arXiv subjects

Bin Liu

Publications and source records attributed to Bin Liu.

At least 217 records · Page 12Linked to original sources

arXiv2024

Change Point Detection for High-dimensional Linear Models: A General Tail-adaptive Approach

We propose a novel approach for detecting change points in high-dimensional linear regression models. Unlike previous research that relied on strict Gaussian/sub-Gaussian error assumptions and had prior knowledge of change points, we propose a tail-adaptive method for change point detection and estimation. We use a weighted combination of composite quantile and least squared losses to build a new loss function, allowing us to leverage information from both conditional means and quantiles. For change point testing, we develop a family of individual testing statistics with different weights to account for unknown tail structures. These individual tests are further aggregated to construct a powerful tail-adaptive test for sparse regression coefficient changes. For change point estimation, we propose a family of argmax-based individual estimators. We provide theoretical justifications for the validity of these tests and change point estimators. Additionally, we introduce a new algorithm for detecting multiple change points in a tail-adaptive manner using the wild binary segmentation. Extensive numerical results show the effectiveness of our method. Lastly, an R package called ``TailAdaptiveCpt" is developed to implement our algorithms.

stat.ME↗

arXiv2024

New galaxy UV luminosity constraints on warm dark matter from JWST

We exploit the recent {\it James Webb Space Telescope} (JWST) determination of galaxy UV luminosity functions over the redshift range $z=9-14.5$ to derive constraints on warm dark matter (WDM) models. The delayed structure formation in WDM universes make high-redshift observations a powerful probe to set limits on the particle mass $m_\mathrm{x}$ of WDM candidates. By integrating these observations with blank-field surveys conducted by the {\it Hubble Space Telescope} (HST) at redshifts $z=4-8$, we impose constraints on both astrophysical parameters ($β$, $γ$, $ε_{\mathrm N}$, $M_c$ for a double-power law star formation efficiency, and $σ_{M_{\mathrm{UV}}}$ for a Gaussian magnitude-halo mass relation) and the WDM parameter (dark matter particle mass $m_\mathrm{x}$) simultaneously. We find a new limit of $m_\mathrm{x} \geq 3.2$ keV for the mass of thermal relic WDM particles at $95\%$ confidence level. This bound is tighter than the most stringent result derived using HST data before. Future JWST observations could further reduce the observation uncertainties and improve this constraint.

astro-ph.CO↗

arXiv2024

Struggle with Adversarial Defense? Try Diffusion

Adversarial attacks induce misclassification by introducing subtle perturbations. Recently, diffusion models are applied to the image classifiers to improve adversarial robustness through adversarial training or by purifying adversarial noise. However, diffusion-based adversarial training often encounters convergence challenges and high computational expenses. Additionally, diffusion-based purification inevitably causes data shift and is deemed susceptible to stronger adaptive attacks. To tackle these issues, we propose the Truth Maximization Diffusion Classifier (TMDC), a generative Bayesian classifier that builds upon pre-trained diffusion models and the Bayesian theorem. Unlike data-driven classifiers, TMDC, guided by Bayesian principles, utilizes the conditional likelihood from diffusion models to determine the class probabilities of input images, thereby insulating against the influences of data shift and the limitations of adversarial training. Moreover, to enhance TMDC's resilience against more potent adversarial attacks, we propose an optimization strategy for diffusion classifiers. This strategy involves post-training the diffusion model on perturbed datasets with ground-truth labels as conditions, guiding the diffusion model to learn the data distribution and maximizing the likelihood under the ground-truth labels. The proposed method achieves state-of-the-art performance on the CIFAR10 dataset against heavy white-box attacks and strong adaptive attacks. Specifically, TMDC achieves robust accuracies of 82.81% against $l_{\infty}$ norm-bounded perturbations and 86.05% against $l_{2}$ norm-bounded perturbations, respectively, with $ε=0.05$.

cs.CV↗

arXiv2024

Annealed adaptive importance sampling method in PINNs for solving high dimensional partial differential equations

Physics-informed neural networks (PINNs) have emerged as powerful tools for solving a wide range of partial differential equations (PDEs). However, despite their user-friendly interface and broad applicability, PINNs encounter challenges in accurately resolving PDEs, especially when dealing with singular cases that may lead to unsatisfactory local minima. To address these challenges and improve solution accuracy, we propose an innovative approach called Annealed Adaptive Importance Sampling (AAIS) for computing the discretized PDE residuals of the cost functions, inspired by the Expectation Maximization algorithm used in finite mixtures to mimic target density. Our objective is to approximate discretized PDE residuals by strategically sampling additional points in regions with elevated residuals, thus enhancing the effectiveness and accuracy of PINNs. Implemented together with a straightforward resampling strategy within PINNs, our AAIS algorithm demonstrates significant improvements in efficiency across a range of tested PDEs, even with limited training datasets. Moreover, our proposed AAIS-PINN method shows promising capabilities in solving high-dimensional singular PDEs. The adaptive sampling framework introduced here can be integrated into various PINN frameworks.

math.NA↗

arXiv2024

MERBench: A Unified Evaluation Benchmark for Multimodal Emotion Recognition

Multimodal emotion recognition plays a crucial role in enhancing user experience in human-computer interaction. Over the past few decades, researchers have proposed a series of algorithms and achieved impressive progress. Although each method shows its superior performance, different methods lack a fair comparison due to inconsistencies in feature extractors, evaluation manners, and experimental settings. These inconsistencies severely hinder the development of this field. Therefore, we build MERBench, a unified evaluation benchmark for multimodal emotion recognition. We aim to reveal the contribution of some important techniques employed in previous works, such as feature selection, multimodal fusion, robustness analysis, fine-tuning, pre-training, etc. We hope this benchmark can provide clear and comprehensive guidance for follow-up researchers. Based on the evaluation results of MERBench, we further point out some promising research directions. Additionally, we introduce a new emotion dataset MER2023, focusing on the Chinese language environment. This dataset can serve as a benchmark dataset for research on multi-label learning, noise robustness, and semi-supervised learning. We encourage the follow-up researchers to evaluate their algorithms under the same experimental setup as MERBench for fair comparisons. Our code is available at: https://github.com/zeroQiaoba/MERTools.

cs.HC↗

arXiv2024

HiGraphDTI: Hierarchical Graph Representation Learning for Drug-Target Interaction Prediction

The discovery of drug-target interactions (DTIs) plays a crucial role in pharmaceutical development. The deep learning model achieves more accurate results in DTI prediction due to its ability to extract robust and expressive features from drug and target chemical structures. However, existing deep learning methods typically generate drug features via aggregating molecular atom representations, ignoring the chemical properties carried by motifs, i.e., substructures of the molecular graph. The atom-drug double-level molecular representation learning can not fully exploit structure information and fails to interpret the DTI mechanism from the motif perspective. In addition, sequential model-based target feature extraction either fuses limited contextual information or requires expensive computational resources. To tackle the above issues, we propose a hierarchical graph representation learning-based DTI prediction method (HiGraphDTI). Specifically, HiGraphDTI learns hierarchical drug representations from triple-level molecular graphs to thoroughly exploit chemical information embedded in atoms, motifs, and molecules. Then, an attentional feature fusion module incorporates information from different receptive fields to extract expressive target features.Last, the hierarchical attention mechanism identifies crucial molecular segments, which offers complementary views for interpreting interaction mechanisms. The experiment results not only demonstrate the superiority of HiGraphDTI to the state-of-the-art methods, but also confirm the practical ability of our model in interaction interpretation and new DTI discovery.

cs.LG↗

arXiv2024

Data Generation-based Operator Learning for Solving Partial Differential Equations on Unbounded Domains

Wave propagation problems are typically formulated as partial differential equations (PDEs) on unbounded domains to be solved. The classical approach to solving such problems involves truncating them to problems on bounded domains by designing the artificial boundary conditions or perfectly matched layers, which typically require significant effort, and the presence of nonlinearity in the equation makes such designs even more challenging. Emerging deep learning-based methods for solving PDEs, with the physics-informed neural networks (PINNs) method as a representative, still face significant challenges when directly used to solve PDEs on unbounded domains. Calculations performed in a bounded domain of interest without imposing boundary constraints can lead to a lack of unique solutions thus causing the failure of PINNs. In light of this, this paper proposes a novel and effective operator learning-based method for solving PDEs on unbounded domains. The key idea behind this method is to generate high-quality training data. Specifically, we construct a family of approximate analytical solutions to the target PDE based on its initial condition and source term. Then, using these constructed data comprising exact solutions, initial conditions, and source terms, we train an operator learning model called MIONet, which is capable of handling multiple inputs, to learn the mapping from the initial condition and source term to the PDE solution on a bounded domain of interest. Finally, we utilize the generalization ability of this model to predict the solution of the target PDE. The effectiveness of this method is exemplified by solving the wave equation and the Schrodinger equation defined on unbounded domains. More importantly, the proposed method can deal with nonlinear problems, which has been demonstrated by solving Burger's equation and Korteweg-de Vries (KdV) equation.

math.NA↗

arXiv2024

In-situ tunable giant electrical anisotropy in a grating gated AlGaN/GaN two-dimensional electron gas

Materials with in-plane electrical anisotropy have great potential for designing artificial synaptic devices. However, natural materials with strong intrinsic in-plane electrical anisotropy are rare. We introduce a simple strategy to produce extremely large electrical anisotropy via grating gating of a semiconductor two-dimensional electron gas (2DEG) of AlGaN/GaN. We show that periodically modulated electric potential in the 2DEG induces in-plane electrical anisotropy, which is significantly enhanced in a magnetic field, leading to an ultra large electrical anisotropy. This is induced by a giant positive magnetoresistance and a giant negative magnetoresistance under two orthogonally oriented in-plane current flows, respectively. This giant electrical anisotropy is in-situ tunable by tailoring both the grating gate voltage and the magnetic field. Our semiconductor device with controllable giant electrical anisotropy will stimulate new device applications, such as multi-terminal memtransistors and bionic synapses.

cond-mat.mes-hall↗

arXiv2024

Blind QSO reconstruction challenge: Exploring methods to reconstruct the Ly$α$ emission line of QSOs

Reconstructing the intrinsic Ly$α$ line flux from high-$z$ QSOs can place constraints on the neutral hydrogen content of the intergalactic medium during reionisation. There are now $\gtrsim10$ different Ly$α$ reconstruction pipelines using different methodologies to predict the Ly$α$ line flux from correlations with the spectral information redward of Ly$α$. However, there have been few attempts to directly compare the performance of these pipelines. Therefore, we devised a blind QSO challenge to compare these reconstruction pipelines on a uniform set of objects. Each author was provided de-identified, observed rest-frame QSO spectra with spectral information only redward of 1260Å rest-frame to ensure unbiased reconstruction. We constructed two samples of 30 QSOs, from X-Shooter and SDSS both spanning $3.5<z<4.5$. Importantly, the purpose of this comparison study was not to champion a single, best performing reconstruction pipeline but rather to explore the relative performance of these pipelines over a range of QSOs with broad observational characteristics to infer general trends. In summary, we find machine learning approaches in general provide the strongest ``best guesses" but underestimate the accompanying statistical uncertainty, although these can be recalibrated, whilst pipelines that decompose the spectral information, for example principal component or factor analysis generally perform better at predicting the Ly$α$ profile. Further, we found that reconstruction pipelines trained on SDSS QSOs performed similarly on average for both the X-Shooter and SDSS samples indicating no discernible biases owing to differences in the observational characteristics of the training set or QSO being reconstructed, although the recovered distributions of reconstructions for X-Shooter were broader likely due to an increased fraction of outliers.

astro-ph.CO↗

arXiv2024

HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition

Audio-Visual Emotion Recognition (AVER) has garnered increasing attention in recent years for its critical role in creating emotion-ware intelligent machines. Previous efforts in this area are dominated by the supervised learning paradigm. Despite significant progress, supervised learning is meeting its bottleneck due to the longstanding data scarcity issue in AVER. Motivated by recent advances in self-supervised learning, we propose Hierarchical Contrastive Masked Autoencoder (HiCMAE), a novel self-supervised framework that leverages large-scale self-supervised pre-training on vast unlabeled audio-visual data to promote the advancement of AVER. Following prior arts in self-supervised audio-visual representation learning, HiCMAE adopts two primary forms of self-supervision for pre-training, namely masked data modeling and contrastive learning. Unlike them which focus exclusively on top-layer representations while neglecting explicit guidance of intermediate layers, HiCMAE develops a three-pronged strategy to foster hierarchical audio-visual feature learning and improve the overall quality of learned representations. To verify the effectiveness of HiCMAE, we conduct extensive experiments on 9 datasets covering both categorical and dimensional AVER tasks. Experimental results show that our method significantly outperforms state-of-the-art supervised and self-supervised audio-visual methods, which indicates that HiCMAE is a powerful audio-visual emotion representation learner. Codes and models will be publicly available at https://github.com/sunlicai/HiCMAE.

cs.CV↗

arXiv2024

Multi-Label Adaptive Batch Selection by Highlighting Hard and Imbalanced Samples

Deep neural network models have demonstrated their effectiveness in classifying multi-label data from various domains. Typically, they employ a training mode that combines mini-batches with optimizers, where each sample is randomly selected with equal probability when constructing mini-batches. However, the intrinsic class imbalance in multi-label data may bias the model towards majority labels, since samples relevant to minority labels may be underrepresented in each mini-batch. Meanwhile, during the training process, we observe that instances associated with minority labels tend to induce greater losses. Existing heuristic batch selection methods, such as priority selection of samples with high contribution to the objective function, i.e., samples with high loss, have been proven to accelerate convergence while reducing the loss and test error in single-label data. However, batch selection methods have not yet been applied and validated in multi-label data. In this study, we introduce a simple yet effective adaptive batch selection algorithm tailored to multi-label deep learning models. It adaptively selects each batch by prioritizing hard samples related to minority labels. A variant of our method also takes informative label correlations into consideration. Comprehensive experiments combining five multi-label deep learning models on thirteen benchmark datasets show that our method converges faster and performs better than random batch selection.

cs.LG↗

arXiv2024

Facile synthesis of micro-flower NiCo2O4 assembled by nanosheets efficient for electrocatalysis of water

Effective regulation of the morphology of transition metal spinel structures is crucial for creating efficient and stable bifunctional catalysts for electrocatalysis of water. In this work, micro-flower NiCo2O4 (F-NCO) assembled by nanosheets via a chemical template method for the simultaneous promotion of hydrogen evolution reaction (HER) and oxygen evolution reaction (OER). Electronic microscope analysis revealed that the thickness of the F-NCO catalyst was only 2.7% of that of the NiCo2O4 bulk (B-NCO), and this ultrathin lamellar structure was conducive to further exposure of the active site and improved reaction kinetics. The F-NCO catalyst exhibited superior HER and OER performance (10 = 236 and 310 mV) and robust long-term stability over the B-NCO catalyst in 1.0 M KOH, with a 2.68-fold and 4.16-fold increase in active surface area and a 0.42-fold and 0.61-fold decrease in charge transfer resistance values, respectively. This micro-flower-structured electrode has remarkable electrocatalytic property and long-term durability, providing a novel insight for characterizing cost-effective and high-performance bifunctional electrocatalysts.

physics.chem-ph↗

arXiv2024

Multimodal Fusion with Pre-Trained Model Features in Affective Behaviour Analysis In-the-wild

Multimodal fusion is a significant method for most multimodal tasks. With the recent surge in the number of large pre-trained models, combining both multimodal fusion methods and pre-trained model features can achieve outstanding performance in many multimodal tasks. In this paper, we present our approach, which leverages both advantages for addressing the task of Expression (Expr) Recognition and Valence-Arousal (VA) Estimation. We evaluate the Aff-Wild2 database using pre-trained models, then extract the final hidden layers of the models as features. Following preprocessing and interpolation or convolution to align the extracted features, different models are employed for modal fusion. Our code is available at GitHub - FulgenceWen/ABAW6th.

cs.CV↗

arXiv2024

MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators

Generating realistic human motion from given action descriptions has experienced significant advancements because of the emerging requirement of digital humans. While recent works have achieved impressive results in generating motion directly from textual action descriptions, they often support only a single modality of the control signal, which limits their application in the real digital human industry. This paper presents a Motion General-Purpose generaTor (MotionGPT) that can use multimodal control signals, e.g., text and single-frame poses, for generating consecutive human motions by treating multimodal signals as special input tokens in large language models (LLMs). Specifically, we first quantize multimodal control signals into discrete codes and then formulate them in a unified prompt instruction to ask the LLMs to generate the motion answer. Our MotionGPT demonstrates a unified human motion generation model with multimodal control signals by tuning a mere 0.4% of LLM parameters. To the best of our knowledge, MotionGPT is the first method to generate human motion by multimodal control signals, which we hope can shed light on this new direction. Visit our webpage at https://qiqiapink.github.io/MotionGPT/.

cs.CV↗

arXiv2024

GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognition

Recently, GPT-4 with Vision (GPT-4V) has demonstrated remarkable visual capabilities across various tasks, but its performance in emotion recognition has not been fully evaluated. To bridge this gap, we present the quantitative evaluation results of GPT-4V on 21 benchmark datasets covering 6 tasks: visual sentiment analysis, tweet sentiment analysis, micro-expression recognition, facial emotion recognition, dynamic facial emotion recognition, and multimodal emotion recognition. This paper collectively refers to these tasks as ``Generalized Emotion Recognition (GER)''. Through experimental analysis, we observe that GPT-4V exhibits strong visual understanding capabilities in GER tasks. Meanwhile, GPT-4V shows the ability to integrate multimodal clues and exploit temporal information, which is also critical for emotion recognition. However, it's worth noting that GPT-4V is primarily designed for general domains and cannot recognize micro-expressions that require specialized knowledge. To the best of our knowledge, this paper provides the first quantitative assessment of GPT-4V for GER tasks. We have open-sourced the code and encourage subsequent researchers to broaden the evaluation scope by including more tasks and datasets. Our code and evaluation results are available at: https://github.com/zeroQiaoba/gpt4v-emotion.

cs.CV↗

arXiv2024

GT-Rain Single Image Deraining Challenge Report

This report reviews the results of the GT-Rain challenge on single image deraining at the UG2+ workshop at CVPR 2023. The aim of this competition is to study the rainy weather phenomenon in real world scenarios, provide a novel real world rainy image dataset, and to spark innovative ideas that will further the development of single image deraining methods on real images. Submissions were trained on the GT-Rain dataset and evaluated on an extension of the dataset consisting of 15 additional scenes. Scenes in GT-Rain are comprised of real rainy image and ground truth image captured moments after the rain had stopped. 275 participants were registered in the challenge and 55 competed in the final testing phase.

cs.CV↗

arXiv2024

Towards More Unified In-context Visual Understanding

The rapid advancement of large language models (LLMs) has accelerated the emergence of in-context learning (ICL) as a cutting-edge approach in the natural language processing domain. Recently, ICL has been employed in visual understanding tasks, such as semantic segmentation and image captioning, yielding promising results. However, existing visual ICL framework can not enable producing content across multiple modalities, which limits their potential usage scenarios. To address this issue, we present a new ICL framework for visual understanding with multi-modal output enabled. First, we quantize and embed both text and visual prompt into a unified representational space, structured as interleaved in-context sequences. Then a decoder-only sparse transformer architecture is employed to perform generative modeling on them, facilitating in-context learning. Thanks to this design, the model is capable of handling in-context vision understanding tasks with multimodal output in a unified pipeline.Experimental results demonstrate that our model achieves competitive performance compared with specialized models and previous ICL baselines. Overall, our research takes a further step toward unified multimodal in-context learning.

cs.CV↗

arXiv2024

The Gravitational Wave Forms of Galactic Compact Binaries with Mass-Transfer Correction

In this paper, we focus on the effect of mass-transfer between compact binaries like neutron-star-neutron-star (NS-NS) systems and neutron-star-white-dwarf (NS-WD) systems on gravitational waves (GWs). We adopt the mass quadrupole formula with 2.5 order Post-Newtonian (2.5 PN) approximation to calculate the GW radiation and the orbital evolution. After a reasonable discussion of astrophysical processes concerning our scenario, two kinds of mass-transfer models are applied here. One is the mass overflow of the atmosphere, where the companion star orbits into the primary's Roche limit and its atmosphere overflows into the common envelope. The other one is the tidal disruption of the core, which is viewed as incompressible fluid towards the primary star, and in the near region branches into an accretion disc (AD) and direct accretion flow. Viewing this envelope and as a background, the GW of its spin can be calculated as a rotating non-spherically symmetric star. We eventually obtained the corrected gravitational waveform (GWF) templates for different initial states in the inspiral phase.

gr-qc↗