Searcharxiv⌕ Search

arXiv subjects

Bin Yang

Publications and source records attributed to Bin Yang.

At least 235 records · Page 13Linked to original sources
arXiv2024

CMGAN: Conformer-based Metric GAN for Speech Enhancement

Recently, convolution-augmented transformer (Conformer) has achieved promising performance in automatic speech recognition (ASR) and time-domain speech enhancement (SE), as it can capture both local and global dependencies in the speech signal. In this paper, we propose a conformer-based metric generative adversarial network (CMGAN) for SE in the time-frequency (TF) domain. In the generator, we utilize two-stage conformer blocks to aggregate all magnitude and complex spectrogram information by modeling both time and frequency dependencies. The estimation of magnitude and complex spectrogram is decoupled in the decoder stage and then jointly incorporated to reconstruct the enhanced speech. In addition, a metric discriminator is employed to further improve the quality of the enhanced estimated speech by optimizing the generator with respect to a corresponding evaluation score. Quantitative analysis on Voice Bank+DEMAND dataset indicates the capability of CMGAN in outperforming various previous models with a margin, i.e., PESQ of 3.41 and SSNR of 11.10 dB.

cs.SD↗
arXiv2024

An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domains

3D Object Detectors (3D-OD) are crucial for understanding the environment in many robotic tasks, especially autonomous driving. Including 3D information via Lidar sensors improves accuracy greatly. However, such detectors perform poorly on domains they were not trained on, i.e. different locations, sensors, weather, etc., limiting their reliability in safety-critical applications. There exist methods to adapt 3D-ODs to these domains; however, these methods treat 3D-ODs as a black box, neglecting underlying architectural decisions and source-domain training strategies. Instead, we dive deep into the details of 3D-ODs, focusing our efforts on fundamental factors that influence robustness prior to domain adaptation. We systematically investigate four design choices (and the interplay between them) often overlooked in 3D-OD robustness and domain adaptation: architecture, voxel encoding, data augmentations, and anchor strategies. We assess their impact on the robustness of nine state-of-the-art 3D-ODs across six benchmarks encompassing three types of domain gaps - sensor type, weather, and location. Our main findings are: (1) transformer backbones with local point features are more robust than 3D CNNs, (2) test-time anchor size adjustment is crucial for adaptation across geographical locations, significantly boosting scores without retraining, (3) source-domain augmentations allow the model to generalize to low-resolution sensors, and (4) surprisingly, robustness to bad weather is improved when training directly on more clean weather data than on training with bad weather data. We outline our main conclusions and findings to provide practical guidance on developing more robust 3D-ODs.

cs.CV↗
arXiv2024

Existence and upper semicontinuity of pullback attractors for Kirchhoff wave equations in time-dependent spaces

In this paper, we shall investigate the existence and upper semicontinuity of pullback attractors for non-autonomous Kirchhoff wave equations with a strong damping in the time-dependent space $X_t$. After deriving the existence and uniqueness of solutions by the Faedo-Galerkin approximation method, we establish the existence of pullback attractors. Later on, we prove the upper semicontinuity of pullback attractors between the Kirchhoff-type wave equations with $δ\geq 0$ and the conventional wave equations with $δ=0$ by a series of complex energy estimates.

math.AP↗
arXiv2024

EEG motor imagery decoding: A framework for comparative analysis with channel attention mechanisms

The objective of this study is to investigate the application of various channel attention mechanisms within the domain of brain-computer interface (BCI) for motor imagery decoding. Channel attention mechanisms can be seen as a powerful evolution of spatial filters traditionally used for motor imagery decoding. This study systematically compares such mechanisms by integrating them into a lightweight architecture framework to evaluate their impact. We carefully construct a straightforward and lightweight baseline architecture designed to seamlessly integrate different channel attention mechanisms. This approach is contrary to previous works which only investigate one attention mechanism and usually build a very complex, sometimes nested architecture. Our framework allows us to evaluate and compare the impact of different attention mechanisms under the same circumstances. The easy integration of different channel attention mechanisms as well as the low computational complexity enables us to conduct a wide range of experiments on four datasets to thoroughly assess the effectiveness of the baseline model and the attention mechanisms. Our experiments demonstrate the strength and generalizability of our architecture framework as well as how channel attention mechanisms can improve the performance while maintaining the small memory footprint and low computational complexity of our baseline architecture. Our architecture emphasizes simplicity, offering easy integration of channel attention mechanisms, while maintaining a high degree of generalizability across datasets, making it a versatile and efficient solution for EEG motor imagery decoding within brain-computer interfaces.

cs.HC↗
arXiv2024

Indoor Positioning based on Active Radar Sensing and Passive Reflectors: Concepts & Initial Results

To navigate reliably in indoor environments, an industrial autonomous vehicle must know its position. However, current indoor vehicle positioning technologies either lack accuracy, usability or are too expensive. Thus, we propose a novel concept called local reference point assisted active radar positioning, which is able to overcome these drawbacks. It is based on distributing passive retroreflectors in the indoor environment such that each position of the vehicle can be identified by a unique reflection characteristic regarding the reflectors. To observe these characteristics, the autonomous vehicle is equipped with an active radar system. On one hand, this paper presents the basic idea and concept of our new approach towards indoor vehicle positioning and especially focuses on the crucial placement of the reflectors. On the other hand, it also provides a proof of concept by conducting a full system simulation including the placement of the local reference points, the radar-based distance estimation and the comparison of two different positioning methods. It successfully demonstrates the feasibility of our proposed approach.

cs.RO↗
arXiv2024

A Hierarchical Random Effects State-space Model for Modeling Brain Activities from Electroencephalogram Data

Mental disorders present challenges in diagnosis and treatment due to their complex and heterogeneous nature. Electroencephalogram (EEG) has shown promise as a potential biomarker for these disorders. However, existing methods for analyzing EEG signals have limitations in addressing heterogeneity and capturing complex brain activity patterns between regions. This paper proposes a novel random effects state-space model (RESSM) for analyzing large-scale multi-channel resting-state EEG signals, accounting for the heterogeneity of brain connectivities between groups and individual subjects. We incorporate multi-level random effects for temporal dynamical and spatial mapping matrices and address nonstationarity so that the brain connectivity patterns can vary over time. The model is fitted under a Bayesian hierarchical model framework coupled with a Gibbs sampler. Compared to previous mixed-effects state-space models, we directly model high-dimensional random effects matrices without structural constraints and tackle the challenge of identifiability. Through extensive simulation studies, we demonstrate that our approach yields valid estimation and inference. We apply RESSM to a multi-site clinical trial of Major Depressive Disorder (MDD). Our analysis uncovers significant differences in resting-state brain temporal dynamics among MDD patients compared to healthy individuals. In addition, we show the subject-level EEG features derived from RESSM exhibit a superior predictive value for the heterogeneous treatment effect compared to the EEG frequency band power, suggesting the potential of EEG as a valuable biomarker for MDD.

stat.ME↗
arXiv2024

Calibration-free online test-time adaptation for electroencephalography motor imagery decoding

Providing a promising pathway to link the human brain with external devices, Brain-Computer Interfaces (BCIs) have seen notable advancements in decoding capabilities, primarily driven by increasingly sophisticated techniques, especially deep learning. However, achieving high accuracy in real-world scenarios remains a challenge due to the distribution shift between sessions and subjects. In this paper we will explore the concept of online test-time adaptation (OTTA) to continuously adapt the model in an unsupervised fashion during inference time. Our approach guarantees the preservation of privacy by eliminating the requirement to access the source data during the adaptation process. Additionally, OTTA achieves calibration-free operation by not requiring any session- or subject-specific data. We will investigate the task of electroencephalography (EEG) motor imagery decoding using a lightweight architecture together with different OTTA techniques like alignment, adaptive batch normalization, and entropy minimization. We examine two datasets and three distinct data settings for a comprehensive analysis. Our adaptation methods produce state-of-the-art results, potentially instigating a shift in transfer learning for BCI decoding towards online adaptation.

cs.HC↗
arXiv2024

Dust and Volatiles in the Disintegrating Comet C/2019 Y4 (ATLAS)

C/2019 Y4 (ATLAS) is an Oort cloud comet with an orbital period of $\sim$5895$\,{\rm yr}$. Starting in March 2020, its nucleus underwent disintegration. In order to investigate the gas and dust properties of C/2019 Y4 (ATLAS) during its disintegration, we obtained long-slit spectra at 3600--8700$\,{\rm\mathring{A}}$ and $BVRI$ multi-band images with the Xinglong 2.16-Meter Telescope in April 2020. Our observations revealed that C/2019 Y4 (ATLAS) exhibited strong emission bands of CN, C$_2$, C$_3$, and NH$_2$ which are superimposed on a dust scattering continuum, typical of cometary spectra in the optical. The production rates of CN, C$_2$, and C$_3$ derived using the Haser model and the corresponding C$_2$/CN and C$_3$/CN ratios suggest that C/2019 Y4 (ATLAS) is a ``typical'' Oort cloud comet under the A'Hearn classification, although it appears less dusty as revealed by the $Afρ$ quantities. Its dust-scattering reflectivity is slightly red, with a gradient of $\sim$5% per $10^3\,{\rm\mathring{A}}$. We model the reflectivity gradient in terms of porous dust and find that the red color is accounted for by porous dust.

astro-ph.EP↗
arXiv2024

Diversity-aware Buffer for Coping with Temporally Correlated Data Streams in Online Test-time Adaptation

Since distribution shifts are likely to occur after a model's deployment and can drastically decrease the model's performance, online test-time adaptation (TTA) continues to update the model during test-time, leveraging the current test data. In real-world scenarios, test data streams are not always independent and identically distributed (i.i.d.). Instead, they are frequently temporally correlated, making them non-i.i.d. Many existing methods struggle to cope with this scenario. In response, we propose a diversity-aware and category-balanced buffer that can simulate an i.i.d. data stream, even in non-i.i.d. scenarios. Combined with a diversity and entropy-weighted entropy loss, we show that a stable adaptation is possible on a wide range of corruptions and natural domain shifts, based on ImageNet. We achieve state-of-the-art results on most considered benchmarks.

cs.CV↗
arXiv2023

Current status of the Extension of the FRIPON network in Chile

FRIPON is an efficient ground-based network for the detection and characterization of fireballs, which was initiated in France in 2016 with over one hundred cameras and which has been very successfully extended to Europe and Canada with one hundred more stations. After seven successful years of operation in the northern hemisphere, it seems necessary to extend this network towards the southern hemisphere - where the lack of detection is evident - to obtain an exhaustive view of fireball activity. The task of extending the network to any region outside the northern hemisphere presents the challenge of a new installation process, where the recommended and tested version of the several sub-systems that compose a station had to be replaced due to regional availability and compatibility considerations, as well as due to constant software and hardware obsolescence and updates. In Chile, we have a unique geography, with a vast extension in latitude, as well as desert regions, which have generated the need to evaluate the scientific and technical performance of the network under special conditions, prioritizing the optimization of a set of factors related to the deployment process, as well as the feasible and achievable versions of the required components, the geographical location of the stations, and their respective operational, maintenance, safety, and communication conditions. In this talk, we will present the current status of this effort, including a brief report on the obstacles and difficulties encountered and how we have solved them, the current operational status of the network in Northern Chile, as well as the challenges and prospects for the densification of the network over South America.

astro-ph.IM↗
arXiv2023

AI-driven projection tomography with multicore fibre-optic cell rotation

Optical tomography has emerged as a non-invasive imaging method, providing three-dimensional insights into subcellular structures and thereby enabling a deeper understanding of cellular functions, interactions, and processes. Conventional optical tomography methods are constrained by a limited illumination scanning range, leading to anisotropic resolution and incomplete imaging of cellular structures. To overcome this problem, we employ a compact multi-core fibre-optic cell rotator system that facilitates precise optical manipulation of cells within a microfluidic chip, achieving full-angle projection tomography with isotropic resolution. Moreover, we demonstrate an AI-driven tomographic reconstruction workflow, which can be a paradigm shift from conventional computational methods, often demanding manual processing, to a fully autonomous process. The performance of the proposed cell rotation tomography approach is validated through the three-dimensional reconstruction of cell phantoms and HL60 human cancer cells. The versatility of this learning-based tomographic reconstruction workflow paves the way for its broad application across diverse tomographic imaging modalities, including but not limited to flow cytometry tomography and acoustic rotation tomography. Therefore, this AI-driven approach can propel advancements in cell biology, aiding in the inception of pioneering therapeutics, and augmenting early-stage cancer diagnostics.

physics.med-ph↗
arXiv2023

Towards Unsupervised Object Detection From LiDAR Point Clouds

In this paper, we study the problem of unsupervised object detection from 3D point clouds in self-driving scenes. We present a simple yet effective method that exploits (i) point clustering in near-range areas where the point clouds are dense, (ii) temporal consistency to filter out noisy unsupervised detections, (iii) translation equivariance of CNNs to extend the auto-labels to long range, and (iv) self-supervision for improving on its own. Our approach, OYSTER (Object Discovery via Spatio-Temporal Refinement), does not impose constraints on data collection (such as repeated traversals of the same location), is able to detect objects in a zero-shot manner without supervised finetuning (even in sparse, distant regions), and continues to self-improve given more rounds of iterative self-training. To better measure model performance in self-driving scenarios, we propose a new planning-centric perception metric based on distance-to-collision. We demonstrate that our unsupervised object detector significantly outperforms unsupervised baselines on PandaSet and Argoverse 2 Sensor dataset, showing promise that self-supervision combined with object priors can enable object discovery in the wild. For more information, visit the project website: https://waabi.ai/research/oyster

cs.CV↗
arXiv2023

Graph Representation Learning for Infrared and Visible Image Fusion

Infrared and visible image fusion aims to extract complementary features to synthesize a single fused image. Many methods employ convolutional neural networks (CNNs) to extract local features due to its translation invariance and locality. However, CNNs fail to consider the image's non-local self-similarity (NLss), though it can expand the receptive field by pooling operations, it still inevitably leads to information loss. In addition, the transformer structure extracts long-range dependence by considering the correlativity among all image patches, leading to information redundancy of such transformer-based methods. However, graph representation is more flexible than grid (CNN) or sequence (transformer structure) representation to address irregular objects, and graph can also construct the relationships among the spatially repeatable details or texture with far-space distance. Therefore, to address the above issues, it is significant to convert images into the graph space and thus adopt graph convolutional networks (GCNs) to extract NLss. This is because the graph can provide a fine structure to aggregate features and propagate information across the nearest vertices without introducing redundant information. Concretely, we implement a cascaded NLss extraction pattern to extract NLss of intra- and inter-modal by exploring interactions of different image pixels in intra- and inter-image positional distance. We commence by preforming GCNs on each intra-modal to aggregate features and propagate information to extract independent intra-modal NLss. Then, GCNs are performed on the concatenate intra-modal NLss features of infrared and visible images, which can explore the cross-domain NLss of inter-modal to reconstruct the fused image. Ablation studies and extensive experiments illustrates the effectiveness and superiority of the proposed method on three datasets.

cs.CV↗
arXiv2023

DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models

A long-standing goal of AI systems is to perform complex multimodal reasoning like humans. Recently, large language models (LLMs) have made remarkable strides in such multi-step reasoning on the language modality solely by leveraging the chain of thought (CoT) to mimic human thinking. However, the transfer of these advancements to multimodal contexts introduces heightened challenges, including but not limited to the impractical need for labor-intensive annotation and the limitations in terms of flexibility, generalizability, and explainability. To evoke CoT reasoning in multimodality, this work first conducts an in-depth analysis of these challenges posed by multimodality and presents two key insights: "keeping critical thinking" and "letting everyone do their jobs" in multimodal CoT reasoning. Furthermore, this study proposes a novel DDCoT prompting that maintains a critical attitude through negative-space prompting and incorporates multimodality into reasoning by first dividing the reasoning responsibility of LLMs into reasoning and recognition and then integrating the visual recognition capability of visual models into the joint reasoning process. The rationales generated by DDCoT not only improve the reasoning abilities of both large and small language models in zero-shot prompting and fine-tuning learning, significantly outperforming state-of-the-art methods but also exhibit impressive generalizability and explainability.

cs.CV↗
arXiv2023

Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correction

Since distribution shifts are likely to occur during test-time and can drastically decrease the model's performance, online test-time adaptation (TTA) continues to update the model after deployment, leveraging the current test data. Clearly, a method proposed for online TTA has to perform well for all kinds of environmental conditions. By introducing the variable factors domain non-stationarity and temporal correlation, we first unfold all practically relevant settings and define the entity as universal TTA. We want to highlight that this is the first work that covers such a broad spectrum, which is indispensable for the use in practice. To tackle the problem of universal TTA, we identify and highlight several challenges a self-training based method has to deal with: 1) model bias and the occurrence of trivial solutions when performing entropy minimization on varying sequence lengths with and without multiple domain shifts, 2) loss of generalization which exacerbates the adaptation to multiple domain shifts and the occurrence of catastrophic forgetting, and 3) performance degradation due to shifts in class prior. To prevent the model from becoming biased, we leverage a dataset and model-agnostic certainty and diversity weighting. In order to maintain generalization and prevent catastrophic forgetting, we propose to continually weight-average the source and adapted model. To compensate for disparities in the class prior during test-time, we propose an adaptive prior correction scheme that reweights the model's predictions. We evaluate our approach, named ROID, on a wide range of settings, datasets, and models, setting new standards in the field of universal TTA. Code is available at: https://github.com/mariodoebler/test-time-adaptation

cs.CV↗
arXiv2023

Existence and regularity of pullback attractors for nonclassical non-autonomous diffusion equations with delay

In this paper, we consider the asymptotic behavior of weak solutions for non-autonomous diffusion equations with delay in time-dependent spaces when the nonlinear function $f$ is critical growth, the delay term $g(t, u_t)$ contains some hereditary characteristics and the external force $h \in L_{l o c}^{2}\left(\mathbb{R} ; L^{2}(Ω)\right)$. Firstly, we prove the well-posedness of solutions by using the Faedo-Galerkin approximation method. Then after a series of elaborate energy estimates and calculations, we establish the existence and regularity of pullback attractors in time-dependent spaces $C_{\mathcal{H}_{t}(Ω)}$ and $C_{\mathcal{H}^{1}_{t}(Ω)}$ respectively.

math.AP↗
arXiv2023

LightPath: Lightweight and Scalable Path Representation Learning

Movement paths are used widely in intelligent transportation and smart city applications. To serve such applications, path representation learning aims to provide compact representations of paths that enable efficient and accurate operations when used for different downstream tasks such as path ranking and travel cost estimation. In many cases, it is attractive that the path representation learning is lightweight and scalable; in resource-limited environments and under green computing limitations, it is essential. Yet, existing path representation learning studies focus on accuracy and pay at most secondary attention to resource consumption and scalability. We propose a lightweight and scalable path representation learning framework, termed LightPath, that aims to reduce resource consumption and achieve scalability without affecting accuracy, thus enabling broader applicability. More specifically, we first propose a sparse auto-encoder that ensures that the framework achieves good scalability with respect to path length. Next, we propose a relational reasoning framework to enable faster training of more robust sparse path encoders. We also propose global-local knowledge distillation to further reduce the size and improve the performance of sparse path encoders. Finally, we report extensive experiments on two real-world datasets to offer insight into the efficiency, scalability, and effectiveness of the proposed framework.

cs.LG↗
arXiv2023

Origin-Destination Travel Time Oracle for Map-based Services

Given an origin (O), a destination (D), and a departure time (T), an Origin-Destination (OD) travel time oracle~(ODT-Oracle) returns an estimate of the time it takes to travel from O to D when departing at T. ODT-Oracles serve important purposes in map-based services. To enable the construction of such oracles, we provide a travel-time estimation (TTE) solution that leverages historical trajectories to estimate time-varying travel times for OD pairs. The problem is complicated by the fact that multiple historical trajectories with different travel times may connect an OD pair, while trajectories may vary from one another. To solve the problem, it is crucial to remove outlier trajectories when doing travel time estimation for future queries. We propose a novel, two-stage framework called Diffusion-based Origin-destination Travel Time Estimation (DOT), that solves the problem. First, DOT employs a conditioned Pixelated Trajectories (PiT) denoiser that enables building a diffusion-based PiT inference process by learning correlations between OD pairs and historical trajectories. Specifically, given an OD pair and a departure time, we aim to infer a PiT. Next, DOT encompasses a Masked Vision Transformer~(MViT) that effectively and efficiently estimates a travel time based on the inferred PiT. We report on extensive experiments on two real-world datasets that offer evidence that DOT is capable of outperforming baseline methods in terms of accuracy, scalability, and explainability.

cs.LG↗