arXiv subjects

Feng Gao

Publications and source records attributed to Feng Gao.

At least 127 records · Page 7Linked to original sources

arXiv2025

MSFMamba: Multi-Scale Feature Fusion State Space Model for Multi-Source Remote Sensing Image Classification

In the field of multi-source remote sensing image classification, remarkable progress has been made by using Convolutional Neural Network (CNN) and Transformer. Recently, Mamba-based methods built upon the State Space Model (SSM) have shown great potential for long-range dependency modeling with linear complexity, but they have rarely been explored for multi-source remote sensing image classification tasks. To address this issue, we propose the Multi-Scale Feature Fusion Mamba (MSFMamba) network, a novel framework designed for the joint classification of hyperspectral image (HSI) and Light Detection and Ranging (LiDAR)/Synthetic Aperture Radar (SAR) data. The MSFMamba network is composed of three key components: the Multi-Scale Spatial Mamba (MSpa-Mamba) block, the Spectral Mamba (Spe-Mamba) block, and the Fusion Mamba (Fus-Mamba) block. The MSpa-Mamba block employs a multi-scale strategy to reduce computational cost and alleviate feature redundancy in multiple scanning routes, ensuring efficient spatial feature modeling. The Spe-Mamba block focuses on spectral feature extraction, addressing the unique challenges of HSI data representation. Finally, the Fus-Mamba block bridges the heterogeneous gap between HSI and LiDAR/SAR data by extending the original Mamba architecture to accommodate dual inputs, enhancing cross-modal feature interactions and enabling seamless data fusion. Together, these components enable MSFMamba to effectively tackle the challenges of multi-source data classification, delivering improved performance with optimized computational efficiency. Comprehensive experiments on four real-world multi-source remote sensing datasets demonstrate the superiority of MSFMamba outperforms several state-of-the-art methods. The source codes of MSFMamba are publicly available at https://github.com/oucailab/MSFMamba.

eess.IV↗

arXiv2025

Aligning Human Motion Generation with Human Perceptions

Human motion generation is a critical task with a wide range of applications. Achieving high realism in generated motions requires naturalness, smoothness, and plausibility. Despite rapid advancements in the field, current generation methods often fall short of these goals. Furthermore, existing evaluation metrics typically rely on ground-truth-based errors, simple heuristics, or distribution distances, which do not align well with human perceptions of motion quality. In this work, we propose a data-driven approach to bridge this gap by introducing a large-scale human perceptual evaluation dataset, MotionPercept, and a human motion critic model, MotionCritic, that capture human perceptual preferences. Our critic model offers a more accurate metric for assessing motion quality and could be readily integrated into the motion generation pipeline to enhance generation quality. Extensive experiments demonstrate the effectiveness of our approach in both evaluating and improving the quality of generated human motions by aligning with human perceptions. Code and data are publicly available at https://motioncritic.github.io/.

cs.CV↗

arXiv2025

Surface-SOS: Self-Supervised Object Segmentation via Neural Surface Representation

Self-supervised Object Segmentation (SOS) aims to segment objects without any annotations. Under conditions of multi-camera inputs, the structural, textural and geometrical consistency among each view can be leveraged to achieve fine-grained object segmentation. To make better use of the above information, we propose Surface representation based Self-supervised Object Segmentation (Surface-SOS), a new framework to segment objects for each view by 3D surface representation from multi-view images of a scene. To model high-quality geometry surfaces for complex scenes, we design a novel scene representation scheme, which decomposes the scene into two complementary neural representation modules respectively with a Signed Distance Function (SDF). Moreover, Surface-SOS is able to refine single-view segmentation with multi-view unlabeled images, by introducing coarse segmentation masks as additional input. To the best of our knowledge, Surface-SOS is the first self-supervised approach that leverages neural surface representation to break the dependence on large amounts of annotated data and strong constraints. These constraints typically involve observing target objects against a static background or relying on temporal supervision in videos. Extensive experiments on standard benchmarks including LLFF, CO3D, BlendedMVS, TUM and several real-world scenes show that Surface-SOS always yields finer object masks than its NeRF-based counterparts and surpasses supervised single-view baselines remarkably. Code is available at: https://github.com/zhengxyun/Surface-SOS.

cs.CV↗

arXiv2025

Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching

Generative models based on flow matching have attracted significant attention for their simplicity and superior performance in high-resolution image synthesis. By leveraging the instantaneous change-of-variables formula, one can directly compute image likelihoods from a learned flow, making them enticing candidates as priors for downstream tasks such as inverse problems. In particular, a natural approach would be to incorporate such image probabilities in a maximum-a-posteriori (MAP) estimation problem. A major obstacle, however, lies in the slow computation of the log-likelihood, as it requires backpropagating through an ODE solver, which can be prohibitively slow for high-dimensional problems. In this work, we propose an iterative algorithm to approximate the MAP estimator efficiently to solve a variety of linear inverse problems. Our algorithm is mathematically justified by the observation that the MAP objective can be approximated by a sum of $N$ ``local MAP'' objectives, where $N$ is the number of function evaluations. By leveraging Tweedie's formula, we show that we can perform gradient steps to sequentially optimize these objectives. We validate our approach for various linear inverse problems, such as super-resolution, deblurring, inpainting, and compressed sensing, and demonstrate that we can outperform other methods based on flow matching. Code is available at https://github.com/YasminZhang/ICTM.

cs.CV↗

arXiv2024

Identifying percolation phase transitions with unsupervised learning based on largest clusters

The application of machine learning in the study of phase transitions has achieved remarkable success in both equilibrium and non-equilibrium systems. It is widely recognized that unsupervised learning can retrieve phase transition information through hidden variables. However, using unsupervised methods to identify the critical point of percolation models has remained an intriguing challenge. This paper suggests that, by inputting the largest cluster rather than the original configuration into the learning model, unsupervised learning can indeed predict the critical point of the percolation model. Furthermore, we observe that when the largest cluster configuration is randomly shuffled-altering the positions of occupied sites or bonds-there is no significant difference in the output compared to learning the largest cluster configuration directly. This finding suggests a more general principle: unsupervised learning primarily captures particle density, or more specifically, occupied site density. However, shuffling does impact the formation of the largest cluster, which is directly related to phase transitions. As randomness increases, we observe that the correlation length tends to decrease, providing direct evidence of this relationship. We also propose a method called Fake Finite Size Scaling (FFSS) to calculate the critical value, which improves the accuracy of fitting to a great extent.

cond-mat.stat-mech↗

arXiv2024

Global and Local Attention-Based Transformer for Hyperspectral Image Change Detection

Recently Transformer-based hyperspectral image (HSI) change detection methods have shown remarkable performance. Nevertheless, existing attention mechanisms in Transformers have limitations in local feature representation. To address this issue, we propose Global and Local Attention-based Transformer (GLAFormer), which incorporates a global and local attention module (GLAM) to combine high-frequency and low-frequency signals. Furthermore, we introduce a cross-gating mechanism, called cross-gated feed-forward network (CGFN), to emphasize salient features and suppress noise interference. Specifically, the GLAM splits attention heads into global and local attention components to capture comprehensive spatial-spectral features. The global attention component employs global attention on downsampled feature maps to capture low-frequency information, while the local attention component focuses on high-frequency details using non-overlapping window-based local attention. The CGFN enhances the feature representation via convolutions and cross-gating mechanism in parallel paths. The proposed GLAFormer is evaluated on three HSI datasets. The results demonstrate its superiority over state-of-the-art HSI change detection methods. The source code of GLAFormer is available at \url{https://github.com/summitgao/GLAFormer}.

eess.IV↗

arXiv2024

Variational learning of integrated quantum photonic circuits

Integrated photonic circuits play a crucial role in implementing quantum information processing in the noisy intermediate-scale quantum (NISQ) era. Variational learning is a promising avenue that leverages classical optimization techniques to enhance quantum advantages on NISQ devices. However, most variational algorithms are circuit-model-based and encounter challenges when implemented on integrated photonic circuits, because they involve explicit decomposition of large quantum circuits into sequences of basic entangled gates, leading to an exponential decay of success probability due to the non-deterministic nature of photonic entangling gates. Here, we present a variational learning approach for designing quantum photonic circuits, which directly incorporates post-selection and elementary photonic elements into the training process. The complicated circuit is treated as a single nonlinear logical operator, and a unified design is discovered for it through variational learning. Engineering an integrated photonic chip with automated control, we adjust and optimize the internal parameters of the chip in real time for task-specific cost functions. We utilize a simple case of designing photonic circuits for a single ancilla CNOT gate with improved success rate to illustrate how our proposed approach works, and then apply the approach in the first demonstration of quantum stochastic simulation using integrated photonics.

quant-ph↗

arXiv2024

Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication

Existing diffusion-based text-to-3D generation methods primarily focus on producing visually realistic shapes and appearances, often neglecting the physical constraints necessary for downstream tasks. Generated models frequently fail to maintain balance when placed in physics-based simulations or 3D printed. This balance is crucial for satisfying user design intentions in interactive gaming, embodied AI, and robotics, where stable models are needed for reliable interaction. Additionally, stable models ensure that 3D-printed objects, such as figurines for home decoration, can stand on their own without requiring additional supports. To fill this gap, we introduce Atlas3D, an automatic and easy-to-implement method that enhances existing Score Distillation Sampling (SDS)-based text-to-3D tools. Atlas3D ensures the generation of self-supporting 3D models that adhere to physical laws of stability under gravity, contact, and friction. Our approach combines a novel differentiable simulation-based loss function with physically inspired regularization, serving as either a refinement or a post-processing module for existing frameworks. We verify Atlas3D's efficacy through extensive generation tasks and validate the resulting 3D models in both simulated and real-world environments.

cs.LG↗

arXiv2024

ARM: Appearance Reconstruction Model for Relightable 3D Generation

Recent image-to-3D reconstruction models have greatly advanced geometry generation, but they still struggle to faithfully generate realistic appearance. To address this, we introduce ARM, a novel method that reconstructs high-quality 3D meshes and realistic appearance from sparse-view images. The core of ARM lies in decoupling geometry from appearance, processing appearance within the UV texture space. Unlike previous methods, ARM improves texture quality by explicitly back-projecting measurements onto the texture map and processing them in a UV space module with a global receptive field. To resolve ambiguities between material and illumination in input images, ARM introduces a material prior that encodes semantic appearance information, enhancing the robustness of appearance decomposition. Trained on just 8 H100 GPUs, ARM outperforms existing methods both quantitatively and qualitatively.

cs.CV↗

arXiv2024

The tricritical point of tricritical directed percolation is determined based on neural network

In recent years, neural networks have increasingly been employed to identify critical points of phase transitions. For the tricritical directed percolation model, its steady-state configurations encompass both first-order and second-order phase transitions. Due to the presence of crossover effects, identifying the critical points of phase transitions becomes challenging. This study utilizes Monte Carlo simulations to obtain steady-state configurations under different probabilities $p$ and $q$, and by calculating the increments in average particle density, we observe first-order transitions, second-order transitions, and regions where both types of transitions interact.These Monte Carlo-generated steady-state configurations are used as input to construct and train a convolutional neural network, from which we determine the critical points $p_{c}$ for different probabilities $q$. Furthermore, by learning the steady-state configurations associated with the superheated point $p=p_u$, we locate the tricritical point at $q_{t}=0.893$. Simultaneously, we employed a three-output CNN model to obtain the phase transition boundaries and the range of the crossover regions. Our method offers a neural network-based approach to capture critical points and distinguish phase transition boundaries, providing a novel solution to this problem.

cond-mat.stat-mech↗

arXiv2024

Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation

The literature on text-to-image generation is plagued by issues of faithfully composing entities with relations. But there lacks a formal understanding of how entity-relation compositions can be effectively learned. Moreover, the underlying phenomenon space that meaningfully reflects the problem structure is not well-defined, leading to an arms race for larger quantities of data in the hope that generalization emerges out of large-scale pretraining. We hypothesize that the underlying phenomenological coverage has not been proportionally scaled up, leading to a skew of the presented phenomenon which harms generalization. We introduce statistical metrics that quantify both the linguistic and visual skew of a dataset for relational learning, and show that generalization failures of text-to-image generation are a direct result of incomplete or unbalanced phenomenological coverage. We first perform experiments in a synthetic domain and demonstrate that systematically controlled metrics are strongly predictive of generalization performance. Then we move to natural images and show that simple distribution perturbations in light of our theories boost generalization without enlarging the absolute data size. This work informs an important direction towards quality-enhancing the data diversity or balance orthogonal to scaling up the absolute size. Our discussions point out important open questions on 1) Evaluation of generated entity-relation compositions, and 2) Better models for reasoning with abstract relations.

cs.LG↗

arXiv2024

Coherent Phonons, Localization and Slow Polaron Formation in Lead-free Gold Perovskite

Lead-free metal halide perovskites are emerging as less-toxic alternatives to their lead-based counterparts. However, their applicability in optoelectronic devices is limited, and the charge transport dynamics remain poorly understood. Understanding photo-induced charge and structural dynamics is critical for unlocking the potential of these novel systems. In this work, we employ ultrafast optical and Raman spectroscopy combined with band structure calculations to investigate the coupled electronic and vibrational dynamics in Caesium gold bromide, a promising lead-free perovskite. We find that the band-edge charge transfer states are strongly coupled to Au-Br stretching phonon modes, leading to frequency modulation of absorption by impulsively excited coherent phonons. Early-stage relaxation is characterized by dynamics of delocalized charge transfer excitation and slowly decaying coherent phonons. The electronic and vibrational relaxation reveals a slow formation of a localized polaronic state in the 10-20 ps timescale. Using a displaced harmonic oscillator model, the polaronic binding energy is estimated to be ~80 meV following lattice relaxation along the phonon modes. Strong exciton-phonon coupling and slow polaron formation via coupling to lattice modes make this material a promising testbed for the control of coherent phonons and localized polaronic states using light.

cond-mat.mtrl-sci↗

arXiv2024

The Discovery of Polarized Water Vapor Megamaser Emission in a Molecular Accretion Disk

For the first time in an extragalactic source, we detect linearly polarized water maser emission associated with the molecular accretion disk of NGC 1068. The position angles of the electric polarization vectors are perpendicular to the axes of filamentary structures in the molecular accretion disk. The inferred magnetic field threading the molecular disk must lie within approximately 35 degrees of the sky plane. The orientation of the magnetic fields relative to the disk plane implies that the maser region is unstable to hydromagnetically powered outflow; we speculate that the maser region may be the source of the larger scale molecular outflow found in ALMA studies. The new VLBI observations also reveal a compact radio continuum source, NGC 1068*, aligned with the near-systemic maser spots. The molecular accretion disk must be viewed nearly edge-on, and the revised central mass is (16.6 +/- 0.1) million solar masses.

astro-ph.GA↗

arXiv2024

Improving constraints on the extended mass distribution in the Galactic Center with stellar orbits

Studying the orbital motion of stars around Sagittarius A* in the Galactic Center provides a unique opportunity to probe the gravitational potential near the supermassive black hole at the heart of our Galaxy. Interferometric data obtained with the GRAVITY instrument at the Very Large Telescope Interferometer (VLTI) since 2016 has allowed us to achieve unprecedented precision in tracking the orbits of these stars. GRAVITY data have been key to detecting the in-plane, prograde Schwarzschild precession of the orbit of the star S2, as predicted by General Relativity. By combining astrometric and spectroscopic data from multiple stars, including S2, S29, S38, and S55 - for which we have data around their time of pericenter passage with GRAVITY - we can now strengthen the significance of this detection to an approximately $10 σ$ confidence level. The prograde precession of S2's orbit provides valuable insights into the potential presence of an extended mass distribution surrounding Sagittarius A*, which could consist of a dynamically relaxed stellar cusp comprised of old stars and stellar remnants, along with a possible dark matter spike. Our analysis, based on two plausible density profiles - a power-law and a Plummer profile - constrains the enclosed mass within the orbit of S2 to be consistent with zero, establishing an upper limit of approximately $1200 \, M_\odot$ with a $1 σ$ confidence level. This significantly improves our constraints on the mass distribution in the Galactic Center. Our upper limit is very close to the expected value from numerical simulations for a stellar cusp in the Galactic Center, leaving little room for a significant enhancement of dark matter density near Sagittarius A*.

astro-ph.GA↗

arXiv2024

MLIC: Multi-Reference Entropy Model for Learned Image Compression

Recently, learned image compression has achieved remarkable performance. The entropy model, which estimates the distribution of the latent representation, plays a crucial role in boosting rate-distortion performance. However, most entropy models only capture correlations in one dimension, while the latent representation contain channel-wise, local spatial, and global spatial correlations. To tackle this issue, we propose the Multi-Reference Entropy Model (MEM) and the advanced version, MEM$^+$. These models capture the different types of correlations present in latent representation. Specifically, We first divide the latent representation into slices. When decoding the current slice, we use previously decoded slices as context and employ the attention map of the previously decoded slice to predict global correlations in the current slice. To capture local contexts, we introduce two enhanced checkerboard context capturing techniques that avoids performance degradation. Based on MEM and MEM$^+$, we propose image compression models MLIC and MLIC$^+$. Extensive experimental evaluations demonstrate that our MLIC and MLIC$^+$ models achieve state-of-the-art performance, reducing BD-rate by $8.05\%$ and $11.39\%$ on the Kodak dataset compared to VTM-17.0 when measured in PSNR. Our code is available at https://github.com/JiangWeibeta/MLIC.

eess.IV↗

arXiv2024

Water-induced high-performance quantum-dot light-emitting diodes

Solution-processed light-emitting diodes (LEDs) are appealing for their potential in the low-cost fabrication of large-area devices. However, the limited performance of solution-processed blue LEDs, particularly their short operation lifetime, is hindering their practical use in display technologies. Here, we demonstrate that trace water in device, previously considered detrimental to most solution-processed LEDs, dramatically enhances the performance of quantum-dot LEDs (QLEDs). This breakthrough stems from our comprehensive mechanism investigations into the positive ageing phenomenon, a long-standing puzzle in the QLED field. Our findings reveal that water passivation on the surface of electron-transport layers, which are composed of zinc-oxide-based nanoparticles, improves charge transport and enhances exciton radiative recombination during device operation. Combined with the advanced top-emitting architecture, our blue QLEDs achieve a high current efficiency of 35.5 cd A-1, a blue index (colour coordinate corrected current efficiency) of over 470 cd A-1 CIEy-1, and unprecedented stability, with an extrapolated T95 lifetime (at an initial brightness of 1,000 cd m-2) of 287 hours. Our work may inspire further exploration into surface passivation of nanocrystalline functional layers, critical for the advancement of emerging solution-processed optoelectronic and electronic devices.

physics.optics↗

arXiv2024

Hierarchical Attention and Parallel Filter Fusion Network for Multi-Source Data Classification

Hyperspectral image (HSI) and synthetic aperture radar (SAR) data joint classification is a crucial and yet challenging task in the field of remote sensing image interpretation. However, feature modeling in existing methods is deficient to exploit the abundant global, spectral, and local features simultaneously, leading to sub-optimal classification performance. To solve the problem, we propose a hierarchical attention and parallel filter fusion network for multi-source data classification. Concretely, we design a hierarchical attention module for hyperspectral feature extraction. This module integrates global, spectral, and local features simultaneously to provide more comprehensive feature representation. In addition, we develop parallel filter fusion module which enhances cross-modal feature interactions among different spatial locations in the frequency domain. Extensive experiments on two multi-source remote sensing data classification datasets verify the superiority of our proposed method over current state-of-the-art classification approaches. Specifically, our proposed method achieves 91.44% and 80.51% of overall accuracy (OA) on the respective datasets, highlighting its superior performance.

eess.IV↗

arXiv2024

Hardware Architecture Design of Model-Based Image Reconstruction Towards Palm-size Photoacoustic Tomography

Photoacoustic (PA) imaging technology combines the advantages of optical imaging and ultrasound imaging, showing great potential in biomedical applications. Many preclinical studies and clinical applications urgently require fast, high-quality, low-cost and portable imaging system. Translating advanced image reconstruction algorithms into hardware implementations is highly desired. However, existing iterative PA image reconstructions, although exhibit higher accuracy than delay-and-sum algorithm, suffer from high computational cost. In this paper, we introduce a model-based hardware acceleration architecture based on superposed Wave (s-Wave) for palm-size PA tomography (palm-PAT), aiming at enhancing both the speed and performance of image reconstruction at a much lower system cost. To achieve this, we propose an innovative data reuse method that significantly reduces hardware storage resource consumption. We conducted experiments by FPGA implementation of the algorithm, using both phantoms and in vivo human finger data to verify the feasibility of the proposed method. The results demonstrate that our proposed architecture can substantially reduce system cost while maintaining high imaging performance. The hardware-accelerated implementation of the model-based algorithm achieves a speedup of up to approximately 270 times compared to the CPU, while the corresponding energy efficiency ratio is improved by more than 2700 times.

eess.IV↗