Searcharxiv⌕ Search

arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 1,171 records · Page 65Linked to original sources
arXiv2023

High efficiency spin-decoupled modulation using chiral C2-symmetric meta-atoms

Orthogonal circularly polarized light is essential for multiplexing tunable metasurfaces. Mainstream spin-decoupled metasurfaces, consisting of numerous meta-atoms with mirror symmetry, rely on the cooperative modulation of the Pancharatnam-Berry (PB) phase and the propagation phase. This paper demonstrates spin-decoupled functionality through the synergistic utilization of planar chiral meta-atom phase response and PB phase. Based on the Jones calculus, it has been found that meta-atoms with chiral C2-symmetry owns a larger geometric parameter range with high cross-polarization ratio compared to those with mirror symmetry or higher symmetries at the same aspect ratio. This characteristic is advantageous in terms of enabling high-efficiency manipulation and enhancing the signal-to-noise ratio. As an example, 10 kinds of C2-symmetry chiral meta-atoms with a H-like shape are selected by the self-adaptive genetic algorithm to attain a full 2$π$ phase span with an interval of $π$/5. To mitigate the additional propagation phase change of the guided modes originated from the arrangement alternation upon the rotation of the meta-atoms, the enantiomer of chiral meta-atoms and its PB phase delay are adopted to minimize the difference between the actual and desired target phases. A polarization-insensitive metalens and a chiral virtual-moving metalens array are designed to demonstrate the spin-decoupled function with both high efficiency and signal-to-noise ratio. The work in this paper may trigger more exciting and interesting spin-decoupled multiplexing metasurfaces and broaden the prospect of chiroptical applications.

physics.optics↗
arXiv2023

Methods for Acquiring and Incorporating Knowledge into Stock Price Prediction: A Survey

Predicting stock prices presents a challenging research problem due to the inherent volatility and non-linear nature of the stock market. In recent years, knowledge-enhanced stock price prediction methods have shown groundbreaking results by utilizing external knowledge to understand the stock market. Despite the importance of these methods, there is a scarcity of scholarly works that systematically synthesize previous studies from the perspective of external knowledge types. Specifically, the external knowledge can be modeled in different data structures, which we group into non-graph-based formats and graph-based formats: 1) non-graph-based knowledge captures contextual information and multimedia descriptions specifically associated with an individual stock; 2) graph-based knowledge captures interconnected and interdependent information in the stock market. This survey paper aims to provide a systematic and comprehensive description of methods for acquiring external knowledge from various unstructured data sources and then incorporating it into stock price prediction models. We also explore fusion methods for combining external knowledge with historical price features. Moreover, this paper includes a compilation of relevant datasets and delves into potential future research directions in this domain.

q-fin.ST↗
arXiv2023

Polarization-insensitive dual-wavelength dispersion tunable metalens achieved by global modulation method

SF$_6$ is widely used as a gas-insulator in high-voltage power electrical system. Detecting SF$_6$ leaks using unmanned aerial vehicle (UAV)-based thermal cameras allows efficient large-scale inspections during routine maintenance. The emergence of lightweight metalenses can increase the endurance of UAVs. Simultaneously controlling dispersion and polarization properties in metalens is significant for thermal camera applications. However, via a propagation phase modulation method in which the phase is tuned locally, it is difficult and time-consuming to obtain enough different nanostructures to control multiwavelength independently while maintain the polarization-insensitive property. To this end, by using a global modulation method, a polarization-insensitive dual-wavelength achromatic and super-chromatic metalens are designed respectively. The working wavelength is set at 10.6 and 12 $\rmμ$m to match the absorption peaks of SF$_6$ and one of its decompositions (SO$_2$F$_2$), respectively. According to the operating wavelengths, only the geometric parameters of two nanofins are required to be optimized (through genetic algorithm). Then they are superimposed on each other to form cross-shaped meta-atoms. In order to control the influence between the two crossed nanofins, an additional term $Δf$ is introduced into the phase equation to modify the shape of the wavefront, whereby the phase dispersion can be easily engineered. Compared with local modulation, the number of unique nanostructures that need to be optimized can be reduced to two (operating at dual wavelengths) by the Pancharatnam-Berry (PB) phase based global modulation method. Therefore, the proposed design strategy is expected to circumvent difficulties in the local design approaches and can find widespread applications in multiwavelength imaging and spectroscopy.

physics.optics↗
arXiv2023

iEDA: An Open-Source Intelligent Physical Implementation Toolkit and Library

Open-source EDA shows promising potential in unleashing EDA innovation and lowering the cost of chip design. This paper presents an open-source EDA project, iEDA, aiming for building a basic infrastructure for EDA technology evolution and closing the industrial-academic gap in the EDA area. iEDA now covers the whole flow of physical design (including Floorplan, Placement, CTS, Routing, Timing Optimization etc.), and part of the analysis tools (Static Timing Analysis and Power Analysis). To demonstrate the effectiveness of iEDA, we implement and tape out three chips of different scales (from 700k to 1.5M gates) on different process nodes (110nm and 28nm) with iEDA. iEDA is publicly available from the project home page http://ieda.oscc.cc.

cs.AR↗
arXiv2023

Quantifying the overall characteristics of urban mobility considering spatial information

Quantification of the overall characteristics of urban mobility using coarse-grained methods is crucial for urban management, planning and sustainable development. Although some recent studies have provided quantification methods for coarse-grained numerical information regarding urban mobility, a method that can simultaneously capture numerical and spatial information remains an outstanding problem. Here, we use mathematical vectors to depict human mobility, with mobility magnitude representing numerical information and mobility direction representing spatial information. We then define anisotropy and centripetality metrics by vector computation to measure imbalance in direction distribution and orientation toward the city center of mobility flows, respectively. As a case study, we apply our method to 60 Chinese cities and identify three mobility patterns: strong monocentric, weak monocentric and polycentric. To better understand mobility pattern, we further study the allometric scaling of the average commuting distance and the spatiotemporal variations of the two metrics in different patterns. Finally, we build a microscopic model to explain the key mechanisms driving the diversity in anisotropy and centripetality. Our work offers a comprehensive method that considers both numerical and spatial information to quantify and classify the overall characteristics of urban mobility, enhancing our understanding of the structure and evolution of urban mobility systems.

physics.soc-ph↗
arXiv2023

Human Culture: A History Irrelevant and Predictable Experience

Human culture research has witnessed an opportunity of revolution thanks to the big data and social network revolution. Websites such as Douban.com, Goodreads.com, Pandora and IMDB become the new gold mine for cultural researchers. In 2021 and 2022, the author of this paper invented 2 data-free recommender systems for AI cold-start problem. The algorithms can recommend cultural and commercial products to users without reference to users' past preferences. The social implications of the new inventions are human cultural tastes can be predicted very precisely without any information related to human individuals. In this paper, we analyze the AI technologies and its cultural implications together with other AI algorithms. We show that human culture is (mostly) a history irrelevant and predictable experience.

cs.CY↗
arXiv2023

MFMAN-YOLO: A Method for Detecting Pole-like Obstacles in Complex Environment

In real-world traffic, there are various uncertainties and complexities in road and weather conditions. To solve the problem that the feature information of pole-like obstacles in complex environments is easily lost, resulting in low detection accuracy and low real-time performance, a multi-scale hybrid attention mechanism detection algorithm is proposed in this paper. First, the optimal transport function Monge-Kantorovich (MK) is incorporated not only to solve the problem of overlapping multiple prediction frames with optimal matching but also the MK function can be regularized to prevent model over-fitting; then, the features at different scales are up-sampled separately according to the optimized efficient multi-scale feature pyramid. Finally, the extraction of multi-scale feature space channel information is enhanced in complex environments based on the hybrid attention mechanism, which suppresses the irrelevant complex environment background information and focuses the feature information of pole-like obstacles. Meanwhile, this paper conducts real road test experiments in a variety of complex environments. The experimental results show that the detection precision, recall, and average precision of the method are 94.7%, 93.1%, and 97.4%, respectively, and the detection frame rate is 400 f/s. This research method can detect pole-like obstacles in a complex road environment in real time and accurately, which further promotes innovation and progress in the field of automatic driving.

cs.CV↗
arXiv2023

A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation

In this paper, we strive to answer the question "how to collaboratively learn convolutional neural network (CNN)-based and vision transformer (ViT)-based models by selecting and exchanging the reliable knowledge between them for semantic segmentation?" Accordingly, we propose an online knowledge distillation (KD) framework that can simultaneously learn compact yet effective CNN-based and ViT-based models with two key technical breakthroughs to take full advantage of CNNs and ViT while compensating their limitations. Firstly, we propose heterogeneous feature distillation (HFD) to improve students' consistency in low-layer feature space by mimicking heterogeneous features between CNNs and ViT. Secondly, to facilitate the two students to learn reliable knowledge from each other, we propose bidirectional selective distillation (BSD) that can dynamically transfer selective knowledge. This is achieved by 1) region-wise BSD determining the directions of knowledge transferred between the corresponding regions in the feature space and 2) pixel-wise BSD discerning which of the prediction knowledge to be transferred in the logit space. Extensive experiments on three benchmark datasets demonstrate that our proposed framework outperforms the state-of-the-art online distillation methods by a large margin, and shows its efficacy in learning collaboratively between ViT-based and CNN-based models.

cs.CV↗
arXiv2023

Local Conditional Neural Fields for Versatile and Generalizable Large-Scale Reconstructions in Computational Imaging

Deep learning has transformed computational imaging, but traditional pixel-based representations limit their ability to capture continuous, multiscale details of objects. Here we introduce a novel Local Conditional Neural Fields (LCNF) framework, leveraging a continuous implicit neural representation to address this limitation. LCNF enables flexible object representation and facilitates the reconstruction of multiscale information. We demonstrate the capabilities of LCNF in solving the highly ill-posed inverse problem in Fourier ptychographic microscopy (FPM) with multiplexed measurements, achieving robust, scalable, and generalizable large-scale phase retrieval. Unlike traditional neural fields frameworks, LCNF incorporates a local conditional representation that promotes model generalization, learning multiscale information, and efficient processing of large-scale imaging data. By combining an encoder and a decoder conditioned on a learned latent vector, LCNF achieves versatile continuous-domain super-resolution image reconstruction. We demonstrate accurate reconstruction of wide field-of-view, high-resolution phase images using only a few multiplexed measurements. LCNF robustly captures the continuous object priors and eliminates various phase artifacts, even when it is trained on imperfect datasets. The framework exhibits strong generalization, reconstructing diverse objects even with limited training data. Furthermore, LCNF can be trained on a physics simulator using natural images and successfully applied to experimental measurements on biological samples. Our results highlight the potential of LCNF for solving large-scale inverse problems in computational imaging, with broad applicability in various deep-learning-based techniques.

eess.IV↗
arXiv2023

Chrion: Optimizing Recurrent Neural Network Inference by Collaboratively Utilizing CPUs and GPUs

Deploying deep learning models in cloud clusters provides efficient and prompt inference services to accommodate the widespread application of deep learning. These clusters are usually equipped with host CPUs and accelerators with distinct responsibilities to handle serving requests, i.e. generalpurpose CPUs for input preprocessing and domain-specific GPUs for forward computation. Recurrent neural networks play an essential role in handling temporal inputs and display distinctive computation characteristics because of their high inter-operator parallelism. Hence, we propose Chrion to optimize recurrent neural network inference by collaboratively utilizing CPUs and GPUs. We formulate the model deployment in the CPU-GPU cluster as an NP-hard scheduling problem of directed acyclic graphs on heterogeneous devices. Given an input model in the ONNX format and user-defined SLO requirement, Chrion firstly preprocesses the model by model parsing and profiling, and then partitions the graph to select execution devices for each operator. When an online request arrives, Chrion performs forward computation according to the graph partition by executing the operators on the CPU and GPU in parallel. Our experimental results show that the execution time can be reduced by 19.4% at most in the latency-optimal pattern and GPU memory footprint by 67.5% in the memory-optimal pattern compared with the execution on the GPU.

cs.DC↗
arXiv2023

NTIRE 2023 Quality Assessment of Video Enhancement Challenge

This paper reports on the NTIRE 2023 Quality Assessment of Video Enhancement Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2023. This challenge is to address a major challenge in the field of video processing, namely, video quality assessment (VQA) for enhanced videos. The challenge uses the VQA Dataset for Perceptual Video Enhancement (VDPVE), which has a total of 1211 enhanced videos, including 600 videos with color, brightness, and contrast enhancements, 310 videos with deblurring, and 301 deshaked videos. The challenge has a total of 167 registered participants. 61 participating teams submitted their prediction results during the development phase, with a total of 3168 submissions. A total of 176 submissions were submitted by 37 participating teams during the final testing phase. Finally, 19 participating teams submitted their models and fact sheets, and detailed the methods they used. Some methods have achieved better results than baseline methods, and the winning methods have demonstrated superior prediction performance.

cs.CV↗
arXiv2023

Exploiting Transformer in Sparse Reward Reinforcement Learning for Interpretable Temporal Logic Motion Planning

Automaton based approaches have enabled robots to perform various complex tasks. However, most existing automaton based algorithms highly rely on the manually customized representation of states for the considered task, limiting its applicability in deep reinforcement learning algorithms. To address this issue, by incorporating Transformer into reinforcement learning, we develop a Double-Transformer-guided Temporal Logic framework (T2TL) that exploits the structural feature of Transformer twice, i.e., first encoding the LTL instruction via the Transformer module for efficient understanding of task instructions during the training and then encoding the context variable via the Transformer again for improved task performance. Particularly, the LTL instruction is specified by co-safe LTL. As a semantics-preserving rewriting operation, LTL progression is exploited to decompose the complex task into learnable sub-goals, which not only converts non-Markovian reward decision processes to Markovian ones, but also improves the sampling efficiency by simultaneous learning of multiple sub-tasks. An environment-agnostic LTL pre-training scheme is further incorporated to facilitate the learning of the Transformer module resulting in an improved representation of LTL. The simulation results demonstrate the effectiveness of the T2TL framework.

cs.RO↗
arXiv2023

A Peer-to-peer Federated Continual Learning Network for Improving CT Imaging from Multiple Institutions

Deep learning techniques have been widely used in computed tomography (CT) but require large data sets to train networks. Moreover, data sharing among multiple institutions is limited due to data privacy constraints, which hinders the development of high-performance DL-based CT imaging models from multi-institutional collaborations. Federated learning (FL) strategy is an alternative way to train the models without centralizing data from multi-institutions. In this work, we propose a novel peer-to-peer federated continual learning strategy to improve low-dose CT imaging performance from multiple institutions. The newly proposed method is called peer-to-peer continual FL with intermediate controllers, i.e., icP2P-FL. Specifically, different from the conventional FL model, the proposed icP2P-FL does not require a central server that coordinates training information for a global model. In the proposed icP2P-FL method, the peer-to-peer federated continual learning is introduced wherein the DL-based model is continually trained one client after another via model transferring and inter institutional parameter sharing due to the common characteristics of CT data among the clients. Furthermore, an intermediate controller is developed to make the overall training more flexible. Numerous experiments were conducted on the AAPM low-dose CT Grand Challenge dataset and local datasets, and the experimental results showed that the proposed icP2P-FL method outperforms the other comparative methods both qualitatively and quantitatively, and reaches an accuracy similar to a model trained with pooling data from all the institutions.

eess.IV↗
arXiv2023

Rethinking Mitosis Detection: Towards Diverse Data and Feature Representation

Mitosis detection is one of the fundamental tasks in computational pathology, which is extremely challenging due to the heterogeneity of mitotic cell. Most of the current studies solve the heterogeneity in the technical aspect by increasing the model complexity. However, lacking consideration of the biological knowledge and the complex model design may lead to the overfitting problem while limited the generalizability of the detection model. In this paper, we systematically study the morphological appearances in different mitotic phases as well as the ambiguous non-mitotic cells and identify that balancing the data and feature diversity can achieve better generalizability. Based on this observation, we propose a novel generalizable framework (MitDet) for mitosis detection. The data diversity is considered by the proposed diversity-guided sample balancing (DGSB). And the feature diversity is preserved by inter- and intra- class feature diversity-preserved module (InCDP). Stain enhancement (SE) module is introduced to enhance the domain-relevant diversity of both data and features simultaneously. Extensive experiments have demonstrated that our proposed model outperforms all the SOTA approaches in several popular mitosis detection datasets in both internal and external test sets using minimal annotation efforts with point annotations only. Comprehensive ablation studies have also proven the effectiveness of the rethinking of data and feature diversity balancing. By analyzing the results quantitatively and qualitatively, we believe that our proposed model not only achieves SOTA performance but also might inspire the future studies in new perspectives. Source code is at https://github.com/Onehour0108/MitDet.

cs.CV↗
arXiv2023

Exploratory mean-variance portfolio selection with Choquet regularizers

In this paper, we study a continuous-time exploratory mean-variance (EMV) problem under the framework of reinforcement learning (RL), and the Choquet regularizers are used to measure the level of exploration. By applying the classical Bellman principle of optimality, the Hamilton-Jacobi-Bellman equation of the EMV problem is derived and solved explicitly via maximizing statically a mean-variance constrained Choquet regularizer. In particular, the optimal distributions form a location-scale family, whose shape depends on the choices of the Choquet regularizer. We further reformulate the continuous-time Choquet-regularized EMV problem using a variant of the Choquet regularizer. Several examples are given under specific Choquet regularizers that generate broadly used exploratory samplers such as exponential, uniform and Gaussian. Finally, we design a RL algorithm to simulate and compare results under the two different forms of regularizers.

math.OC↗
arXiv2023

LogitMat : Zeroshot Learning Algorithm for Recommender Systems without Transfer Learning or Pretrained Models

Recommender system is adored in the internet industry as one of the most profitable technologies. Unlike other sectors such as fraud detection in the Fintech industry, recommender system is both deep and broad. In recent years, many researchers start to focus on the cold-start problem of recommender systems. In spite of the large volume of research literature, the majority of the research utilizes transfer learning / meta learning and pretrained model to solve the problem. Although the researchers claim the effectiveness of the approaches, everyone of them does rely on extra input data from other sources. In 2021 and 2022, several zeroshot learning algorithm for recommender system such as ZeroMat, DotMat, PoissonMat and PowerMat were invented. They are the first batch of the algorithms that rely on no transfer learning or pretrained models to tackle the problem. In this paper, we follow this line and invent a new zeroshot learning algorithm named LogitMat. We take advantage of the Zipf Law property of the user item rating values and logistic regression model to tackle the cold-start problem and generate competitive results with other competing techniques. We prove in experiments that our algorithm is fast, robust and effective.

cs.IR↗
arXiv2023

Taxonomy-Structured Domain Adaptation

Domain adaptation aims to mitigate distribution shifts among different domains. However, traditional formulations are mostly limited to categorical domains, greatly simplifying nuanced domain relationships in the real world. In this work, we tackle a generalization with taxonomy-structured domains, which formalizes domains with nested, hierarchical similarity structures such as animal species and product catalogs. We build on the classic adversarial framework and introduce a novel taxonomist, which competes with the adversarial discriminator to preserve the taxonomy information. The equilibrium recovers the classic adversarial domain adaptation's solution if given a non-informative domain taxonomy (e.g., a flat taxonomy where all leaf nodes connect to the root node) while yielding non-trivial results with other taxonomies. Empirically, our method achieves state-of-the-art performance on both synthetic and real-world datasets with successful adaptation. Code is available at https://github.com/Wang-ML-Lab/TSDA.

cs.LG↗
arXiv2023

PMaF: Deep Declarative Layers for Principal Matrix Features

We explore two differentiable deep declarative layers, namely least squares on sphere (LESS) and implicit eigen decomposition (IED), for learning the principal matrix features (PMaF). It can be used to represent data features with a low-dimensional vector containing dominant information from a high-dimensional matrix. We first solve the problems with iterative optimization in the forward pass and then backpropagate the solution for implicit gradients under a bi-level optimization framework. Particularly, adaptive descent steps with the backtracking line search method and descent decay in the tangent space are studied to improve the forward pass efficiency of LESS. Meanwhile, exploited data structures are used to greatly reduce the computational complexity in the backward pass of LESS and IED. Empirically, we demonstrate the superiority of our layers over the off-the-shelf baselines by comparing the solution optimality and computational requirements.

cs.LG↗