Searcharxiv⌕ Search

arXiv subjects

Bin Liu

Publications and source records attributed to Bin Liu.

At least 289 records · Page 16Linked to original sources
arXiv2023

ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning

Noisy partial label learning (noisy PLL) is an important branch of weakly supervised learning. Unlike PLL where the ground-truth label must conceal in the candidate label set, noisy PLL relaxes this constraint and allows the ground-truth label may not be in the candidate label set. To address this challenging problem, most of the existing works attempt to detect noisy samples and estimate the ground-truth label for each noisy sample. However, detection errors are unavoidable. These errors can accumulate during training and continuously affect model optimization. To this end, we propose a novel framework for noisy PLL with theoretical guarantees, called ``Adjusting Label Importance Mechanism (ALIM)''. It aims to reduce the negative impact of detection errors by trading off the initial candidate set and model outputs. ALIM is a plug-in strategy that can be integrated with existing PLL approaches. Experimental results on benchmark datasets demonstrate that our method can achieve state-of-the-art performance on noisy PLL. \textcolor[rgb]{0.93,0.0,0.47}{Our code can be found in Supplementary Material}.

cs.CV↗
arXiv2023

VRA: Variational Rectified Activation for Out-of-distribution Detection

Out-of-distribution (OOD) detection is critical to building reliable machine learning systems in the open world. Researchers have proposed various strategies to reduce model overconfidence on OOD data. Among them, ReAct is a typical and effective technique to deal with model overconfidence, which truncates high activations to increase the gap between in-distribution and OOD. Despite its promising results, is this technique the best choice for widening the gap? To answer this question, we leverage the variational method to find the optimal operation and verify the necessity of suppressing abnormally low and high activations and amplifying intermediate activations in OOD detection, rather than focusing only on high activations like ReAct. This motivates us to propose a novel technique called ``Variational Rectified Activation (VRA)'', which simulates these suppression and amplification operations using piecewise functions. Experimental results on multiple benchmark datasets demonstrate that our method outperforms existing post-hoc strategies. Meanwhile, VRA is compatible with different scoring functions and network architectures. \textcolor[rgb]{0.93,0.0,0.47}{Our code can be found in Supplementary Material}.

cs.LG↗
arXiv2023

Use the Detection Transformer as a Data Augmenter

Detection Transformer (DETR) is a Transformer architecture based object detection model. In this paper, we demonstrate that it can also be used as a data augmenter. We term our approach as DETR assisted CutMix, or DeMix for short. DeMix builds on CutMix, a simple yet highly effective data augmentation technique that has gained popularity in recent years. CutMix improves model performance by cutting and pasting a patch from one image onto another, yielding a new image. The corresponding label for this new example is specified as the weighted average of the original labels, where the weight is proportional to the area of the patch. CutMix selects a random patch to be cut. In contrast, DeMix elaborately selects a semantically rich patch, located by a pre-trained DETR. The label of the new image is specified in the same way as in CutMix. Experimental results on benchmark datasets for image classification demonstrate that DeMix significantly outperforms prior art data augmentation methods including CutMix. Oue code is available at https://github.com/ZJLAB-AMMI/DeMix.

cs.CV↗
arXiv2023

Robust Sequential Online Prediction with Dynamic Ensemble of Multiple Models: A Review

The use of time series for sequential online prediction (SOP) has long been a research topic, but achieving robust and computationally efficient SOP with non-stationary time series remains a challenge. This paper reviews a framework, called Bayesian Dynamic Ensemble of Multiple Models (BDEMM), which addresses SOP in a theoretically elegant way, and have found widespread use in various fields. BDEMM utilizes a model pool of weighted candidate models, adapted online using Bayesian formalism to capture possible temporal evolutions of the data. This review comprehensively describes BDEMM from five perspectives: its theoretical foundations, algorithms, practical applications, connections to other research, and strengths, limitations, and potential future directions.

stat.ME↗
arXiv2023

BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models

Image-to-image translation is an important and challenging problem in computer vision and image processing. Diffusion models (DM) have shown great potentials for high-quality image synthesis, and have gained competitive performance on the task of image-to-image translation. However, most of the existing diffusion models treat image-to-image translation as conditional generation processes, and suffer heavily from the gap between distinct domains. In this paper, a novel image-to-image translation method based on the Brownian Bridge Diffusion Model (BBDM) is proposed, which models image-to-image translation as a stochastic Brownian bridge process, and learns the translation between two domains directly through the bidirectional diffusion process rather than a conditional generation process. To the best of our knowledge, it is the first work that proposes Brownian Bridge diffusion process for image-to-image translation. Experimental results on various benchmarks demonstrate that the proposed BBDM model achieves competitive performance through both visual inspection and measurable metrics.

cs.CV↗
arXiv2023

Fine-Grained Selective Similarity Integration for Drug-Target Interaction Prediction

The discovery of drug-target interactions (DTIs) is a pivotal process in pharmaceutical development. Computational approaches are a promising and efficient alternative to tedious and costly wet-lab experiments for predicting novel DTIs from numerous candidates. Recently, with the availability of abundant heterogeneous biological information from diverse data sources, computational methods have been able to leverage multiple drug and target similarities to boost the performance of DTI prediction. Similarity integration is an effective and flexible strategy to extract crucial information across complementary similarity views, providing a compressed input for any similarity-based DTI prediction model. However, existing similarity integration methods filter and fuse similarities from a global perspective, neglecting the utility of similarity views for each drug and target. In this study, we propose a Fine-Grained Selective similarity integration approach, called FGS, which employs a local interaction consistency-based weight matrix to capture and exploit the importance of similarities at a finer granularity in both similarity selection and combination steps. We evaluate FGS on five DTI prediction datasets under various prediction settings. Experimental results show that our method not only outperforms similarity integration competitors with comparable computational costs, but also achieves better prediction performance than state-of-the-art DTI prediction approaches by collaborating with conventional base models. Furthermore, case studies on the analysis of similarity weights and on the verification of novel predictions confirm the practical ability of FGS.

cs.AI↗
arXiv2023

Q-Net: Query-Informed Few-Shot Medical Image Segmentation

Deep learning has achieved tremendous success in computer vision, while medical image segmentation (MIS) remains a challenge, due to the scarcity of data annotations. Meta-learning techniques for few-shot segmentation (Meta-FSS) have been widely used to tackle this challenge, while they neglect possible distribution shifts between the query image and the support set. In contrast, an experienced clinician can perceive and address such shifts by borrowing information from the query image, then fine-tune or calibrate her prior cognitive model accordingly. Inspired by this, we propose Q-Net, a Query-informed Meta-FSS approach, which mimics in spirit the learning mechanism of an expert clinician. We build Q-Net based on ADNet, a recently proposed anomaly detection-inspired method. Specifically, we add two query-informed computation modules into ADNet, namely a query-informed threshold adaptation module and a query-informed prototype refinement module. Combining them with a dual-path extension of the feature extraction module, Q-Net achieves state-of-the-art performance on widely used abdominal and cardiac magnetic resonance (MR) image datasets. Our work sheds light on a novel way to improve Meta-FSS techniques by leveraging query information.

cs.CV↗
arXiv2023

Pose-Controllable 3D Facial Animation Synthesis using Hierarchical Audio-Vertex Attention

Most of the existing audio-driven 3D facial animation methods suffered from the lack of detailed facial expression and head pose, resulting in unsatisfactory experience of human-robot interaction. In this paper, a novel pose-controllable 3D facial animation synthesis method is proposed by utilizing hierarchical audio-vertex attention. To synthesize real and detailed expression, a hierarchical decomposition strategy is proposed to encode the audio signal into both a global latent feature and a local vertex-wise control feature. Then the local and global audio features combined with vertex spatial features are used to predict the final consistent facial animation via a graph convolutional neural network by fusing the intrinsic spatial topology structure of the face model and the corresponding semantic feature of the audio. To accomplish pose-controllable animation, we introduce a novel pose attribute augmentation method by utilizing the 2D talking face technique. Experimental results indicate that the proposed method can produce more realistic facial expressions and head posture movements. Qualitative and quantitative experiments show that the proposed method achieves competitive performance against state-of-the-art methods.

cs.CV↗
arXiv2023

Feasible Region for DERs in Unbalanced Distribution Networks with Uncertain Line Impedances

The rapid development of distributed energy resources (DERs) has brought many challenges to the operation of distribution networks in recent years, where operating envelopes (OEs), as a key enabler to facilitate DER integration via virtual power plants, have attracted increasing attention. Geometrically, OEs are inherently linked to the feasible region (FR) concept, which depicts an area that quantifies the permissible operational ranges for all DERs. This paper studies how to calculate FR for DERs based on a linear unbalanced three-phase power flow model while considering uncertainties from measured/estimated network impedances, leading to the robust feasible region (RFR). With an initialised FR, the proposed solution algorithm aims to seek the RFR by solving a non-convex bilinear problem, formulated based on Motzkin Transposition Theorem, and updating the RFR alternatively until reaching convergence. Two cases, including a 2-bus illustrative network and a representative Australian network, have been tested to demonstrate the effectiveness of the proposed approach.

math.OC↗
arXiv2023

3D Colored Shape Reconstruction from a Single RGB Image through Diffusion

We propose a novel 3d colored shape reconstruction method from a single RGB image through diffusion model. Diffusion models have shown great development potentials for high-quality 3D shape generation. However, most existing work based on diffusion models only focus on geometric shape generation, they cannot either accomplish 3D reconstruction from a single image, or produce 3D geometric shape with color information. In this work, we propose to reconstruct a 3D colored shape from a single RGB image through a novel conditional diffusion model. The reverse process of the proposed diffusion model is consisted of three modules, shape prediction module, color prediction module and NeRF-like rendering module. In shape prediction module, the reference RGB image is first encoded into a high-level shape feature and then the shape feature is utilized as a condition to predict the reverse geometric noise in diffusion model. Then the color of each 3D point updated in shape prediction module is predicted by color prediction module. Finally, a NeRF-like rendering module is designed to render the colored point cloud predicted by the former two modules to 2D image space to guide the training conditioned only on a reference image. As far as the authors know, the proposed method is the first diffusion model for 3D colored shape reconstruction from a single RGB image. Experimental results demonstrate that the proposed method achieves competitive performance on colored 3D shape reconstruction, and the ablation study validates the positive role of the color prediction module in improving the reconstruction quality of 3D geometric point cloud.

cs.CV↗
arXiv2023

High-entropy silicide superconductors with W$_{5}$Si$_{3}$-type structure

We report the synthesis, crystal structure and physical properties of two new high-entropy silicides (HESs), namely (Nb$_{0.1}$Mo$_{0.3}$W$_{0.3}$Re$_{0.2}$Ru$_{0.1}$)$_{5}$Si$_{3}$ and (Nb$_{0.2}$Mo$_{0.3}$W$_{0.3}$Re$_{0.1}$Ru$_{0.1}$)$_{5}$Si$_{3}$. Structural analysis indicates that both HESs consist of a (nearly) single tetragonal W$_{5}$Si$_{3}$-type phase (space group $I$4/$mcm$) with a disordered cation distribution. Electrical resistivity, magnetic susceptibility and specific heat measurements show that (Nb$_{0.1}$Mo$_{0.3}$W$_{0.3}$Re$_{0.2}$Ru$_{0.1}$)$_{5}$Si$_{3}$ and (Nb$_{0.2}$Mo$_{0.3}$W$_{0.3}$Re$_{0.1}$Ru$_{0.1}$)$_{5}$Si$_{3}$ are weakly coupled bulk superconductors, which represent the first superconducting high-entropy nonoxide ceramics. In particular, these HESs have higher $T_{\rm c}$ values (3.2-3.3 K) compared with those of the binary counterparts, and their $B_{\rm c2}$(0)/$T_{\rm c}$ ratios are the largest among superconductors of the same structural type.

cond-mat.supr-con↗
arXiv2023

Universality in nonlinear passage through the miscible-immiscible phase transition in two component Bose-Einstein condensates

In this study, we investigate the formation of domain defects and the universal critical real-time dynamics in a two-component Bose-Einstein condensate with nonlinear quenching across the miscible-immiscible phase transition. By analyzing the Bogoliubov excitations, we obtain the power-law relations among the defect density, the phase transition delay and the quench time near the phase transition. Moreover, by simulating the real-time dynamics across the miscible-immiscible phase transition, we clearly show the formation of domain defects and the delay of the phase transition. Furthermore, we find that the domain defects are suppressed by large nonlinear coefficients and long quench times. To accurately characterize the domain defects, we quantify the defect excitations using the correlation length and the domain number. In addition, by combining the power-law relations between the phase transition delay and the quench time, we extract the critical exponents for different nonlinear coefficients. Our study not only confirms that the critical exponents do not sensitively depend on the nonlinear quenches but also provides a dynamic path toward the suppression of nonadiabatic excitation.

cond-mat.quant-gas↗
arXiv2023

Possible discrimination of black hole origins from the lensing rate of DECIGO and B-DECIGO sources

In this paper, we forecast the expected detection rates and redshift distributions of gravitationally lensed gravitational waves (GWs) from three different mass distributions of primordial black holes (PBHs) and two stellar formation models of astrophysical black holes (ABHs) in the context of DECi-hertz Interferometer Gravitational wave Observatory (DECIGO) and it's smaller scale version B-DECIGO. It suggests that DECIGO will be able to detect $10^4-10^5$ GW signals from such binary black holes (BBHs) each year and the event rate distributions for PBHs will differ from those for ABHs due to their different merger rate with respect to redshift. The large number of event rates make $5-100$ detections of lensed GW signals being possible. After considering the gravitational lensing effect, the difference between the detection rates and distributions for PBHs and ABHs will be more significant. Therefore, this can be served as a complementary method to distinguish PBHs from ABHs.

astro-ph.CO↗
arXiv2023

GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation

Conversations have become a critical data format on social media platforms. Understanding conversation from emotion, content and other aspects also attracts increasing attention from researchers due to its widespread application in human-computer interaction. In real-world environments, we often encounter the problem of incomplete modalities, which has become a core issue of conversation understanding. To address this problem, researchers propose various methods. However, existing approaches are mainly designed for individual utterances rather than conversational data, which cannot fully exploit temporal and speaker information in conversations. To this end, we propose a novel framework for incomplete multimodal learning in conversations, called "Graph Complete Network (GCNet)", filling the gap of existing works. Our GCNet contains two well-designed graph neural network-based modules, "Speaker GNN" and "Temporal GNN", to capture temporal and speaker dependencies. To make full use of complete and incomplete data, we jointly optimize classification and reconstruction tasks in an end-to-end manner. To verify the effectiveness of our method, we conduct experiments on three benchmark conversational datasets. Experimental results demonstrate that our GCNet is superior to existing state-of-the-art approaches in incomplete multimodal learning. Code is available at https://github.com/zeroQiaoba/GCNet.

cs.LG↗
arXiv2022

Personalized local heating neutralizing individual, spatial and temporal thermo-physiological variances in extreme cold environments

In this paper, we investigate the feasibility, robustness and optimization of introducing personal comfort systems (PCS), apparatuses that promises in energy saving and comfort improvement, into a broader range of environments. We report a series of laboratory experiments systematically examining the effect of personalized heating in neutralizing individual, spatial and temporal variations of thermal demands. The experiments were conducted in an artificial climate chamber at -15 degC in order to simulate extreme cold environments. We developed a heating garment with 20 pieces of 20 * 20 cm2 heating cloth (grouped into 9 regions) comprehensively covering human body. Surface temperatures of the garment can be controlled independently, quickly (within 20 seconds), precisely (within 1 degC) and easily (through a tablet) up to 45 degC. Participants were instructed to adjust surface temperatures of each segment to their preferences, with their physiological, psychological and adjustment data collected. We found that active heating could significantly and stably improve thermal satisfaction. The overall TSV and TCV were improved 1.50 and 1.53 during the self-adjustment phase. Preferred heating surface temperatures for different segments varied widely. Further, even for the same segment, individual differences among participants were considerable. Such variances were observed through local heating powers, while unnoticeable among thermal perception votes. In other words, all these various differences could be neutralized given the flexibility in personalized adjustments. Our research reaffirms the paradigm of "adaptive thermal comfort" and will promote innovations on human-centric design for more efficient PCSs.

cs.HC↗
arXiv2022

Vortex-ring quantum droplets in a radially-periodic potential

We establish stability and characteristics of two-dimensional (2D) vortex ring-shaped quantum droplets (QDs) formed by binary Bose-Einstein condensates (BECs). The system is modeled by the Gross-Pitaevskii (GP) equation with the cubic term multiplied by a logarithmic factor (as produced by the Lee-Huang-Yang correction to the mean-field theory) and a potential which is a periodic function of the radial coordinate. Narrow vortex rings with high values of the topological charge, trapped in particular circular troughs of the radial potential, are produced. These results suggest an experimentally relevant method for the creation of vortical QDs (thus far, only zero-vorticity ones have been reported). The 2D GP equation for the narrow rings is approximately reduced to the 1D form, which makes it possible to study the modulational stability of the rings against azimuthal perturbations. Full stability areas are delineated for these modes. The trapping capacity of the circular troughs is identified for the vortex rings with different winding numbers (WNs). Stable compound states in the form of mutually nested concentric multiple rings are constructed too, including ones with opposite signs of the WNs. Other robust compound states combine a modulationally stable narrow ring in one circular potential trough and an azimuthal soliton performing orbital motion in an adjacent one. The results may be used to design a device employing coexisting ring-shaped modes with different WNs for data storage.

nlin.PS↗
arXiv2022

MnTTS2: An Open-Source Multi-Speaker Mongolian Text-to-Speech Synthesis Dataset

Text-to-Speech (TTS) synthesis for low-resource languages is an attractive research issue in academia and industry nowadays. Mongolian is the official language of the Inner Mongolia Autonomous Region and a representative low-resource language spoken by over 10 million people worldwide. However, there is a relative lack of open-source datasets for Mongolian TTS. Therefore, we make public an open-source multi-speaker Mongolian TTS dataset, named MnTTS2, for the benefit of related researchers. In this work, we prepare the transcription from various topics and invite three professional Mongolian announcers to form a three-speaker TTS dataset, in which each announcer records 10 hours of speeches in Mongolian, resulting 30 hours in total. Furthermore, we build the baseline system based on the state-of-the-art FastSpeech2 model and HiFi-GAN vocoder. The experimental results suggest that the constructed MnTTS2 dataset is sufficient to build robust multi-speaker TTS models for real-world applications. The MnTTS2 dataset, training recipe, and pretrained models are released at: \url{https://github.com/ssmlkl/MnTTS2}

eess.AS↗
arXiv2022

Uncovering a hidden black hole binary from secular eccentricity variations of a tertiary star

We study the dynamics of a solar-type star orbiting around a black hole binary (BHB) in a nearly coplanar system. We present a novel effect that can prompt a growth and significant oscillations of the eccentricity of the stellar orbit when the system encounters an "apsidal precession resonance", where the apsidal precession rate of the outer stellar orbit matches that of the inner BHB. The eccentricity excitation requires the inner binary to have a non-zero eccentricity and unequal masses, and can be created even in non-coplanar triples. We show that the secular variability of the stellar orbit's apocenter, induced by the changing eccentricity, could be potentially detectable by \textit{Gaia}. Detection is favorable for BHBs emitting gravitational waves in the frequency band of the Laser Interferometer Space Antenna (LISA), hence providing a distinctive, multi-messenger probe on the existence of stellar-mass BHBs in the Milky Way.

astro-ph.HE↗