arXiv subjects

Yan Wang

Publications and source records attributed to Yan Wang.

At least 703 records · Page 39Linked to original sources

arXiv2023

Experimental demonstration of separating the waveparticle duality of a single photon with the quantum Cheshire cat

As a fundamental characteristic of physical entities, waveparticle duality describes whether a microscopic entity exhibits wave or particle attributes depending on the specific experimental setup. This assumption is premised on the notion that physical properties are inseparable from the objective carrier. However, after the concept of the quantum Cheshire cats was proposed, which makes the separation of physical attributes from the entity possible, the premise no longer holds. Furthermore, an experimental demonstration of the separation of the wave and particle attributes inspired by this scenario remains scarce. In this work, we experimentally separated the wave and particle attributes of a single photon by exploiting the quantum Cheshire cat concept for the first time. By applying a weak disturbance to the evolution of the system, we achieve an effect similar to the quantum Cheshire cat and demonstrated the separation of the wave and particle attributes via the extraction of weak values. Our work provides a new perspective for the indepth understanding of waveparticle duality and promotes the application of weak measurements in fundamentals of quantum mechanics.

quant-ph↗

arXiv2023

Precoding and Beamforming Design for Intelligent Reconfigurable Surface-Aided Hybrid Secure Spatial Modulation

Intelligent reflecting surface (IRS) is an emerging technology for wireless communication composed of a large number of low-cost passive devices with reconfigurable parameters, which can reflect signals with a certain phase shift and is capable of building programmable communication environment. In this paper, to avoid the high hardware cost and energy consumption in spatial modulation (SM), an IRS-aided hybrid secure SM (SSM) system with a hybrid precoder is proposed. To improve the security performance, we formulate an optimization problem to maximize the secrecy rate (SR) by jointly optimizing the beamforming at IRS and hybrid precoding at the transmitter. Considering that the SR has no closed form expression, an approximate SR (ASR) expression is derived as the objective function. To improve the SR performance, three IRS beamforming methods, called IRS alternating direction method of multipliers (IRS-ADMM), IRS block coordinate ascend (IRS-BCA) and IRS semi-definite relaxation (IRS-SDR), are proposed. As for the hybrid precoding design, approximated secrecy rate-successive convex approximation (ASR-SCA) method and cut-off rate-gradient ascend (COR-GA) method are proposed. Simulation results demonstrate that the proposed IRS-SDR and IRS-ADMM beamformers harvest substantial SR performance gains over IRS-BCA. Particularly, the proposed IRS-ADMM and IRS-BCA are of low-complexity at the expense of a little performance loss compared with IRS-SDR. For hybrid precoding, the proposed ASR-SCA performs better than COR-GA in the high transmit power region.

cs.IT↗

arXiv2023

DCMT: A Direct Entire-Space Causal Multi-Task Framework for Post-Click Conversion Estimation

In recommendation scenarios, there are two long-standing challenges, i.e., selection bias and data sparsity, which lead to a significant drop in prediction accuracy for both Click-Through Rate (CTR) and post-click Conversion Rate (CVR) tasks. To cope with these issues, existing works emphasize on leveraging Multi-Task Learning (MTL) frameworks (Category 1) or causal debiasing frameworks (Category 2) to incorporate more auxiliary data in the entire exposure/inference space D or debias the selection bias in the click/training space O. However, these two kinds of solutions cannot effectively address the not-missing-at-random problem and debias the selection bias in O to fit the inference in D. To fill the research gaps, we propose a Direct entire-space Causal Multi-Task framework, namely DCMT, for post-click conversion prediction in this paper. Specifically, inspired by users' decision process of conversion, we propose a new counterfactual mechanism to debias the selection bias in D, which can predict the factual CVR and the counterfactual CVR under the soft constraint of a counterfactual prior knowledge. Extensive experiments demonstrate that our DCMT can improve the state-of-the-art methods by an average of 1.07% in terms of CVR AUC on the five offline datasets and 0.75% in terms of PV-CVR on the online A/B test (the Alipay Search). Such improvements can increase millions of conversions per week in real industrial applications, e.g., the Alipay Search.

cs.IR↗

arXiv2023

On stability of rainbow matchings

We show that for any integer $k\ge 1$ there exists an integer $t_0(k)$ such that for integers $t, k_1, \ldots, k_{t+1}, n$ with $t>t_0(k)$, $\max\{k_1, \ldots, k_{t+1}\}\le k$, and $n > 2k(t+1)$, the following holds: If $F_i \subseteq {[n]\choose k_i}$ and $|F_i|> {n\choose k_i}-{n-t\choose k_i} - {n-t-k \choose k_i-1} + 1$ for all $i \in [t+1]$, then either $\{F_1,\ldots, F_{t+1}\}$ admits a rainbow matching of size $t+1$ or there exists $W\in {[n]\choose t}$ such that $W$ is a vertex cover of $F_i$ for all $i\in [t+1]$. This may be viewed as a rainbow non-uniform extension of the classical Hilton-Milner theorem. We also show that the same holds for every $t$ and $n > 2k^3t$, generalizing a recent stability result of Frankl and Kupavskii on matchings to rainbow matchings.

math.CO↗

arXiv2023

Balanced subdivisions of a large clique in graphs with high average degree

In 1984, Thomassen conjectured that for every constant $k \in \mathbb{N}$, there exists $d$ such that every graph with average degree at least $d$ contains a balanced subdivision of a complete graph on $k$ vertices, i.e. a subdivision in which each edge is subdivided the same number of times. Recently, Liu and Montgomery confirmed Thomassen's conjecture. We show that for every constant $0<c<1/2$, every graph with average degree at least $d$ contains a balanced subdivision of a complete graph of size at least $Ω(d^{c})$. Note that this bound is almost optimal. Moreover, we show that every sparse expander with minimum degree at least $d$ contains a balanced subdivision of a complete graph of size at least $Ω(d)$.

math.CO↗

arXiv2023

Exploring Invariant Representation for Visible-Infrared Person Re-Identification

Cross-spectral person re-identification, which aims to associate identities to pedestrians across different spectra, faces a main challenge of the modality discrepancy. In this paper, we address the problem from both image-level and feature-level in an end-to-end hybrid learning framework named robust feature mining network (RFM). In particular, we observe that the reflective intensity of the same surface in photos shot in different wavelengths could be transformed using a linear model. Besides, we show the variable linear factor across the different surfaces is the main culprit which initiates the modality discrepancy. We integrate such a reflection observation into an image-level data augmentation by proposing the linear transformation generator (LTG). Moreover, at the feature level, we introduce a cross-center loss to explore a more compact intra-class distribution and modality-aware spatial attention to take advantage of textured regions more efficiently. Experiment results on two standard cross-spectral person re-identification datasets, i.e., RegDB and SYSU-MM01, have demonstrated state-of-the-art performance.

cs.CV↗

arXiv2023

GeneFormer: Learned Gene Compression using Transformer-based Context Modeling

With the development of gene sequencing technology, an explosive growth of gene data has been witnessed. And the storage of gene data has become an important issue. Traditional gene data compression methods rely on general software like G-zip, which fails to utilize the interrelation of nucleotide sequence. Recently, many researchers begin to investigate deep learning based gene data compression method. In this paper, we propose a transformer-based gene compression method named GeneFormer. Specifically, we first introduce a modified transformer structure to fully explore the nucleotide sequence dependency. Then, we propose fixed-length parallel grouping to accelerate the decoding speed of our autoregressive model. Experimental results on real-world datasets show that our method saves 29.7% bit rate compared with the state-of-the-art method, and the decoding speed is significantly faster than all existing learning-based gene compression methods.

cs.LG↗

arXiv2023

Discovering explicit Reynolds-averaged turbulence closures for turbulent separated flows through deep learning-based symbolic regression with non-linear corrections

This work introduces a novel data-driven framework to formulate explicit algebraic Reynolds-averaged Navier-Stokes (RANS) turbulence closures. Recent years have witnessed a blossom in applying machine learning (ML) methods to revolutionize the paradigm of turbulence modeling. However, due to the black-box essence of most ML methods, it is currently hard to extract interpretable information and knowledge from data-driven models. To address this critical limitation, this work leverages deep learning with symbolic regression methods to discover hidden governing equations of Reynolds stress models. Specifically, the Reynolds stress tensor is decomposed into linear and non-linear parts. While the linear part is taken as the regular linear eddy viscosity model, a long short-term memory neural network is employed to generate symbolic terms on which tractable mathematical expressions for the non-linear counterpart are built. A novel reinforcement learning algorithm is employed to train the neural network to produce best-fitted symbolic expressions. Within the proposed framework, the Reynolds stress closure is explicitly expressed in algebraic forms, thus allowing for direct functional inference. On the other hand, the Galilean and rotational invariance are craftily respected by constructing the training feature space with independent invariants and tensor basis functions. The performance of the present methodology is validated through numerical simulations of three different canonical flows that deviate in geometrical configurations. The results demonstrate promising accuracy improvements over traditional RANS models, showing the generalization ability of the proposed method. Moreover, with the given explicit model equations, it can be easier to interpret the influence of input features on generated models.

physics.flu-dyn↗

arXiv2023

Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problem

Self-supervised monocular depth estimation (MDE) models universally suffer from the notorious edge-fattening issue. Triplet loss, as a widespread metric learning strategy, has largely succeeded in many computer vision applications. In this paper, we redesign the patch-based triplet loss in MDE to alleviate the ubiquitous edge-fattening issue. We show two drawbacks of the raw triplet loss in MDE and demonstrate our problem-driven redesigns. First, we present a min. operator based strategy applied to all negative samples, to prevent well-performing negatives sheltering the error of edge-fattening negatives. Second, we split the anchor-positive distance and anchor-negative distance from within the original triplet, which directly optimizes the positives without any mutual effect with the negatives. Extensive experiments show the combination of these two small redesigns can achieve unprecedented results: Our powerful and versatile triplet loss not only makes our model outperform all previous SoTA by a large margin, but also provides substantial performance boosts to a large number of existing models, while introducing no extra inference computation at all.

cs.CV↗

arXiv2023

Symmetry breaking of Pancharatnam-Berry phase using non-axisymmetric meta-atoms

The Pancharatnam-Berry (PB) phase in metasurfaces obeys the symmetry restriction, according to which the PB phases of two orthogonal circularly polarized waves are the same but with opposite signs. Here, we reveal a general mechanism to break the axisymmetry of meta-atoms in order to break the PB-phase symmetry restriction. As a proof of concept, we designed a novel meta-atom with a QR-code structure and successfully demonstrated circular-polarization multiplexing metasurface holography. This study provides a fundamentally new understanding of the PB phase and opens a path for arbitrary wavefront engineering using asymmetric electromagnetic structures.

physics.optics↗

arXiv2023

Investigating the Dynamics of Social Norm Emergence within Online Communities

Although the effects of the social norm on mitigating misinformation are identified, scant knowledge exists about the patterns of social norm emergence, such as the patterns and variations of social tipping in online communities with diverse characteristics. Accordingly, this study investigates the features of social tipping in online communities and examines the correlations between the tipping features and characteristics of online communities. Taking the side effects of COVID-19 vaccination as the case topic, we first track the patterns of tipping features in 100 online communities, which are detected using Louvain Algorithm from the aggregated communication network on Twitter between May 2020 and April 2021. Then, we use multi-variant linear regression to explore the correlations between tipping features and community characteristics. We find that social tipping in online communities can sustain for two to four months and lead to a 50% increase in populations who accept the normative belief in online communities. The regression indicates that the duration of social tipping is positively related to the community populations and original acceptance of social norms, while the correlation between the tipping duration and the degrees among community members is negative. Additionally, the network modularity and original acceptance of social norms have negative relationships with the extent of social tipping, while the degree and betweenness centrality can have significant positive relationships with the extent of tipping. Our findings shed light on more precise normative interventions on misinformation in digital environments as it offers preliminary evidence about the timing and mechanism of social norm emergence.

cs.SI↗

arXiv2022

EarSpy: Spying Caller Speech and Identity through Tiny Vibrations of Smartphone Ear Speakers

Eavesdropping from the user's smartphone is a well-known threat to the user's safety and privacy. Existing studies show that loudspeaker reverberation can inject speech into motion sensor readings, leading to speech eavesdropping. While more devastating attacks on ear speakers, which produce much smaller scale vibrations, were believed impossible to eavesdrop with zero-permission motion sensors. In this work, we revisit this important line of reach. We explore recent trends in smartphone manufacturers that include extra/powerful speakers in place of small ear speakers, and demonstrate the feasibility of using motion sensors to capture such tiny speech vibrations. We investigate the impacts of these new ear speakers on built-in motion sensors and examine the potential to elicit private speech information from the minute vibrations. Our designed system EarSpy can successfully detect word regions, time, and frequency domain features and generate a spectrogram for each word region. We train and test the extracted data using classical machine learning algorithms and convolutional neural networks. We found up to 98.66% accuracy in gender detection, 92.6% detection in speaker detection, and 56.42% detection in digit detection (which is 5X more significant than the random selection (10%)). Our result unveils the potential threat of eavesdropping on phone conversations from ear speakers using motion sensors.

cs.SD↗

arXiv2022

A K-variate Time Series Is Worth K Words: Evolution of the Vanilla Transformer Architecture for Long-term Multivariate Time Series Forecasting

Multivariate time series forecasting (MTSF) is a fundamental problem in numerous real-world applications. Recently, Transformer has become the de facto solution for MTSF, especially for the long-term cases. However, except for the one forward operation, the basic configurations in existing MTSF Transformer architectures were barely carefully verified. In this study, we point out that the current tokenization strategy in MTSF Transformer architectures ignores the token uniformity inductive bias of Transformers. Therefore, the vanilla MTSF transformer struggles to capture details in time series and presents inferior performance. Based on this observation, we make a series of evolution on the basic architecture of the vanilla MTSF transformer. We vary the flawed tokenization strategy, along with the decoder structure and embeddings. Surprisingly, the evolved simple transformer architecture is highly effective, which successfully avoids the over-smoothing phenomena in the vanilla MTSF transformer, achieves a more detailed and accurate prediction, and even substantially outperforms the state-of-the-art Transformers that are well-designed for MTSF.

cs.LG↗

arXiv2022

SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud

LiDAR-based 3D object detection is an indispensable task in advanced autonomous driving systems. Though impressive detection results have been achieved by superior 3D detectors, they suffer from significant performance degeneration when facing unseen domains, such as different LiDAR configurations, different cities, and weather conditions. The mainstream approaches tend to solve these challenges by leveraging unsupervised domain adaptation (UDA) techniques. However, these UDA solutions just yield unsatisfactory 3D detection results when there is a severe domain shift, e.g., from Waymo (64-beam) to nuScenes (32-beam). To address this, we present a novel Semi-Supervised Domain Adaptation method for 3D object detection (SSDA3D), where only a few labeled target data is available, yet can significantly improve the adaptation performance. In particular, our SSDA3D includes an Inter-domain Adaptation stage and an Intra-domain Generalization stage. In the first stage, an Inter-domain Point-CutMix module is presented to efficiently align the point cloud distribution across domains. The Point-CutMix generates mixed samples of an intermediate domain, thus encouraging to learn domain-invariant knowledge. Then, in the second stage, we further enhance the model for better generalization on the unlabeled target set. This is achieved by exploring Intra-domain Point-MixUp in semi-supervised learning, which essentially regularizes the pseudo label distribution. Experiments from Waymo to nuScenes show that, with only 10% labeled target data, our SSDA3D can surpass the fully-supervised oracle model with 100% target label. Our code is available at https://github.com/yinjunbo/SSDA3D.

cs.CV↗

arXiv2022

Generalizing Math Word Problem Solvers via Solution Diversification

Current math word problem (MWP) solvers are usually Seq2Seq models trained by the (one-problem; one-solution) pairs, each of which is made of a problem description and a solution showing reasoning flow to get the correct answer. However, one MWP problem naturally has multiple solution equations. The training of an MWP solver with (one-problem; one-solution) pairs excludes other correct solutions, and thus limits the generalizability of the MWP solver. One feasible solution to this limitation is to augment multiple solutions to a given problem. However, it is difficult to collect diverse and accurate augment solutions through human efforts. In this paper, we design a new training framework for an MWP solver by introducing a solution buffer and a solution discriminator. The buffer includes solutions generated by an MWP solver to encourage the training data diversity. The discriminator controls the quality of buffered solutions to participate in training. Our framework is flexibly applicable to a wide setting of fully, semi-weakly and weakly supervised training for all Seq2Seq MWP solvers. We conduct extensive experiments on a benchmark dataset Math23k and a new dataset named Weak12k, and show that our framework improves the performance of various MWP solvers under different settings by generating correct and diverse solutions.

cs.CL↗

arXiv2022

Post-Training Quantization for Cross-Platform Learned Image Compression

It has been witnessed that learned image compression has outperformed conventional image coding techniques and tends to be practical in industrial applications. One of the most critical issues that need to be considered is the non-deterministic calculation, which makes the probability prediction cross-platform inconsistent and frustrates successful decoding. We propose to solve this problem by introducing well-developed post-training quantization and making the model inference integer-arithmetic-only, which is much simpler than presently existing training and fine-tuning based approaches yet still keeps the superior rate-distortion performance of learned image compression. Based on that, we further improve the discretization of the entropy parameters and extend the deterministic inference to fit Gaussian mixture models. With our proposed methods, the current state-of-the-art image compression models can infer in a cross-platform consistent manner, which makes the further development and practice of learned image compression more promising.

eess.IV↗

arXiv2022

Intriguing Findings of Frequency Selection for Image Deblurring

Blur was naturally analyzed in the frequency domain, by estimating the latent sharp image and the blur kernel given a blurry image. Recent progress on image deblurring always designs end-to-end architectures and aims at learning the difference between blurry and sharp image pairs from pixel-level, which inevitably overlooks the importance of blur kernels. This paper reveals an intriguing phenomenon that simply applying ReLU operation on the frequency domain of a blur image followed by inverse Fourier transform, i.e., frequency selection, provides faithful information about the blur pattern (e.g., the blur direction and blur level, implicitly shows the kernel pattern). Based on this observation, we attempt to leverage kernel-level information for image deblurring networks by inserting Fourier transform, ReLU operation, and inverse Fourier transform to the standard ResBlock. 1x1 convolution is further added to let the network modulate flexible thresholds for frequency selection. We term our newly built block as Res FFT-ReLU Block, which takes advantages of both kernel-level and pixel-level features via learning frequency-spatial dual-domain representations. Extensive experiments are conducted to acquire a thorough analysis on the insights of the method. Moreover, after plugging the proposed block into NAFNet, we can achieve 33.85 dB in PSNR on GoPro dataset. Our method noticeably improves backbone architectures without introducing many parameters, while maintaining low computational complexity. Code is available at https://github.com/DeepMed-Lab/DeepRFT-AAAI2023.

cs.CV↗

arXiv2022

DynaVIG: Monocular Vision/INS/GNSS Integrated Navigation and Object Tracking for AGV in Dynamic Scenes

Visual-Inertial Odometry (VIO) usually suffers from drifting over long-time runs, the accuracy is easily affected by dynamic objects. We propose DynaVIG, a navigation and object tracking system based on the integration of Monocular Vision, Inertial Navigation System (INS), and Global Navigation Satellite System (GNSS). Our system aims to provide an accurate global estimation of the navigation states and object poses for the automated ground vehicle (AGV) in dynamic scenes. Due to the scale ambiguity of the object, a prior height model is proposed to initialize the object pose, and the scale is continuously estimated with the aid of GNSS and INS. To precisely track the object with complex moving, we establish an accurate dynamics model according to its motion state. Then the multi-sensor observations are optimized in a unified framework. Experiments on the KITTI dataset demonstrate that the multisensor fusion can effectively improve the accuracy of navigation and object tracking, compared to state-of-the-art methods. In addition, the proposed system achieves good estimation of the objects that change speed or direction.

cs.RO↗