improve the robustness under sparse input by explicitly filling the unstable depth features with stable image features. Second, we propose a two-branch feature embedder to predict both the precise local geometry of regions with available depth values and accurate structures in regions with no depth. The key of the embedder is an uncertainty-based fusion module called UFFM to balance the local and long-term information extracted by CNNs and ViTs. Extensive indoor and outdoor experiments demonstrate the robustness of our framework when facing sparse and non-uniform input depths. The pre-trained model and code are available at https://github.com/WHU-USI3DV/SparseDC.

cs.CV↗
arXiv2023

GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces

The advent of neural 3D Gaussians has recently brought about a revolution in the field of neural rendering, facilitating the generation of high-quality renderings at real-time speeds. However, the explicit and discrete representation encounters challenges when applied to scenes featuring reflective surfaces. In this paper, we present GaussianShader, a novel method that applies a simplified shading function on 3D Gaussians to enhance the neural rendering in scenes with reflective surfaces while preserving the training and rendering efficiency. The main challenge in applying the shading function lies in the accurate normal estimation on discrete 3D Gaussians. Specifically, we proposed a novel normal estimation framework based on the shortest axis directions of 3D Gaussians with a delicately designed loss to make the consistency between the normals and the geometries of Gaussian spheres. Experiments show that GaussianShader strikes a commendable balance between efficiency and visual quality. Our method surpasses Gaussian Splatting in PSNR on specular object datasets, exhibiting an improvement of 1.57dB. When compared to prior works handling reflective surfaces, such as Ref-NeRF, our optimization time is significantly accelerated (23h vs. 0.58h). Please click on our project website to see more results.

cs.CV↗
arXiv2023

Asynchronous Wireless Federated Learning with Probabilistic Client Selection

Federated learning (FL) is a promising distributed learning framework where distributed clients collaboratively train a machine learning model coordinated by a server. To tackle the stragglers issue in asynchronous FL, we consider that each client keeps local updates and probabilistically transmits the local model to the server at arbitrary times. We first derive the (approximate) expression for the convergence rate based on the probabilistic client selection. Then, an optimization problem is formulated to trade off the convergence rate of asynchronous FL and mobile energy consumption by joint probabilistic client selection and bandwidth allocation. We develop an iterative algorithm to solve the non-convex problem globally optimally. Experiments demonstrate the superiority of the proposed approach compared with the traditional schemes.

cs.LG↗
arXiv2023

Quasi-finiteness of morphisms between character varieties

Let $f: Y\to X$ be a morphism between smooth complex quasi-projective varieties and $Z$ be the closure of $f(Y)$ with $ι: Z\to X$ the inclusion map. We prove that a. for any field $K$, there exist finitely many semisimple representations $\{τ_i:π_1(Z)\to {\rm GL}_N(\overline{k})\}_{i=1,\ldots,\ell}$ with $k\subset K$ the minimal field contained in $K$ such that if $\varrho:π_1(X)\to {\rm GL}_{N}(K)$ is any representation satisfying $[f^*\varrho]=1$, then $[ι^*\varrho]=[τ_i]$ for some $i$. b. The induced morphism between ${\rm GL}_{N}$-character varieties (of any characteristic) of $π_1(X)$ and $π_1(Y)$ is quasi-finite if ${\rm Im}[π_1(Z)\to π_1(X)]$ is a finite index subgroup of $π_1(X)$. These results extend the main results by Lasell in 1995 and Lasell-Ramachandran in 1996 from smooth complex projective varieties to quasi-projective cases with richer structures.

math.AG↗
arXiv2023

Resilient Control of Networked Microgrids using Vertical Federated Reinforcement Learning: Designs and Real-Time Test-Bed Validations

Improving system-level resiliency of networked microgrids is an important aspect with increased population of inverter-based resources (IBRs). This paper (1) presents resilient control design in presence of adversarial cyber-events, and proposes a novel federated reinforcement learning (Fed-RL) approach to tackle (a) model complexities, unknown dynamical behaviors of IBR devices, (b) privacy issues regarding data sharing in multi-party-owned networked grids, and (2) transfers learned controls from simulation to hardware-in-the-loop test-bed, thereby bridging the gap between simulation and real world. With these multi-prong objectives, first, we formulate a reinforcement learning (RL) training setup generating episodic trajectories with adversaries (attack signal) injected at the primary controllers of the grid forming (GFM) inverters where RL agents (or controllers) are being trained to mitigate the injected attacks. For networked microgrids, the horizontal Fed-RL method involving distinct independent environments is not appropriate, leading us to develop vertical variant Federated Soft Actor-Critic (FedSAC) algorithm to grasp the interconnected dynamics of networked microgrid. Next, utilizing OpenAI Gym interface, we built a custom simulation set-up in GridLAB-D/HELICS co-simulation platform, named Resilient RL Co-simulation (ResRLCoSIM), to train the RL agents with IEEE 123-bus benchmark test systems comprising 3 interconnected microgrids. Finally, the learned policies in simulation world are transferred to the real-time hardware-in-the-loop test-bed set-up developed using high-fidelity Hypersim platform. Experiments show that the simulator-trained RL controllers produce convincing results with the real-time test-bed set-up, validating the minimization of sim-to-real gap.

eess.SY↗
arXiv2023

Three Dimensional Reconfigurable Optical Singularities in Bilayer Photonic Crystals

Metasurfaces and photonic crystals have revolutionized classical and quantum manipulation of light, and opened the door to studying various optical singularities related to phases and polarization states. However, traditional nanophotonic devices lack reconfigurability, hindering the dynamic switching and optimization of optical singularities. This paper delves into the underexplored concept of tunable bilayer photonic crystals (BPhCs), which offer rich interlayer coupling effects. Utilizing silicon nitride-based BPhCs, we demonstrate tunable bidirectional and unidirectional polarization singularities, along with spatiotemporal phase singularities. Leveraging these tunable singularities, we achieve dynamic modulation of bound-state-in-continuum states, unidirectional guided resonances, and both longitudinal and transverse orbital angular momentum. Our work paves the way for multidimensional control over polarization and phase, inspiring new directions in ultrafast optics, optoelectronics, and quantum optics.

physics.optics↗
arXiv2023

Wonder3D: Single Image to 3D using Cross-Domain Diffusion

In this work, we introduce Wonder3D, a novel method for efficiently generating high-fidelity textured meshes from single-view images.Recent methods based on Score Distillation Sampling (SDS) have shown the potential to recover 3D geometry from 2D diffusion priors, but they typically suffer from time-consuming per-shape optimization and inconsistent geometry. In contrast, certain works directly produce 3D information via fast network inferences, but their results are often of low quality and lack geometric details. To holistically improve the quality, consistency, and efficiency of image-to-3D tasks, we propose a cross-domain diffusion model that generates multi-view normal maps and the corresponding color images. To ensure consistency, we employ a multi-view cross-domain attention mechanism that facilitates information exchange across views and modalities. Lastly, we introduce a geometry-aware normal fusion algorithm that extracts high-quality surfaces from the multi-view 2D representations. Our extensive evaluations demonstrate that our method achieves high-quality reconstruction results, robust generalization, and reasonably good efficiency compared to prior works.

cs.CV↗
arXiv2023

Static Virus Spread Algorithm for DNA Sequence Design

DNA is not only the genetic material of life, but also a favorable material for a new computing model. Various research works based on DNA computing have been carried out in recent years. DNA sequence design is the foundation of such research. The sequence quality directly affects the universality, robustness, and stability of DNA computing. How to design DNA sequences depends on the biological properties and target requirements, which is a typical combinatorial optimization problem. In this paper, in order to design DNA sequences with high-quality, we propose a novel meta-heuristic evolutionary algorithm, termed the static virus spread algorithm (SVS). Through this algorithm, we focus on the constraints of universal DNA sequence design and produce a large number of DNA sequences with non-complementarity and small difference in melting temperature as the objectives, and fully considering the balanced proportion of the four bases. The computer simulation and polyacrylamide gel electrophoresis experiments show that the high-quality DNA sequences designed by this algorithm are effective, which is expected to provide a convenient tool for sequence preparation before DNA biochemical operations.

cs.ET↗
arXiv2023

Accelerating Split Federated Learning over Wireless Communication Networks

The development of artificial intelligence (AI) provides opportunities for the promotion of deep neural network (DNN)-based applications. However, the large amount of parameters and computational complexity of DNN makes it difficult to deploy it on edge devices which are resource-constrained. An efficient method to address this challenge is model partition/splitting, in which DNN is divided into two parts which are deployed on device and server respectively for co-training or co-inference. In this paper, we consider a split federated learning (SFL) framework that combines the parallel model training mechanism of federated learning (FL) and the model splitting structure of split learning (SL). We consider a practical scenario of heterogeneous devices with individual split points of DNN. We formulate a joint problem of split point selection and bandwidth allocation to minimize the system latency. By using alternating optimization, we decompose the problem into two sub-problems and solve them optimally. Experiment results demonstrate the superiority of our work in latency reduction and accuracy improvement.

cs.LG↗