arXiv subjects

Yi Yu

Publications and source records attributed to Yi Yu.

At least 217 records · Page 12Linked to original sources

arXiv2022

Sparsity-Aware Robust Normalized Subband Adaptive Filtering algorithms based on Alternating Optimization

This paper proposes a unified sparsity-aware robust normalized subband adaptive filtering (SA-RNSAF) algorithm for identification of sparse systems under impulsive noise. The proposed SA-RNSAF algorithm generalizes different algorithms by defining the robust criterion and sparsity-aware penalty. Furthermore, by alternating optimization of the parameters (AOP) of the algorithm, including the step-size and the sparsity penalty weight, we develop the AOP-SA-RNSAF algorithm, which not only exhibits fast convergence but also obtains low steady-state misadjustment for sparse systems. Simulations in various noise scenarios have verified that the proposed AOP-SA-RNSAF algorithm outperforms existing techniques.

cs.LG↗

arXiv2022

Investigation of Singing Voice Separation for Singing Voice Detection in Polyphonic Music

Singing voice detection (SVD), to recognize vocal parts in the song, is an essential task in music information retrieval (MIR). The task remains challenging since singing voice varies and intertwines with the accompaniment music, especially for some complicated polyphonic music such as choral music recordings. To address this problem, we investigate singing voice detection while discarding the interference from the accompaniment. The proposed SVD has two steps: i. The singing voice separation (SVS) technique is first utilized to filter out the singing voice's potential part coarsely. ii. Upon the continuity of vocal in the time domain, Long-term Recurrent Convolutional Networks (LRCN) is used to learn compositional features. Moreover, to eliminate the outliers, we choose to use a median filter for time-domain smoothing. Experimental results show that the proposed method outperforms the existing state-of-the-art works on two public datasets, the Jamendo Corpus and the RWC pop dataset.

eess.AS↗

arXiv2022

Lightweight Bimodal Network for Single-Image Super-Resolution via Symmetric CNN and Recursive Transformer

Single-image super-resolution (SISR) has achieved significant breakthroughs with the development of deep learning. However, these methods are difficult to be applied in real-world scenarios since they are inevitably accompanied by the problems of computational and memory costs caused by the complex operations. To solve this issue, we propose a Lightweight Bimodal Network (LBNet) for SISR. Specifically, an effective Symmetric CNN is designed for local feature extraction and coarse image reconstruction. Meanwhile, we propose a Recursive Transformer to fully learn the long-term dependence of images thus the global information can be fully used to further refine texture details. Studies show that the hybrid of CNN and Transformer can build a more efficient model. Extensive experiments have proved that our LBNet achieves more prominent performance than other state-of-the-art methods with a relatively low computational cost and memory consumption. The code is available at https://github.com/IVIPLab/LBNet.

cs.CV↗

arXiv2022

Feature Distillation Interaction Weighting Network for Lightweight Image Super-Resolution

Convolutional neural networks based single-image super-resolution (SISR) has made great progress in recent years. However, it is difficult to apply these methods to real-world scenarios due to the computational and memory cost. Meanwhile, how to take full advantage of the intermediate features under the constraints of limited parameters and calculations is also a huge challenge. To alleviate these issues, we propose a lightweight yet efficient Feature Distillation Interaction Weighted Network (FDIWN). Specifically, FDIWN utilizes a series of specially designed Feature Shuffle Weighted Groups (FSWG) as the backbone, and several novel mutual Wide-residual Distillation Interaction Blocks (WDIB) form an FSWG. In addition, Wide Identical Residual Weighting (WIRW) units and Wide Convolutional Residual Weighting (WCRW) units are introduced into WDIB for better feature distillation. Moreover, a Wide-Residual Distillation Connection (WRDC) framework and a Self-Calibration Fusion (SCF) unit are proposed to interact features with different scales more flexibly and efficiently.Extensive experiments show that our FDIWN is superior to other models to strike a good balance between model performance and efficiency. The code is available at https://github.com/IVIPLab/FDIWN.

cs.CV↗

arXiv2022

Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond

Rain removal aims to remove rain streaks from images/videos and reduce the disruptive effects caused by rain. It not only enhances image/video visibility but also allows many computer vision algorithms to function properly. This paper makes the first attempt to conduct a comprehensive study on the robustness of deep learning-based rain removal methods against adversarial attacks. Our study shows that, when the image/video is highly degraded, rain removal methods are more vulnerable to the adversarial attacks as small distortions/perturbations become less noticeable or detectable. In this paper, we first present a comprehensive empirical evaluation of various methods at different levels of attacks and with various losses/targets to generate the perturbations from the perspective of human perception and machine analysis tasks. A systematic evaluation of key modules in existing methods is performed in terms of their robustness against adversarial attacks. From the insights of our analysis, we construct a more robust deraining method by integrating these effective modules. Finally, we examine various types of adversarial attacks that are specific to deraining problems and their effects on both human and machine vision tasks, including 1) rain region attacks, adding perturbations only in the rain regions to make the perturbations in the attacked rain images less visible; 2) object-sensitive attacks, adding perturbations only in regions near the given objects. Code is available at https://github.com/yuyi-sd/Robust_Rain_Removal.

cs.CV↗

arXiv2022

Conjugate Gradient Adaptive Learning with Tukey's Biweight M-Estimate

We propose a novel M-estimate conjugate gradient (CG) algorithm, termed Tukey's biweight M-estimate CG (TbMCG), for system identification in impulsive noise environments. In particular, the TbMCG algorithm can achieve a faster convergence while retaining a reduced computational complexity as compared to the recursive least-squares (RLS) algorithm. Specifically, the Tukey's biweight M-estimate incorporates a constraint into the CG filter to tackle impulsive noise environments. Moreover, the convergence behavior of the TbMCG algorithm is analyzed. Simulation results confirm the excellent performance of the proposed TbMCG algorithm for system identification and active noise control applications.

cs.LG↗

arXiv2022

FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic Segmentation

Real-time semantic segmentation, which can be visually understood as the pixel-level classification task on the input image, currently has broad application prospects, especially in the fast-developing fields of autonomous driving and drone navigation. However, the huge burden of calculation together with redundant parameters are still the obstacles to its technological development. In this paper, we propose a Fast Bilateral Symmetrical Network (FBSNet) to alleviate the above challenges. Specifically, FBSNet employs a symmetrical encoder-decoder structure with two branches, semantic information branch and spatial detail branch. The Semantic Information Branch (SIB) is the main branch with semantic architecture to acquire the contextual information of the input image and meanwhile acquire sufficient receptive field. While the Spatial Detail Branch (SDB) is a shallow and simple network used to establish local dependencies of each pixel for preserving details, which is essential for restoring the original resolution during the decoding phase. Meanwhile, a Feature Aggregation Module (FAM) is designed to effectively combine the output of these two branches. Experimental results of Cityscapes and CamVid show that the proposed FBSNet can strike a good balance between accuracy and efficiency. Specifically, it obtains 70.9\% and 68.9\% mIoU along with the inference speed of 90 fps and 120 fps on these two test datasets, respectively, with only 0.62 million parameters on a single RTX 2080Ti GPU. The code is available at https://github.com/IVIPLab/FBSNet.

cs.CV↗

arXiv2022

Recent Advances and Challenges in Deep Audio-Visual Correlation Learning

Audio-visual correlation learning aims to capture essential correspondences and understand natural phenomena between audio and video. With the rapid growth of deep learning, an increasing amount of attention has been paid to this emerging research issue. Through the past few years, various methods and datasets have been proposed for audio-visual correlation learning, which motivate us to conclude a comprehensive survey. This survey paper focuses on state-of-the-art (SOTA) models used to learn correlations between audio and video, but also discusses some tasks of definition and paradigm applied in AI multimedia. In addition, we investigate some objective functions frequently used for optimizing audio-visual correlation learning models and discuss how audio-visual data is exploited in the optimization process. Most importantly, we provide an extensive comparison and summarization of the recent progress of SOTA audio-visual correlation learning and discuss future research directions.

cs.MM↗

arXiv2022

Optimal partition recovery in general graphs

We consider a graph-structured change point problem in which we observe a random vector with piecewise constant but unknown mean and whose independent, sub-Gaussian coordinates correspond to the $n$ nodes of a fixed graph. We are interested in the localisation task of recovering the partition of the nodes associated to the constancy regions of the mean vector. When the partition $\mathcal{S}$ consists of only two elements, we characterise the difficulty of the localisation problem in terms of four key parameters: the maximal noise variance $σ^2$, the size $Δ$ of the smaller element of the partition, the magnitude $κ$ of the difference in the signal values across contiguous elements of the partition and the sum of the effective resistance edge weights $|\partial_r(\mathcal{S})|$ of the corresponding cut -- a graph theoretic quantity quantifying the size of the partition boundary. In particular, we demonstrate an information theoretical lower bound implying that, in the low signal-to-noise ratio regime $κ^2 Δσ^{-2} |\partial_r(\mathcal{S})|^{-1} \lesssim 1$, no consistent estimator of the true partition exists. On the other hand, when $κ^2 Δσ^{-2} |\partial_r(\mathcal{S})|^{-1} \gtrsim ζ_n \log\{r(|E|)\}$, with $r(|E|)$ being the sum of effective resistance weighted edges and $ζ_n$ being any diverging sequence in $n$, we show that a polynomial-time, approximate $\ell_0$-penalised least squared estimator delivers a localisation error -- measured by the symmetric difference between the true and estimated partition -- of order $ κ^{-2} σ^2 |\partial_r(\mathcal{S})| \log\{r(|E|)\}$. Aside from the $\log\{r(|E|)\}$ term, this rate is minimax optimal. Finally, we provide discussions on the localisation error for more general partitions of unknown sizes.

math.ST↗

arXiv2022

Denoising and change point localisation in piecewise-constant high-dimensional regression coefficients

We study the theoretical properties of the fused lasso procedure originally proposed by \cite{tibshirani2005sparsity} in the context of a linear regression model in which the regression coefficient are totally ordered and assumed to be sparse and piecewise constant. Despite its popularity, to the best of our knowledge, estimation error bounds in high-dimensional settings have only been obtained for the simple case in which the design matrix is the identity matrix. We formulate a novel restricted isometry condition on the design matrix that is tailored to the fused lasso estimator and derive estimation bounds for both the constrained version of the fused lasso assuming dense coefficients and for its penalised version. We observe that the estimation error can be dominated by either the lasso or the fused lasso rate, depending on whether the number of non-zero coefficient is larger than the number of piece-wise constant segments. Finally, we devise a post-processing procedure to recover the piecewise-constant pattern of the coefficients. Extensive numerical experiments support our theoretical findings.

math.ST↗

arXiv2022

Active noise control techniques for nonlinear systems

Most of the literature focuses on the development of the linear active noise control (ANC) techniques. However, ANC systems might have to deal with some nonlinear components and the performance of linear ANC techniques may degrade in this scenario. To overcome this limitation, nonlinear ANC (NLANC) algorithms were developed. In Part II, we review the development of NLANC algorithms during the last decade. The contributions of heuristic ANC algorithms are outlined. Moreover, we emphasize recent advances of NLANC algorithms, such as spline ANC algorithms, kernel adaptive filters, and nonlinear distributed ANC algorithms. Then, we present recent applications of ANC technique including linear and nonlinear perspectives. Future research challenges regarding ANC techniques are also discussed.

cs.LG↗

arXiv2022

Leaning Compact and Representative Features for Cross-Modality Person Re-Identification

This paper pays close attention to the cross-modality visible-infrared person re-identification (VI Re-ID) task, which aims to match pedestrian samples between visible and infrared modes. In order to reduce the modality-discrepancy between samples from different cameras, most existing works usually use constraints based on Euclidean metric. Because of the Euclidean based distance metric strategy cannot effectively measure the internal angles between the embedded vectors, the existing solutions cannot learn the angularly discriminative feature embedding. Since the most important factor affecting the classification task based on embedding vector is whether there is an angularly discriminative feature space, in this paper, we present a new loss function called Enumerate Angular Triplet (EAT) loss. Also, motivated by the knowledge distillation, to narrow down the features between different modalities before feature embedding, we further present a novel Cross-Modality Knowledge Distillation (CMKD) loss. Benefit from the above two considerations, the embedded features are discriminative enough in a way to tackle modality-discrepancy problem. The experimental results on RegDB and SYSU-MM01 datasets have demonstrated that the proposed method is superior to the other most advanced methods in terms of impressive performance. Code is available at https://github.com/IVIPLab/LCCRF.

cs.CV↗

arXiv2022

Localising change points in piecewise polynomials of general degrees

In this paper we are concerned with a sequence of univariate random variables with piecewise polynomial means and independent sub-Gaussian noise. The underlying polynomials are allowed to be of arbitrary but fixed degrees. All the other model parameters are allowed to vary depending on the sample size. We propose a two-step estimation procedure based on the $\ell_0$-penalisation and provide upper bounds on the localisation error. We complement these results by deriving a global information-theoretic lower bounds, which show that our two-step estimators are nearly minimax rate-optimal. We also show that our estimator enjoys near optimally adaptive performance by attaining individual localisation errors depending on the level of smoothness at individual change points of the underlying signal. In addition, under a special smoothness constraint, we provide a minimax lower bound on the localisation errors. This lower bound is independent of the polynomial orders and is sharper than the global minimax lower bound.

math.ST↗

arXiv2022

Measurement of longitudinal spin transfer of the $Λ(\barΛ)$ hyperon in polarized p+p collisions at $\sqrt{s}=200$ GeV at RHIC-STAR

Since the first surprising results on the spin structure of the proton by the EMC experiment in the late 1980s, much progress has been made in understanding the origin of the proton spin. However, the sea quark contribution to the proton spin, for example, the helicity distributions of the strange quark (anti-quark), $s(\bar{s})$, is still not well constrained by experimental data. Since the $s(\bar{s})$ is expected to carry a substantial fraction of the spin of the $Λ(\barΛ)$ hyperon, measurements of the longitudinal spin transfer, $D_{LL}$, of the $Λ(\barΛ$) hyperon can thus shed light on the helicity distribution of the $s(\bar{s})$ and the longitudinally polarized fragmentation functions. In these proceedings, we will present the status of the $Λ(\barΛ$) $D_{LL}$ analysis using data collected at RHIC-STAR in 2015, for the pseudo-rapidity $|η| < 1.2$ and transverse momenta up to $8.0$ GeV$/c$. The $D_{LL}$ as a function of the longitudinal momentum fraction of the $Λ(\barΛ)$ hyperon in the jet is also investigated. This data set is about twice as large as the 2009 data used for the previously published $D_{LL}$ results.

hep-ex↗

arXiv2021

Variational Autoencoder with CCA for Audio-Visual Cross-Modal Retrieval

Cross-modal retrieval is to utilize one modality as a query to retrieve data from another modality, which has become a popular topic in information retrieval, machine learning, and database. How to effectively measure the similarity between different modality data is the major challenge of cross-modal retrieval. Although several reasearch works have calculated the correlation between different modality data via learning a common subspace representation, the encoder's ability to extract features from multi-modal information is not satisfactory. In this paper, we present a novel variational autoencoder (VAE) architecture for audio-visual cross-modal retrieval, by learning paired audio-visual correlation embedding and category correlation embedding as constraints to reinforce the mutuality of audio-visual information. On the one hand, audio encoder and visual encoder separately encode audio data and visual data into two different latent spaces. Further, two mutual latent spaces are respectively constructed by canonical correlation analysis (CCA). On the other hand, probabilistic modeling methods is used to deal with possible noise and missing information in the data. Additionally, in this way, the cross-modal discrepancy from intra-modal and inter-modal information are simultaneously eliminated in the joint embedding subspace. We conduct extensive experiments over two benchmark datasets. The experimental outcomes exhibit that the proposed architecture is effective in learning audio-visual correlation and is appreciably better than the existing cross-modal retrieval methods.

cs.IR↗

arXiv2021

Lattice partition recovery with dyadic CART

We study piece-wise constant signals corrupted by additive Gaussian noise over a $d$-dimensional lattice. Data of this form naturally arise in a host of applications, and the tasks of signal detection or testing, de-noising and estimation have been studied extensively in the statistical and signal processing literature. In this paper we consider instead the problem of partition recovery, i.e.~of estimating the partition of the lattice induced by the constancy regions of the unknown signal, using the computationally-efficient dyadic classification and regression tree (DCART) methodology proposed by \citep{donoho1997cart}. We prove that, under appropriate regularity conditions on the shape of the partition elements, a DCART-based procedure consistently estimates the underlying partition at a rate of order $σ^2 k^* \log (N)/κ^2$, where $k^*$ is the minimal number of rectangular sub-graphs obtained using recursive dyadic partitions supporting the signal partition, $σ^2$ is the noise variance, $κ$ is the minimal magnitude of the signal difference among contiguous elements of the partition and $N$ is the size of the lattice. Furthermore, under stronger assumptions, our method attains a sharper estimation error of order $σ^2\log(N)/κ^2$, independent of $k^*$, which we show to be minimax rate optimal. Our theoretical guarantees further extend to the partition estimator based on the optimal regression tree estimator (ORT) of \cite{chatterjee2019adaptive} and to the one obtained through an NP-hard exhaustive search method. We corroborate our theoretical findings and the effectiveness of DCART for partition recovery in simulations.

math.ST↗

arXiv2021

Learning Explicit and Implicit Latent Common Spaces for Audio-Visual Cross-Modal Retrieval

Learning common subspace is prevalent way in cross-modal retrieval to solve the problem of data from different modalities having inconsistent distributions and representations that cannot be directly compared. Previous cross-modal retrieval methods focus on projecting the cross-modal data into a common space by learning the correlation between them to bridge the modality gap. However, the rich semantic information in the video and the heterogeneous nature of audio-visual data leads to more serious heterogeneous gaps intuitively, which may lead to the loss of key semantic content of video with single clue by the previous methods when eliminating the modality gap, while the semantics of the categories may undermine the properties of the original features. In this work, we aim to learn effective audio-visual representations to support audio-visual cross-modal retrieval (AVCMR). We propose a novel model that maps audio-visual modalities into two distinct shared latent subspaces: explicit and implicit shared spaces. In particular, the explicit shared space is used to optimize pairwise correlations, where learned representations across modalities capture the commonalities of audio-visual pairs and reduce the modality gap. The implicit shared space is used to preserve the distinctive features between modalities by maintaining the discrimination of audio/video patterns from different semantic categories. Finally, the fusion of the features learned from the two latent subspaces is used for the similarity computation of the AVCMR task. The comprehensive experimental results on two audio-visual datasets demonstrate that our proposed model for using two different latent subspaces for audio-visual cross-modal learning is effective and significantly outperforms the state-of-the-art cross-modal models that learn features from a single subspace.

cs.MM↗

arXiv2021

Adversarially robust change point detection

Change point detection is becoming increasingly popular in many application areas. On one hand, most of the theoretically-justified methods are investigated in an ideal setting without model violations, or merely robust against identical heavy-tailed noise distribution across time and/or against isolate outliers; on the other hand, we are aware that there have been exponentially growing attacks from adversaries, who may pose systematic contamination on data to purposely create spurious change points or disguise true change points. In light of the timely need for a change point detection method that is robust against adversaries, we start with, arguably, the simplest univariate mean change point detection problem. The adversarial attacks are formulated through the Huber $\varepsilon$-contamination framework, which in particular allows the contamination distributions to be different at each time point. In this paper, we demonstrate a phase transition phenomenon in change point detection. This detection boundary is a function of the contamination proportion $\varepsilon$ and is the first time shown in the literature. In addition, we derive the minimax-rate optimal localisation error rate, quantifying the cost of accuracy in terms of the contamination proportion. We propose a computationally feasible method, matching the minimax lower bound under certain conditions, saving for logarithmic factors. Extensive numerical experiments are conducted with comparisons to robust change point detection methods in the existing literature.

stat.ME↗