arXiv subjects

Yongsheng Gao

Publications and source records attributed to Yongsheng Gao.

71 records · Page 4Linked to original sources

arXiv2020

Deep Residual-Dense Lattice Network for Speech Enhancement

Convolutional neural networks (CNNs) with residual links (ResNets) and causal dilated convolutional units have been the network of choice for deep learning approaches to speech enhancement. While residual links improve gradient flow during training, feature diminution of shallow layer outputs can occur due to repetitive summations with deeper layer outputs. One strategy to improve feature re-usage is to fuse both ResNets and densely connected CNNs (DenseNets). DenseNets, however, over-allocate parameters for feature re-usage. Motivated by this, we propose the residual-dense lattice network (RDL-Net), which is a new CNN for speech enhancement that employs both residual and dense aggregations without over-allocating parameters for feature re-usage. This is managed through the topology of the RDL blocks, which limit the number of outputs used for dense aggregations. Our extensive experimental investigation shows that RDL-Nets are able to achieve a higher speech enhancement performance than CNNs that employ residual and/or dense aggregations. RDL-Nets also use substantially fewer parameters and have a lower computational requirement. Furthermore, we demonstrate that RDL-Nets outperform many state-of-the-art deep learning approaches to speech enhancement.

eess.AS↗

arXiv2019

Patchy Image Structure Classification Using Multi-Orientation Region Transform

Exterior contour and interior structure are both vital features for classifying objects. However, most of the existing methods consider exterior contour feature and internal structure feature separately, and thus fail to function when classifying patchy image structures that have similar contours and flexible structures. To address above limitations, this paper proposes a novel Multi-Orientation Region Transform (MORT), which can effectively characterize both contour and structure features simultaneously, for patchy image structure classification. MORT is performed over multiple orientation regions at multiple scales to effectively integrate patchy features, and thus enables a better description of the shape in a coarse-to-fine manner. Moreover, the proposed MORT can be extended to combine with the deep convolutional neural network techniques, for further enhancement of classification accuracy. Very encouraging experimental results on the challenging ultra-fine-grained cultivar recognition task, insect wing recognition task, and large variation butterfly recognition task are obtained, which demonstrate the effectiveness and superiority of the proposed MORT over the state-of-the-art methods in classifying patchy image structures. Our code and three patchy image structure datasets are available at: https://github.com/XiaohanYu-GU/MReT2019.

cs.CV↗

arXiv2019

MobileFAN: Transferring Deep Hidden Representation for Face Alignment

Facial landmark detection is a crucial prerequisite for many face analysis applications. Deep learning-based methods currently dominate the approach of addressing the facial landmark detection. However, such works generally introduce a large number of parameters, resulting in high memory cost. In this paper, we aim for a lightweight as well as effective solution to facial landmark detection. To this end, we propose an effective lightweight model, namely Mobile Face Alignment Network (MobileFAN), using a simple backbone MobileNetV2 as the encoder and three deconvolutional layers as the decoder. The proposed MobileFAN, with only 8% of the model size and lower computational cost, achieves superior or equivalent performance compared with state-of-the-art models. Moreover, by transferring the geometric structural information of a face graph from a large complex model to our proposed MobileFAN through feature-aligned distillation and feature-similarity distillation, the performance of MobileFAN is further improved in effectiveness and efficiency for face alignment. Extensive experiment results on three challenging facial landmark estimation benchmarks including COFW, 300W and WFLW show the superiority of our proposed MobileFAN against state-of-the-art methods.

cs.CV↗

arXiv2019

From Species to Cultivar: Soybean Cultivar Recognition using Multiscale Sliding Chord Matching of Leaf Images

Leaf image recognition techniques have been actively researched for plant species identification. However it remains unclear whether leaf patterns can provide sufficient information for cultivar recognition. This paper reports the first attempt on soybean cultivar recognition from plant leaves which is not only a challenging research problem but also important for soybean cultivar evaluation, selection and production in agriculture. In this paper, we propose a novel multiscale sliding chord matching (MSCM) approach to extract leaf patterns that are distinctive for soybean cultivar identification. A chord is defined to slide along the contour for measuring the synchronised patterns of exterior shape and interior appearance of soybean leaf images. A multiscale sliding chord strategy is developed to extract features in a coarse-to-fine hierarchical order. A joint description that integrates the leaf descriptors from different parts of a soybean plant is proposed for further enhancing the discriminative power of cultivar description. We built a cultivar leaf image database, SoyCultivar, consisting of 1200 sample leaf images from 200 soybean cultivars for performance evaluation. Encouraging experimental results of the proposed method in comparison to the state-of-the-art leaf species recognition methods demonstrate the availability of cultivar information in soybean leaves and effectiveness of the proposed MSCM for soybean cultivar identification, which may advance the research in leaf recognition from species to cultivar.

cs.CV↗

arXiv2018

Robust Facial Landmark Localization Based on Texture and Pose Correlated Initialization

Robust facial landmark localization remains a challenging task when faces are partially occluded. Recently, the cascaded pose regression has attracted increasing attentions, due to it's superior performance in facial landmark localization and occlusion detection. However, such an approach is sensitive to initialization, where an improper initialization can severly degrade the performance. In this paper, we propose a Robust Initialization for Cascaded Pose Regression (RICPR) by providing texture and pose correlated initial shapes for the testing face. By examining the correlation of local binary patterns histograms between the testing face and the training faces, the shapes of the training faces that are most correlated with the testing face are selected as the texture correlated initialization. To make the initialization more robust to various poses, we estimate the rough pose of the testing face according to five fiducial landmarks located by multitask cascaded convolutional networks. Then the pose correlated initial shapes are constructed by the mean face's shape and the rough testing face pose. Finally, the texture correlated and the pose correlated initial shapes are joined together as the robust initialization. We evaluate RICPR on the challenging dataset of COFW. The experimental results demonstrate that the proposed scheme achieves better performances than the state-of-the-art methods in facial landmark localization and occlusion detection.

cs.CV↗

arXiv2017

Conditional Random Field and Deep Feature Learning for Hyperspectral Image Segmentation

Image segmentation is considered to be one of the critical tasks in hyperspectral remote sensing image processing. Recently, convolutional neural network (CNN) has established itself as a powerful model in segmentation and classification by demonstrating excellent performances. The use of a graphical model such as a conditional random field (CRF) contributes further in capturing contextual information and thus improving the segmentation performance. In this paper, we propose a method to segment hyperspectral images by considering both spectral and spatial information via a combined framework consisting of CNN and CRF. We use multiple spectral cubes to learn deep features using CNN, and then formulate deep CRF with CNN-based unary and pairwise potential functions to effectively extract the semantic correlations between patches consisting of three-dimensional data cubes. Effective piecewise training is applied in order to avoid the computationally expensive iterative CRF inference. Furthermore, we introduce a deep deconvolution network that improves the segmentation masks. We also introduce a new dataset and experimented our proposed method on it along with several widely adopted benchmark datasets to evaluate the effectiveness of our method. By comparing our results with those from several state-of-the-art models, we show the promising potential of our method.

cs.CV↗

arXiv2016

On the Sampling Strategy for Evaluation of Spectral-spatial Methods in Hyperspectral Image Classification

Spectral-spatial processing has been increasingly explored in remote sensing hyperspectral image classification. While extensive studies have focused on developing methods to improve the classification accuracy, experimental setting and design for method evaluation have drawn little attention. In the scope of supervised classification, we find that traditional experimental designs for spectral processing are often improperly used in the spectral-spatial processing context, leading to unfair or biased performance evaluation. This is especially the case when training and testing samples are randomly drawn from the same image - a practice that has been commonly adopted in the experiments. Under such setting, the dependence caused by overlap between the training and testing samples may be artificially enhanced by some spatial information processing methods such as spatial filtering and morphological operation. Such interaction between training and testing sets has violated data independence assumption that is abided by supervised learning theory and performance evaluation mechanism. Therefore, the widely adopted pixel-based random sampling strategy is not always suitable to evaluate spectral-spatial classification algorithms because it is difficult to determine whether the improvement of classification accuracy is caused by incorporating spatial information into classifier or by increasing the overlap between training and testing samples. To partially solve this problem, we propose a novel controlled random sampling strategy for spectral-spatial methods. It can greatly reduce the overlap between training and testing samples and provides more objective and accurate evaluation.

cs.CV↗

arXiv2011

Face Recognition using Optimal Representation Ensemble

Recently, the face recognizers based on linear representations have been shown to deliver state-of-the-art performance. In real-world applications, however, face images usually suffer from expressions, disguises and random occlusions. The problematic facial parts undermine the validity of the linear-subspace assumption and thus the recognition performance deteriorates significantly. In this work, we address the problem in a learning-inference-mixed fashion. By observing that the linear-subspace assumption is more reliable on certain face patches rather than on the holistic face, some Bayesian Patch Representations (BPRs) are randomly generated and interpreted according to the Bayes' theory. We then train an ensemble model over the patch-representations by minimizing the empirical risk w.r.t the "leave-one-out margins". The obtained model is termed Optimal Representation Ensemble (ORE), since it guarantees the optimality from the perspective of Empirical Risk Minimization. To handle the unknown patterns in test faces, a robust version of BPR is proposed by taking the non-face category into consideration. Equipped with the Robust-BPRs, the inference ability of ORE is increased dramatically and several record-breaking accuracies (99.9% on Yale-B and 99.5% on AR) and desirable efficiencies (below 20 ms per face in Matlab) are achieved. It also overwhelms other modular heuristics on the faces with random occlusions, extreme expressions and disguises. Furthermore, to accommodate immense BPRs sets, a boosting-like algorithm is also derived. The boosted model, a.k.a Boosted-ORE, obtains similar performance to its prototype. Besides the empirical superiorities, two desirable features of the proposed methods, namely, the training-determined model-selection and the data-weight-free boosting procedure, are also theoretically verified.

cs.CV↗

arXiv2005

D+ to mu+nu and fD+ from 281 pb-1 at Psi(3770) from CLEO-c

We report improved measurements of branching fraction and decay constant fD+ in D+ to mu+nu using 281 pb-1 of data taken on the Psi(3770) resonance with the CLEO-c detector. We extract a relatively precise value for the decay constant of the D+ meson by measuring Br(D+ to mu+nu) = (4.40+-0.66+0.09-0.12)x10^-4 and find fD+ = (222.6+-16.7+2.8-3.4) MeV. We also set 90% confidence upper limit on Br(D+ to e+nu) < 2.4x10^-5 which limits contributions from non-Standard Model physics.

hep-ex↗

arXiv2005

Hadronic branching fractions and DDbar cross-sections at Psi(3770) from CLEO-c

We present some recent results in hadronic decays and cross-section measurements at Psi(3770) from CLEO collaboration. They include measurement of absolute hadronic branching fractions of D mesons and e+e- to DDbar cross-sections, inclusive production of eta, eta', phi in D decays, branching fractions of D+ to K0_{S,L} pi+ and eta pi+, Psi(3770) non-DDbar decays, and timelike electromagnetic form factors of pion, kaon and proton. These results are based on 55.8 pb-1 and 281 pb-1 at Psi(3770), and other data samples collected by the CLEO-c detector at the Cornell Electron Storage Ring (CESR).

hep-ex↗

arXiv2005

Significance Calculation and a New Analysis Method in Searching for New Physics at the LHC

The LHC experiments have great potential in discovering many possible new particles up to the TeV scale. The significance calculation of an observation of a physics signal with known location and shape is no longer valid when either the location or the shape of the signal is unknown. We find the current LHC significance calculation of new physics is over-estimated and strongly depends on the specifics of the method and the situation it applies to. We describe general procedures for significance calculation and comparing different search schemes. A new method uses maximum likelihood fits with floating parameters and scans the parameter space for the best fit to the entire sample. We find that the new method is significantly more sensitive than current method and is insensitive to the exact location of the new physics signal we search.

physics.ins-det↗

arXiv2004

Semileptonic D Decays from CLEO and BELLE

Recent semileptonic D meson decay results are summarized, including the improved measurements of absolute branching fractions for exclusive D0 semileptonic decays into $K^{-}e^{+}ν$, $π^{-}e^{+}ν$ and $K^{*-}e^{+}ν$, and the first observation and absolute branching fraction measurement of $D^{0} \to ρ^{-}e^{+}ν$ with the first CLEO-c data sample.

hep-ex↗

arXiv2003

Recent Charm from CLEO

We present some recent results in rare charm decays from CLEO Collaboration. The data used were collected by the CLEO II and III detectors at the Cornell Electron Storage Ring (CESR). A brief future outlook for the CESR-c/CLEO-c program is also presented.

hep-ex↗

arXiv2003

New Analysis Strategy to Search for New Particles at LHC

The ATLAS and CMS experiments at LHC have great physics potential in discovering many possible new particles, from Standard Model (SM) Higgs boson to supersymmetric (SUSY) and other beyond the SM new particles over a very large mass range around the TeV scale. We first review the current analysis strategy in searching for new particles at LHC and its vulnerability to statistical fluctuations. We then discuss an alternative new analysis strategy in order to avoid this vulnerability. We use maximum likelihood method as an example and discuss the new challenges in using maximum likelihood method as such a new analysis strategy to search for new particles at LHC.

hep-ex↗

arXiv2001

Recent results from CLEO collaboration

Recent CLEO results on beauty and charm meson decays presented at the International Conference on Flavor Physics (ICFP2001) are discussed. The results include exclusive rare B decays (B to PP, PV, VV, \phiK^(*), l^+l^-K^(*)), inclusive b to s γ, and CP violation measurements in beauty and charm mesons. Preliminary results on rare B decays using CLEO III data are also included.

hep-ex↗

arXiv2000

Results on B to Charmonia Decays from CLEO

We review some recent results on B to charmonia decays from CLEO based on 9.7 BBbar pairs collected with the CLEO detector. These include measurements of B^{0} to JΨK^0_s, χ_{c1} K^0_s and J/Ψπ^0 branching fractions, search for direct CP violation in B^{\pm} to J/ΨK^\pm and Ψ(2S) K^\pm, observation of B \to η_{c} K, study of χ_{c1}, χ_{c2} production and measurement of the relative branching fraction of Υ(4S) to charged and neutral B meson pairs.

hep-ex↗

arXiv1999

Charmless Hadronic B Decays at CLEO

The CLEO collaboration has studied two-body charmless hadronic decays of $B$ mesons into final states containing two pseudo-scalar mesons, or a pseudo-scalar and a vector meson. We summarize and discuss results presented during the winter/spring 1999 conference season, and provide a brief outlook towards future attractions to come. In particular, CLEO presented preliminary results on the decays $B^\pm \to π^\pmρ^0$ ($Br(B^\pm \to π^\pmρ^0) = (1.5 \pm 0.5 \pm 0.4)\times 10^{-5}$), $B\to π^\pmρ^\mp$ ($Br(B\to π^\pmρ^\mp)=(3.5^{+1.1}_{-1.0}\pm 0.5)\times 10^{-5}$), $B\to π^\pm K^{\star\mp}$ ($Br(B\to π^\pm K^{\star\mp}) = (2.2^{+0.8+0.4}_{-0.6-0.5})\times 10^{-5}$), and $B^\pm \to K^\pm π^0$ ($Br(B^\pm \to K^\pm π^0) = (1.5 \pm 0.4 \pm 0.3) \times 10^{-5}$) at DPF99, APS99, APS99, and ICHEP98 respectively. None of these decays had been observed previously. The first two of these constitute the first observation of hadronic $b\to u$ transitions. In addition, CLEO presented preliminary updates on a large number of previously published branching fractions and upper limits.

hep-ex↗