arXiv subjects

Bin Yang

Publications and source records attributed to Bin Yang.

At least 217 records · Page 12Linked to original sources

arXiv2024

Squeeze-and-Remember Block

Convolutional Neural Networks (CNNs) are important for many machine learning tasks. They are built with different types of layers: convolutional layers that detect features, dropout layers that help to avoid over-reliance on any single neuron, and residual layers that allow the reuse of features. However, CNNs lack a dynamic feature retention mechanism similar to the human brain's memory, limiting their ability to use learned information in new contexts. To bridge this gap, we introduce the "Squeeze-and-Remember" (SR) block, a novel architectural unit that gives CNNs dynamic memory-like functionalities. The SR block selectively memorizes important features during training, and then adaptively re-applies these features during inference. This improves the network's ability to make contextually informed predictions. Empirical results on ImageNet and Cityscapes datasets demonstrate the SR block's efficacy: integration into ResNet50 improved top-1 validation accuracy on ImageNet by 0.52% over dropout2d alone, and its application in DeepLab v3 increased mean Intersection over Union in Cityscapes by 0.20%. These improvements are achieved with minimal computational overhead. This show the SR block's potential to enhance the capabilities of CNNs in image processing tasks.

cs.CV↗

arXiv2024

Spectral Wavelet Dropout: Regularization in the Wavelet Domain

Regularization techniques help prevent overfitting and therefore improve the ability of convolutional neural networks (CNNs) to generalize. One reason for overfitting is the complex co-adaptations among different parts of the network, which make the CNN dependent on their joint response rather than encouraging each part to learn a useful feature representation independently. Frequency domain manipulation is a powerful strategy for modifying data that has temporal and spatial coherence by utilizing frequency decomposition. This work introduces Spectral Wavelet Dropout (SWD), a novel regularization method that includes two variants: 1D-SWD and 2D-SWD. These variants improve CNN generalization by randomly dropping detailed frequency bands in the discrete wavelet decomposition of feature maps. Our approach distinguishes itself from the pre-existing Spectral "Fourier" Dropout (2D-SFD), which eliminates coefficients in the Fourier domain. Notably, SWD requires only a single hyperparameter, unlike the two required by SFD. We also extend the literature by implementing a one-dimensional version of Spectral "Fourier" Dropout (1D-SFD), setting the stage for a comprehensive comparison. Our evaluation shows that both 1D and 2D SWD variants have competitive performance on CIFAR-10/100 benchmarks relative to both 1D-SFD and 2D-SFD. Specifically, 1D-SWD has a significantly lower computational complexity compared to 1D/2D-SFD. In the Pascal VOC Object Detection benchmark, SWD variants surpass 1D-SFD and 2D-SFD in performance and demonstrate lower computational complexity during training.

cs.CV↗

arXiv2024

CNN Mixture-of-Depths

We introduce Mixture-of-Depths (MoD) for Convolutional Neural Networks (CNNs), a novel approach that enhances the computational efficiency of CNNs by selectively processing channels based on their relevance to the current prediction. This method optimizes computational resources by dynamically selecting key channels in feature maps for focused processing within the convolutional blocks (Conv-Blocks), while skipping less relevant channels. Unlike conditional computation methods that require dynamic computation graphs, CNN MoD uses a static computation graph with fixed tensor sizes which improve hardware efficiency. It speeds up the training and inference processes without the need for customized CUDA kernels, unique loss functions, or finetuning. CNN MoD either matches the performance of traditional CNNs with reduced inference times, GMACs, and parameters, or exceeds their performance while maintaining similar inference times, GMACs, and parameters. For example, on ImageNet, ResNet86-MoD exceeds the performance of the standard ResNet50 by 0.45% with a 6% speedup on CPU and 5% on GPU. Moreover, ResNet75-MoD achieves the same performance as ResNet50 with a 25% speedup on CPU and 15% on GPU.

cs.CV↗

arXiv2024

Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting

Transformers for time series forecasting mainly model time series from limited or fixed scales, making it challenging to capture different characteristics spanning various scales. We propose Pathformer, a multi-scale Transformer with adaptive pathways. It integrates both temporal resolution and temporal distance for multi-scale modeling. Multi-scale division divides the time series into different temporal resolutions using patches of various sizes. Based on the division of each scale, dual attention is performed over these patches to capture global correlations and local details as temporal dependencies. We further enrich the multi-scale Transformer with adaptive pathways, which adaptively adjust the multi-scale modeling process based on the varying temporal dynamics of the input, improving the accuracy and generalization of Pathformer. Extensive experiments on eleven real-world datasets demonstrate that Pathformer not only achieves state-of-the-art performance by surpassing all current models but also exhibits stronger generalization abilities under various transfer scenarios. The code is made available at https://github.com/decisionintelligence/pathformer.

cs.LG↗

arXiv2024

FAST Observations of Four Comets to Search for the Molecular Line Emissions between 1.0 and 1.5 GHz Frequencies

We used the Five-hundred-meter Aperture Spherical radio Telescope (FAST) to search for the molecular emissions in the L-band between 1.0 and 1.5 GHz toward four comets, C/2020 F3 (NEOWISE), C/2020 R4 (ATLAS), C/2021 A1 (Leonard), and 67P/Churyumov-Gerasimenko during or after their perihelion passages. Thousands of molecular transition lines fall in this low-frequency range, many attributed to complex organic or prebiotic molecules. We conducted a blind search for the possible molecular lines in this frequency range in those comets and could not identify clear signals of molecular emissions in the data. Although several molecules have been detected at high frequencies of great than 100 GHz in comets, our results confirm that it is challenging to detect molecular transitions in the L-band frequency ranges. The non-detection of L-band molecular lines in the cometary environment could rule out the possibility of unusually strong lines, which could be caused by the masers or non-LTE effects. Although the line strengths are predicted to be weak, for FAST, using the ultra-wide bandwidth receiver and improving the radio frequency interference environments would enhance the detectability of those molecular transitions at low frequencies in the future.

astro-ph.EP↗

arXiv2024

A Lost Opportunity for Vision-Language Models: A Comparative Study of Online Test-Time Adaptation for Vision-Language Models

In deep learning, maintaining model robustness against distribution shifts is critical. This work explores a broad range of possibilities to adapt vision-language foundation models at test-time, with a particular emphasis on CLIP and its variants. The study systematically examines prompt-based techniques and existing test-time adaptation methods, aiming to improve the robustness under distribution shift in diverse real-world scenarios. Specifically, the investigation covers various prompt engineering strategies, including handcrafted prompts, prompt ensembles, and prompt learning techniques. Additionally, we introduce a vision-text-space ensemble that substantially enhances average performance compared to text-space-only ensembles. Since online test-time adaptation has shown to be effective to mitigate performance drops under distribution shift, the study extends its scope to evaluate the effectiveness of existing test-time adaptation methods that were originally designed for vision-only classification models. Through extensive experimental evaluations conducted across multiple datasets and diverse model architectures, the research demonstrates the effectiveness of these adaptation strategies. Code is available at: https://github.com/mariodoebler/test-time-adaptation

cs.CV↗

arXiv2024

SVS-GAN: Leveraging GANs for Semantic Video Synthesis

In recent years, there has been a growing interest in Semantic Image Synthesis (SIS) through the use of Generative Adversarial Networks (GANs) and diffusion models. This field has seen innovations such as the implementation of specialized loss functions tailored for this task, diverging from the more general approaches in Image-to-Image (I2I) translation. While the concept of Semantic Video Synthesis (SVS)$\unicode{x2013}$the generation of temporally coherent, realistic sequences of images from semantic maps$\unicode{x2013}$is newly formalized in this paper, some existing methods have already explored aspects of this field. Most of these approaches rely on generic loss functions designed for video-to-video translation or require additional data to achieve temporal coherence. In this paper, we introduce the SVS-GAN, a framework specifically designed for SVS, featuring a custom architecture and loss functions. Our approach includes a triple-pyramid generator that utilizes SPADE blocks. Additionally, we employ a U-Net-based network for the image discriminator, which performs semantic segmentation for the OASIS loss. Through this combination of tailored architecture and objective engineering, our framework aims to bridge the existing gap between SIS and SVS, outperforming current state-of-the-art models on datasets like Cityscapes and KITTI-360.

cs.CV↗

arXiv2024

Multiagent Reinforcement Learning Enhanced Decision-making of Crew Agents During Floor Construction Process

Fine-grained simulation of floor construction processes is essential for supporting lean management and the integration of information technology. However, existing research does not adequately address the on-site decision-making of constructors in selecting tasks and determining their sequence within the entire construction process. Moreover, decision-making frameworks from computer science and robotics are not directly applicable to construction scenarios. To facilitate intelligent simulation in construction, this study introduces the Construction Markov Decision Process (CMDP). The primary contribution of this CMDP framework lies in its construction knowledge in decision, observation modifications and policy design, enabling agents to perceive the construction state and follow policy guidance to evaluate and reach various range of targets for optimizing the planning of construction activities. The CMDP is developed on the Unity platform, utilizing a two-stage training approach with the multi-agent proximal policy optimization algorithm. A case study demonstrates the effectiveness of this framework: the low-level policy successfully simulates the construction process in continuous space, facilitating policy testing and training focused on reducing conflicts and blockages among crews; and the high-level policy improving the spatio-temporal planning of construction activities, generating construction patterns in distinct phases, leading to the discovery of new construction insights.

cs.CE↗

arXiv2024

The Linked Data Benchmark Council (LDBC): Driving competition and collaboration in the graph data management space

Graph data management is instrumental for several use cases such as recommendation, root cause analysis, financial fraud detection, and enterprise knowledge representation. Efficiently supporting these use cases yields a number of unique requirements, including the need for a concise query language and graph-aware query optimization techniques. The goal of the Linked Data Benchmark Council (LDBC) is to design a set of standard benchmarks that capture representative categories of graph data management problems, making the performance of systems comparable and facilitating competition among vendors. LDBC also conducts research on graph schemas and graph query languages. This paper introduces the LDBC organization and its work over the last decade.

cs.DB↗

arXiv2024

Exploring Domain Shift on Radar-Based 3D Object Detection Amidst Diverse Environmental Conditions

The rapid evolution of deep learning and its integration with autonomous driving systems have led to substantial advancements in 3D perception using multimodal sensors. Notably, radar sensors show greater robustness compared to cameras and lidar under adverse weather and varying illumination conditions. This study delves into the often-overlooked yet crucial issue of domain shift in 4D radar-based object detection, examining how varying environmental conditions, such as different weather patterns and road types, impact 3D object detection performance. Our findings highlight distinct domain shifts across various weather scenarios, revealing unique dataset sensitivities that underscore the critical role of radar point cloud generation. Additionally, we demonstrate that transitioning between different road types, especially from highways to urban settings, introduces notable domain shifts, emphasizing the necessity for diverse data collection across varied road environments. To the best of our knowledge, this is the first comprehensive analysis of domain shift effects on 4D radar-based object detection. We believe this empirical study contributes to understanding the complex nature of domain shifts in radar data and suggests paths forward for data collection strategy in the face of environmental variability.

cs.CV↗

arXiv2024

Orca: Ocean Significant Wave Height Estimation with Spatio-temporally Aware Large Language Models

Significant wave height (SWH) is a vital metric in marine science, and accurate SWH estimation is crucial for various applications, e.g., marine energy development, fishery, early warning systems for potential risks, etc. Traditional SWH estimation methods that are based on numerical models and physical theories are hindered by computational inefficiencies. Recently, machine learning has emerged as an appealing alternative to improve accuracy and reduce computational time. However, due to limited observational technology and high costs, the scarcity of real-world data restricts the potential of machine learning models. To overcome these limitations, we propose an ocean SWH estimation framework, namely Orca. Specifically, Orca enhances the limited spatio-temporal reasoning abilities of classic LLMs with a novel spatiotemporal aware encoding module. By segmenting the limited buoy observational data temporally, encoding the buoys' locations spatially, and designing prompt templates, Orca capitalizes on the robust generalization ability of LLMs to estimate significant wave height effectively with limited data. Experimental results on the Gulf of Mexico demonstrate that Orca achieves state-of-the-art performance in SWH estimation.

cs.LG↗

arXiv2024

Part2Object: Hierarchical Unsupervised 3D Instance Segmentation

Unsupervised 3D instance segmentation aims to segment objects from a 3D point cloud without any annotations. Existing methods face the challenge of either too loose or too tight clustering, leading to under-segmentation or over-segmentation. To address this issue, we propose Part2Object, hierarchical clustering with object guidance. Part2Object employs multi-layer clustering from points to object parts and objects, allowing objects to manifest at any layer. Additionally, it extracts and utilizes 3D objectness priors from temporally consecutive 2D RGB frames to guide the clustering process. Moreover, we propose Hi-Mask3D to support hierarchical 3D object part and instance segmentation. By training Hi-Mask3D on the objects and object parts extracted from Part2Object, we achieve consistent and superior performance compared to state-of-the-art models in various settings, including unsupervised instance segmentation, data-efficient fine-tuning, and cross-dataset generalization. Code is release at https://github.com/ChengShiest/Part2Object

cs.CV↗

arXiv2024

Efficient Stochastic Routing in Path-Centric Uncertain Road Networks -- Extended Version

The availability of massive vehicle trajectory data enables the modeling of road-network constrained movement as travel-cost distributions rather than just single-valued costs, thereby capturing the inherent uncertainty of movement and enabling improved routing quality. Thus, stochastic routing has been studied extensively in the edge-centric model, where such costs are assigned to the edges in a graph representation of a road network. However, as this model still disregards important information in trajectories and fails to capture dependencies among cost distributions, a path-centric model, where costs are assigned to paths, has been proposed that captures dependencies better and provides an improved foundation for routing. Unfortunately, when applied in this model, existing routing algorithms are inefficient due to two shortcomings that we eliminate. First, when exploring candidate paths, existing algorithms only consider the costs of candidate paths from the source to intermediate vertices, while disregarding the costs of travel from the intermediate vertices to the destination, causing many non-competitive paths to be explored. We propose two heuristics for estimating the cost from an intermediate vertex to the destination, thus improving routing efficiency. Second, the edge-centric model relies on stochastic dominance-based pruning to improve efficiency. This pruning assumes that costs are independent and is therefore inapplicable in the path-centric model that takes dependencies into account. We introduce a notion of virtual path that effectively enables stochastic dominance-based pruning in the path-based model, thus further improving efficiency. Empirical studies using two real-world trajectory sets offer insight into the properties of the proposed solution, indicating that it enables efficient stochastic routing in the path-centric model.

cs.DS↗

arXiv2024

A Mathematical Aspect of Bloch's Theorem

In this paper, by studying a class of 1-D Sturm-Liouville problems with periodic coefficients, we show and classify the solutions of periodic Schrodinger equations in a multidimensional case, which tells that not all the solutions are Bloch solutions. In addition, we also provide several properties of the solutions and quasimomenta and illustrate the relationship between bounded solutions and Bloch solutions.

math-ph↗

arXiv2024

Modeling User Retention through Generative Flow Networks

Recommender systems aim to fulfill the user's daily demands. While most existing research focuses on maximizing the user's engagement with the system, it has recently been pointed out that how frequently the users come back for the service also reflects the quality and stability of recommendations. However, optimizing this user retention behavior is non-trivial and poses several challenges including the intractable leave-and-return user activities, the sparse and delayed signal, and the uncertain relations between users' retention and their immediate feedback towards each item in the recommendation list. In this work, we regard the retention signal as an overall estimation of the user's end-of-session satisfaction and propose to estimate this signal through a probabilistic flow. This flow-based modeling technique can back-propagate the retention reward towards each recommended item in the user session, and we show that the flow combined with traditional learning-to-rank objectives eventually optimizes a non-discounted cumulative reward for both immediate user feedback and user retention. We verify the effectiveness of our method through both offline empirical studies on two public datasets and online A/B tests in an industrial platform.

cs.IR↗

arXiv2024

Position: What Can Large Language Models Tell Us about Time Series Analysis

Time series analysis is essential for comprehending the complexities inherent in various realworld systems and applications. Although large language models (LLMs) have recently made significant strides, the development of artificial general intelligence (AGI) equipped with time series analysis capabilities remains in its nascent phase. Most existing time series models heavily rely on domain knowledge and extensive model tuning, predominantly focusing on prediction tasks. In this paper, we argue that current LLMs have the potential to revolutionize time series analysis, thereby promoting efficient decision-making and advancing towards a more universal form of time series analytical intelligence. Such advancement could unlock a wide range of possibilities, including time series modality switching and question answering. We encourage researchers and practitioners to recognize the potential of LLMs in advancing time series analysis and emphasize the need for trust in these related efforts. Furthermore, we detail the seamless integration of time series analysis with existing LLM technologies and outline promising avenues for future research.

cs.LG↗

arXiv2024

Defect Category Prediction Based on Multi-Source Domain Adaptation

In recent years, defect prediction techniques based on deep learning have become a prominent research topic in the field of software engineering. These techniques can identify potential defects without executing the code. However, existing approaches mostly concentrate on determining the presence of defects at the method-level code, lacking the ability to precisely classify specific defect categories. Consequently, this undermines the efficiency of developers in locating and rectifying defects. Furthermore, in practical software development, new projects often lack sufficient defect data to train high-accuracy deep learning models. Models trained on historical data from existing projects frequently struggle to achieve satisfactory generalization performance on new projects. Hence, this paper initially reformulates the traditional binary defect prediction task into a multi-label classification problem, employing defect categories described in the Common Weakness Enumeration (CWE) as fine-grained predictive labels. To enhance the model performance in cross-project scenarios, this paper proposes a multi-source domain adaptation framework that integrates adversarial training and attention mechanisms. Specifically, the proposed framework employs adversarial training to mitigate domain (i.e., software projects) discrepancies, and further utilizes domain-invariant features to capture feature correlations between each source domain and the target domain. Simultaneously, the proposed framework employs a weighted maximum mean discrepancy as an attention mechanism to minimize the representation distance between source and target domain features, facilitating model in learning more domain-independent features. The experiments on 8 real-world open-source projects show that the proposed approach achieves significant performance improvements compared to state-of-the-art baselines.

cs.SE↗

arXiv2024

TULIP: Transformer for Upsampling of LiDAR Point Clouds

LiDAR Upsampling is a challenging task for the perception systems of robots and autonomous vehicles, due to the sparse and irregular structure of large-scale scene contexts. Recent works propose to solve this problem by converting LiDAR data from 3D Euclidean space into an image super-resolution problem in 2D image space. Although their methods can generate high-resolution range images with fine-grained details, the resulting 3D point clouds often blur out details and predict invalid points. In this paper, we propose TULIP, a new method to reconstruct high-resolution LiDAR point clouds from low-resolution LiDAR input. We also follow a range image-based approach but specifically modify the patch and window geometries of a Swin-Transformer-based network to better fit the characteristics of range images. We conducted several experiments on three public real-world and simulated datasets. TULIP outperforms state-of-the-art methods in all relevant metrics and generates robust and more realistic point clouds than prior works.

cs.CV↗