arXiv subjects

Xiaoyu Wang

Publications and source records attributed to Xiaoyu Wang.

At least 199 records · Page 11Linked to original sources

arXiv2022

Multiplex-detection Based Multiple Instance Learning Network for Whole Slide Image Classification

Multiple instance learning (MIL) is a powerful approach to classify whole slide images (WSIs) for diagnostic pathology. A fundamental challenge of MIL on WSI classification is to discover the \textit{critical instances} that trigger the bag label. However, previous methods are primarily designed under the independent and identical distribution hypothesis (\textit{i.i.d}), ignoring either the correlations between instances or heterogeneity of tumours. In this paper, we propose a novel multiplex-detection-based multiple instance learning (MDMIL) to tackle the issues above. Specifically, MDMIL is constructed by the internal query generation module (IQGM) and the multiplex detection module (MDM) and assisted by the memory-based contrastive loss during training. Firstly, IQGM gives the probability of instances and generates the internal query (IQ) for the subsequent MDM by aggregating highly reliable features after the distribution analysis. Secondly, the multiplex-detection cross-attention (MDCA) and multi-head self-attention (MHSA) in MDM cooperate to generate the final representations for the WSI. In this process, the IQ and trainable variational query (VQ) successfully build up the connections between instances and significantly improve the model's robustness toward heterogeneous tumours. At last, to further enforce constraints in the feature space and stabilize the training process, we adopt a memory-based contrastive loss, which is practicable for WSI classification even with a single sample as input in each iteration. We conduct experiments on three computational pathology datasets, e.g., CAMELYON16, TCGA-NSCLC, and TCGA-RCC datasets. The superior accuracy and AUC demonstrate the superiority of our proposed MDMIL over other state-of-the-art methods.

cs.CV↗

arXiv2022

Lifted Bregman Training of Neural Networks

We introduce a novel mathematical formulation for the training of feed-forward neural networks with (potentially non-smooth) proximal maps as activation functions. This formulation is based on Bregman distances and a key advantage is that its partial derivatives with respect to the network's parameters do not require the computation of derivatives of the network's activation functions. Instead of estimating the parameters with a combination of first-order optimisation method and back-propagation (as is the state-of-the-art), we propose the use of non-smooth first-order optimisation methods that exploit the specific structure of the novel formulation. We present several numerical results that demonstrate that these training approaches can be equally well or even better suited for the training of neural network-based classifiers and (denoising) autoencoders with sparse coding compared to more conventional training frameworks.

math.OC↗

arXiv2022

ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer

Recently, vision transformers started to show impressive results which outperform large convolution based models significantly. However, in the area of small models for mobile or resource constrained devices, ConvNet still has its own advantages in both performance and model complexity. We propose ParC-Net, a pure ConvNet based backbone model that further strengthens these advantages by fusing the merits of vision transformers into ConvNets. Specifically, we propose position aware circular convolution (ParC), a light-weight convolution op which boasts a global receptive field while producing location sensitive features as in local convolutions. We combine the ParCs and squeeze-exictation ops to form a meta-former like model block, which further has the attention mechanism like transformers. The aforementioned block can be used in plug-and-play manner to replace relevant blocks in ConvNets or transformers. Experiment results show that the proposed ParC-Net achieves better performance than popular light-weight ConvNets and vision transformer based models in common vision tasks and datasets, while having fewer parameters and faster inference speed. For classification on ImageNet-1k, ParC-Net achieves 78.6% top-1 accuracy with about 5.0 million parameters, saving 11% parameters and 13% computational cost but gaining 0.2% higher accuracy and 23% faster inference speed (on ARM based Rockchip RK3288) compared with MobileViT, and uses only 0.5 times parameters but gaining 2.7% accuracy compared with DeIT. On MS-COCO object detection and PASCAL VOC segmentation tasks, ParC-Net also shows better performance. Source code is available at https://github.com/hkzhang91/ParC-Net

cs.CV↗

arXiv2022

Improving Adversarial Robustness via Mutual Information Estimation

Deep neural networks (DNNs) are found to be vulnerable to adversarial noise. They are typically misled by adversarial samples to make wrong predictions. To alleviate this negative effect, in this paper, we investigate the dependence between outputs of the target model and input adversarial samples from the perspective of information theory, and propose an adversarial defense method. Specifically, we first measure the dependence by estimating the mutual information (MI) between outputs and the natural patterns of inputs (called natural MI) and MI between outputs and the adversarial patterns of inputs (called adversarial MI), respectively. We find that adversarial samples usually have larger adversarial MI and smaller natural MI compared with those w.r.t. natural samples. Motivated by this observation, we propose to enhance the adversarial robustness by maximizing the natural MI and minimizing the adversarial MI during the training process. In this way, the target model is expected to pay more attention to the natural pattern that contains objective semantics. Empirical evaluations demonstrate that our method could effectively improve the adversarial accuracy against multiple attacks.

cs.LG↗

arXiv2022

Multi-Modal Multi-Correlation Learning for Audio-Visual Speech Separation

In this paper we propose a multi-modal multi-correlation learning framework targeting at the task of audio-visual speech separation. Although previous efforts have been extensively put on combining audio and visual modalities, most of them solely adopt a straightforward concatenation of audio and visual features. To exploit the real useful information behind these two modalities, we define two key correlations which are: (1) identity correlation (between timbre and facial attributes); (2) phonetic correlation (between phoneme and lip motion). These two correlations together comprise the complete information, which shows a certain superiority in separating target speaker's voice especially in some hard cases, such as the same gender or similar content. For implementation, contrastive learning or adversarial training approach is applied to maximize these two correlations. Both of them work well, while adversarial training shows its advantage by avoiding some limitations of contrastive learning. Compared with previous research, our solution demonstrates clear improvement on experimental metrics without additional complexity. Further analysis reveals the validity of the proposed architecture and its good potential for future extension.

cs.SD↗

arXiv2022

On Uniform Boundedness Properties of SGD and its Momentum Variants

A theoretical, and potentially also practical, problem with stochastic gradient descent is that trajectories may escape to infinity. In this note, we investigate uniform boundedness properties of iterates and function values along the trajectories of the stochastic gradient descent algorithm and its important momentum variant. Under smoothness and $R$-dissipativity of the loss function, we show that broad families of step-sizes, including the widely used step-decay and cosine with (or without) restart step-sizes, result in uniformly bounded iterates and function values. Several important applications that satisfy these assumptions, including phase retrieval problems, Gaussian mixture models, and some neural network classifiers, are discussed in detail. We further extend the uniform boundedness of SGD and its momentum variant under the generalized dissipativity for the functions whose tails grow slower than quadratic functions. This includes some interesting applications, for example, Bayesian logistic regression and logistic regression with $\ell_1$ regularization.

cs.LG↗

arXiv2022

Transverse momentum weighted Sivers asymmetries in SIDIS and Drell-Yan processes at COMPASS

We investigate the transverse momentum weighted Sivers asymmetries in the processes with transversely polarized proton target, including the $\frac{P_{hT}}{zM_p}\sin (ϕ_h-ϕ_S)$ weighted asymmetry in charged hadron production in semi-inclusive deeply inelastic scattering (SIDIS) and the $\frac{q_T}{M_p}\sin (ϕ_S)$ weighted asymmetry in $π^- p$ Drell-Yan process. Due to the integration over the transverse momentum, the weighted asymmetries can be expressed as the product of the transverse-moments of the transverse momentum dependent (TMD) parton distribution functions (PDFs) and fragmentation functions (FFs). Using the parametrization for the Sivers function of the proton, the unpolarized PDFs of proton and pion, and the unpolarized FF of charged hadron, we present the numerical calculation for weighted Sivers asymmetries in SIDIS and Drell-Yan processes at the kinematics of COMPASS, and compare them with experimental data. We find that our prediction on the weighted Sivers asymmetry in SIDIS process is in agreement with the recent COMPASS measurement. Due to the relatively large uncertainties of the preliminary data from COMPASS Drell-Yan program, high precision experimental data are needed to test the sign change property of the Sivers function between SIDIS and Drell-Yan processes and to constrain the sea quark Sivers function.

hep-ph↗

arXiv2022

Topological Electride Phase of Sodium at High Pressures and Temperatures

Ab initio evolutionary structure searches coupled with quasiharmonic calculations predict that the insulating Na hP4 phase transitions to a novel P63/m phase between 200 GPa at 150 K, and 350 GPa at 1900 K. P63/m Na is a topological semimetal with a Dirac nodal surface that is protected by a non-symmorphic symmetry, S2z . It is characterized by localized non-nuclear charge within 1D honeycomb channels and 0D cages rendering it an electride. These results highlight the complexity of warm dense sodiums electronic structure and free energy landscape that emerges at conditions where ionic cores overlap.

cond-mat.mtrl-sci↗

arXiv2022

The Microscopic Diamond Anvil Cell: Stabilization of Superhard, Superconducting Carbon Allotropes at Ambient Pressure

A metallic covalently bonded carbon allotrope is predicted via first principles calculations. It is composed of an $sp^3$ carbon framework that acts as a diamond anvil cell by constraining the distance between parallel cis-polyacetylene chains. The distance between these $sp^2$ carbon atoms renders the phase metallic, and yields two well-nested nearly parallel bands that span the Fermi level. Calculations show that this phase is a conventional superconductor, with the motions of the $sp^2$ carbons being key contributors to the electron phonon coupling. The $sp^3$ carbon atoms impart superior mechanical properties, with a predicted Vickers hardness of 48~GPa. This phase, metastable at ambient conditions, could be made via cold compression of graphite to 40~GPa. A family of multifunctional materials with tunable superconducting and mechanical properties could be derived from this phase by varying the $sp^2$ versus $sp^3$ carbon content and by doping.

cond-mat.mtrl-sci↗

arXiv2022

Connecting Compression Spaces with Transformer for Approximate Nearest Neighbor Search

We propose a generic feature compression method for Approximate Nearest Neighbor Search (ANNS) problems, which speeds up existing ANNS methods in a plug-and-play manner. Specifically, based on transformer, we propose a new network structure to compress the feature into a low dimensional space, and an inhomogeneous neighborhood relationship preserving (INRP) loss that aims to maintain high search accuracy. Specifically, we use multiple compression projections to cast the feature into many low dimensional spaces, and then use transformer to globally optimize these projections such that the features are well compressed following the guidance from our loss function. The loss function is designed to assign high weights on point pairs that are close in original feature space, and keep their distances in projected space. Keeping these distances helps maintain the eventual top-k retrieval accuracy, and down weighting others creates room for feature compression. In experiments, we run our compression method on public datasets, and use the compressed features in graph based, product quantization and scalar quantization based ANNS solutions. Experimental results show that our compression method can significantly improve the efficiency of these methods while preserves or even improves search accuracy, suggesting its broad potential impact on real world applications.

cs.IR↗

arXiv2022

Implementation of an Automated Learning System for Non-experts

Automated machine learning systems for non-experts could be critical for industries to adopt artificial intelligence to their own applications. This paper detailed the engineering system implementation of an automated machine learning system called YMIR, which completely relies on graphical interface to interact with users. After importing training/validation data into the system, a user without AI knowledge can label the data, train models, perform data mining and evaluation by simply clicking buttons. The paper described: 1) Open implementation of model training and inference through docker containers. 2) Implementation of task and resource management. 3) Integration of Labeling software. 4) Implementation of HCI (Human Computer Interaction) with a rebuilt collaborative development paradigm. We also provide subsequent case study on training models with the system. We hope this paper can facilitate the prosperity of our automated machine learning community from industry application perspective. The code of the system has already been released to GitHub (https://github.com/industryessentials/ymir).

cs.HC↗

arXiv2022

Towards Semi-Supervised Deep Facial Expression Recognition with An Adaptive Confidence Margin

Only parts of unlabeled data are selected to train models for most semi-supervised learning methods, whose confidence scores are usually higher than the pre-defined threshold (i.e., the confidence margin). We argue that the recognition performance should be further improved by making full use of all unlabeled data. In this paper, we learn an Adaptive Confidence Margin (Ada-CM) to fully leverage all unlabeled data for semi-supervised deep facial expression recognition. All unlabeled samples are partitioned into two subsets by comparing their confidence scores with the adaptively learned confidence margin at each training epoch: (1) subset I including samples whose confidence scores are no lower than the margin; (2) subset II including samples whose confidence scores are lower than the margin. For samples in subset I, we constrain their predictions to match pseudo labels. Meanwhile, samples in subset II participate in the feature-level contrastive objective to learn effective facial expression features. We extensively evaluate Ada-CM on four challenging datasets, showing that our method achieves state-of-the-art performance, especially surpassing fully-supervised baselines in a semi-supervised manner. Ablation study further proves the effectiveness of our method. The source code is available at https://github.com/hangyu94/Ada-CM.

cs.CV↗

arXiv2022

FaceMap: Towards Unsupervised Face Clustering via Map Equation

Face clustering is an essential task in computer vision due to the explosion of related applications such as augmented reality or photo album management. The main challenge of this task lies in the imperfectness of similarities among image feature representations. Given an existing feature extraction model, it is still an unresolved problem that how can the inherent characteristics of similarities of unlabelled images be leveraged to improve the clustering performance. Motivated by answering the question, we develop an effective unsupervised method, named as FaceMap, by formulating face clustering as a process of non-overlapping community detection, and minimizing the entropy of information flows on a network of images. The entropy is denoted by the map equation and its minimum represents the least description of paths among images in expectation. Inspired by observations on the ranked transition probabilities in the affinity graph constructed from facial images, we develop an outlier detection strategy to adaptively adjust transition probabilities among images. Experiments with ablation studies demonstrate that FaceMap significantly outperforms existing methods and achieves new state-of-the-arts on three popular large-scale datasets for face clustering, e.g., an absolute improvement of more than $10\%$ and $4\%$ comparing with prior unsupervised and supervised methods respectively in terms of average of Pairwise F-score. Our code is publicly available on github.

cs.CV↗

arXiv2022

Semi-parametric Makeup Transfer via Semantic-aware Correspondence

The large discrepancy between the source non-makeup image and the reference makeup image is one of the key challenges in makeup transfer. Conventional approaches for makeup transfer either learn disentangled representation or perform pixel-wise correspondence in a parametric way between two images. We argue that non-parametric techniques have a high potential for addressing the pose, expression, and occlusion discrepancies. To this end, this paper proposes a \textbf{S}emi-\textbf{p}arametric \textbf{M}akeup \textbf{T}ransfer (SpMT) method, which combines the reciprocal strengths of non-parametric and parametric mechanisms. The non-parametric component is a novel \textbf{S}emantic-\textbf{a}ware \textbf{C}orrespondence (SaC) module that explicitly reconstructs content representation with makeup representation under the strong constraint of component semantics. The reconstructed representation is desired to preserve the spatial and identity information of the source image while "wearing" the makeup of the reference image. The output image is synthesized via a parametric decoder that draws on the reconstructed representation. Extensive experiments demonstrate the superiority of our method in terms of visual quality, robustness, and flexibility. Code and pre-trained model are available at \url{https://github.com/AnonymScholar/SpMT.

cs.CV↗

arXiv2022

Zeroth-Order Randomized Subspace Newton Methods

Zeroth-order methods have become important tools for solving problems where we have access only to function evaluations. However, the zeroth-order methods only using gradient approximations are $n$ times slower than classical first-order methods for solving n-dimensional problems. To accelerate the convergence rate, this paper proposes the zeroth order randomized subspace Newton (ZO-RSN) method, which estimates projections of the gradient and Hessian by random sketching and finite differences. This allows us to compute the Newton step in a lower dimensional subspace, with small computational costs. We prove that ZO-RSN can attain lower iteration complexity than existing zeroth order methods for strongly convex problems. Our numerical experiments show that ZO-RSN can perform black-box attacks under a more restrictive limit on the number of function queries than the state-of-the-art Hessian-aware zeroth-order method.

math.OC↗

arXiv2022

Narrow bands in magnetic field and strong-coupling Hofstadter spectra

We develop a new, efficient, and general method to determine the Hofstadter spectrum of isolated narrow bands. The method works for topological as well as for trivial narrow bands by projecting the zero $\mathbf{B}$-field hybrid Wannier states -- which are localized in one direction and Bloch extended in another direction -- onto a representation of the magnetic translation group in the Landau gauge. We then apply this method to find, for the first time, the Hofstadter spectrum for the exact single particle charged excitations in the strong coupling limit of the magic angle twisted bilayer graphene at the charge neutrality point and at $|ν|=2$ down to low magnetic fields when the flux through the moiré unit cell is only $\sim 1/25$ of the electronic flux quantum i.e. $\sim 1$T at the first magic angle. The resulting spectra provide a means to investigate Landau quantization of the quasiparticles even if their dispersion is interaction induced.

cond-mat.str-el↗

arXiv2021

Leading and higher twist transverse momentum dependent parton distribution functions in the spectator model

Transverse momentum dependent parton distribution functions, also abbreviated as TMDs, offer a three-dimensional picture of hadrons by taking the intrinsic transverse momentum of the parton into consideration. Hence, they are very important for us to understand the structure of hadrons. In this article, we calculate and summarize all TMDs of quark through the spectator model, from twist-2 to twist-4. Especially, we give complete results of TMDs at twist-4. We adopt a general analytical framework to calculate TMDs, with both scalar and axial-vector spectators being considered. All TMDs are calculated analytically in the light-cone coordinate, and single gluon rescattering is considered to generate T-odd TMDs. T-even TMDs are also calculated to this level, maybe for the first time. Different from the traditional point of view, the twist-4 TMDs can contribute to some physical observables like azimuthal asymmetries. An approximate formula of the Sivers asymmetry, including twist-4 TMDs, is given.

hep-ph↗

arXiv2021

YMIR: A Rapid Data-centric Development Platform for Vision Applications

This paper introduces an open source platform to support the rapid development of computer vision applications at scale. The platform puts the efficient data development at the center of the machine learning development process, integrates active learning methods, data and model version control, and uses concepts such as projects to enable fast iterations of multiple task specific datasets in parallel. This platform abstracts the development process into core states and operations, and integrates third party tools via open APIs as implementations of the operations. This open design reduces the development cost and adoption cost for ML teams with existing tools. At the same time, the platform supports recording project development histories, through which successful projects can be shared to further boost model production efficiency on similar tasks. The platform is open source and is already used internally to meet the increasing demand for different real world computer vision applications.

cs.AI↗