arXiv subjects

Yu Tian

Publications and source records attributed to Yu Tian.

At least 289 records · Page 16Linked to original sources

arXiv2022

The topological RN-AdS black holes cannot be overcharged by the new version of gedanken experiment

In this paper, we test the weak cosmic censorship conjecture (WCCC) for n >= 4 dimensional nearly extremal RN-AdS black holes with non-trivial topologies, namely plane and hyperbola, using the new version of gedanken experiment proposed by Sorce and Wald. Provided that the non-electromagnetic part of the stress tensor of matter fields satisfies the null energy condition and the linear stability condition holds, we find that the black holes cannot be overcharged under the second-order perturbation approximation, which includes the self-force and finite-size effects. As a result, we conclude that the violation of Hubeny type never occurs and the WCCC holds for the topological RN-AdS black hole.

gr-qc↗

arXiv2022

Thermodynamic equilibrium condition and the first law of thermodynamics for charged perfect fluids in electromagnetic and gravitational fields

We provide a proof of the necessary and sufficient condition on the profile of the temperature, chemical potential, and angular velocity for a charged perfect fluid in dynamic equilibrium to be in thermodynamic equilibrium not only in fixed but also in dynamical electromagnetic and gravitational fields. In passing, we also present the corresponding expression for the first law of thermodynamics for such a charged star.

gr-qc↗

arXiv2022

Generalized Visual Quality Assessment of GAN-Generated Face Images

Recent years have witnessed the dramatically increased interest in face generation with generative adversarial networks (GANs). A number of successful GAN algorithms have been developed to produce vivid face images towards different application scenarios. However, little work has been dedicated to automatic quality assessment of such GAN-generated face images (GFIs), even less have been devoted to generalized and robust quality assessment of GFIs generated with unseen GAN model. Herein, we make the first attempt to study the subjective and objective quality towards generalized quality assessment of GFIs. More specifically, we establish a large-scale database consisting of GFIs from four GAN algorithms, the pseudo labels from image quality assessment (IQA) measures, as well as the human opinion scores via subjective testing. Subsequently, we develop a quality assessment model that is able to deliver accurate quality predictions for GFIs from both available and unseen GAN algorithms based on meta-learning. In particular, to learn shared knowledge from GFIs pairs that are born of limited GAN algorithms, we develop the convolutional block attention (CBA) and facial attributes-based analysis (ABA) modules, ensuring that the learned knowledge tends to be consistent with human visual perception. Extensive experiments exhibit that the proposed model achieves better performance compared with the state-of-the-art IQA models, and is capable of retaining the effectiveness when evaluating GFIs from the unseen GAN algorithms.

cs.CV↗

arXiv2022

Logarithmic correction to black hole entropy from the nonlocality of quantum gravity

It has been known for many years that the leading correction to the black hole entropy is a logarithmic term, which is universal and closely related to conformal anomaly. A fully consistent analysis of this issue has to take quantum backreactions to the black hole geometry into account. However, it was always unclear how to naturally derive the modified black hole metric especially from an effective action, because the problem refers to the elusive non-locality of quantum gravity. In this paper, we show that this problem can be resolved within an effective field theory (EFT) framework of quantum gravity. Our work suggests that the EFT approach provides a powerful and self-consistent tool for studying the quantum gravitational corrections to black hole geometries and thermodynamics.

gr-qc↗

arXiv2021

Dual Projection Generative Adversarial Networks for Conditional Image Generation

Conditional Generative Adversarial Networks (cGANs) extend the standard unconditional GAN framework to learning joint data-label distributions from samples, and have been established as powerful generative models capable of generating high-fidelity imagery. A challenge of training such a model lies in properly infusing class information into its generator and discriminator. For the discriminator, class conditioning can be achieved by either (1) directly incorporating labels as input or (2) involving labels in an auxiliary classification loss. In this paper, we show that the former directly aligns the class-conditioned fake-and-real data distributions $P(\text{image}|\text{class})$ ({\em data matching}), while the latter aligns data-conditioned class distributions $P(\text{class}|\text{image})$ ({\em label matching}). Although class separability does not directly translate to sample quality and becomes a burden if classification itself is intrinsically difficult, the discriminator cannot provide useful guidance for the generator if features of distinct classes are mapped to the same point and thus become inseparable. Motivated by this intuition, we propose a Dual Projection GAN (P2GAN) model that learns to balance between {\em data matching} and {\em label matching}. We then propose an improved cGAN model with Auxiliary Classification that directly aligns the fake and real conditionals $P(\text{class}|\text{image})$ by minimizing their $f$-divergence. Experiments on a synthetic Mixture of Gaussian (MoG) dataset and a variety of real-world datasets including CIFAR100, ImageNet, and VGGFace2 demonstrate the efficacy of our proposed models.

cs.CV↗

arXiv2021

Holographic Abrikosov lattice: vortex matter from black hole

The AdS/CFT correspondence provides a unique way to study the vortex matter phases in superconductors. We solved the nonlinear equations of motion for the Abelain-Higgs theory living on the AdS$_4$ black hole boundary that is dual to a two dimensional strongly coupled type II superconductor at temperature $T$ with a perpendicular external uniform magnetic field $B_0$. We found the associated two critical magnetic fields, $B_{c1}(T)$ and $B_{c2}(T)$. For $B_0 < B_{c1}(T)$ the magnetic field will be expelled out by the superconductor resembling the Meissner effect and the superconductivity will be destroyed when $B_0 > B_{c2}(T)$. The Abrikosov lattice appears in the range $B_{c1}(T) < B_0 < B_{c2}(T)$ including, due to the finite size and boundary effect, several kinds of configurations such as hexagonal, square and slightly irregular square lattices, when the magnetic field is increased. The upper and lower critical fields behave as inverse squares of coherence length and magnetic penetration depth respectively which matches the well known consensus.

hep-th↗

arXiv2021

Instability of Holographic Superfuids in Optical Lattice

The instability of superfluids in optical lattice has been investigated using the holographic model. The static and steady flow solutions are numerically obtained from the static equations of motion and the solutions are described as Bloch waves with different Bloch wave vector $k$. Based on these Bloch waves, the instability is investigated at two levels. At the linear perturbation level, we show that there is a critical $k_{c}$ above which the superflow is unstable. At the fully nonlinear level, the intermediate state and final state of unstable superflow are identified through numerical simulation of the full equations of motion. The results show that during the time evolution, the unstable superflow will undergo a chaotic state, where solitons will appear and disappear. The system will settle down to a stable state with $k<k_{c}$ eventually, with a smaller current and a larger condensate.

hep-th↗

arXiv2021

Self-supervised Mean Teacher for Semi-supervised Chest X-ray Classification

The training of deep learning models generally requires a large amount of annotated data for effective convergence and generalisation. However, obtaining high-quality annotations is a laboursome and expensive process due to the need of expert radiologists for the labelling task. The study of semi-supervised learning in medical image analysis is then of crucial importance given that it is much less expensive to obtain unlabelled images than to acquire images labelled by expert radiologists. Essentially, semi-supervised methods leverage large sets of unlabelled data to enable better training convergence and generalisation than using only the small set of labelled images. In this paper, we propose Self-supervised Mean Teacher for Semi-supervised (S$^2$MTS$^2$) learning that combines self-supervised mean-teacher pre-training with semi-supervised fine-tuning. The main innovation of S$^2$MTS$^2$ is the self-supervised mean-teacher pre-training based on the joint contrastive learning, which uses an infinite number of pairs of positive query and key features to improve the mean-teacher representation. The model is then fine-tuned using the exponential moving average teacher framework trained with semi-supervised learning. We validate S$^2$MTS$^2$ on the multi-label classification problems from Chest X-ray14 and CheXpert, and the multi-class classification from ISIC2018, where we show that it outperforms the previous SOTA semi-supervised learning methods by a large margin.

cs.CV↗

arXiv2021

AE-StyleGAN: Improved Training of Style-Based Auto-Encoders

StyleGANs have shown impressive results on data generation and manipulation in recent years, thanks to its disentangled style latent space. A lot of efforts have been made in inverting a pretrained generator, where an encoder is trained ad hoc after the generator is trained in a two-stage fashion. In this paper, we focus on style-based generators asking a scientific question: Does forcing such a generator to reconstruct real data lead to more disentangled latent space and make the inversion process from image to latent space easy? We describe a new methodology to train a style-based autoencoder where the encoder and generator are optimized end-to-end. We show that our proposed model consistently outperforms baselines in terms of image inversion and generation quality. Supplementary, code, and pretrained models are available on the project website.

cs.CV↗

arXiv2021

Vision-Aided Beam Tracking: Explore the Proper Use of Camera Images with Deep Learning

We investigate the problem of wireless beam tracking on mmWave bands with the assistance of camera images. In particular, based on the user's beam indices used and camera images taken in the trajectory, we predict the optimal beam indices in the next few time spots. To resolve this problem, we first reformulate the "ViWi" dataset in [1] to get rid of the image repetition problem. Then we develop a deep learning approach and investigate various model components to achieve the best performance. Finally, we explore whether, when, and how to use the image for better beam prediction. To answer this question, we split the dataset into three clusters -- (LOS, light NLOS, serious NLOS)-like -- based on the standard deviation of the beam sequence. With experiments we demonstrate that using the image indeed helps beam tracking especially when the user is in serious NLOS, and the solution relies on carefully-designed dataset for training a model. Generally speaking, including NLOS-like data for training a model does not benefit beam tracking of the user in LOS, but including light NLOS-like data for training a model benefits beam tracking of the user in serious NLOS.

cs.LG↗

arXiv2021

Concept-Aware Denoising Graph Neural Network for Micro-Video Recommendation

Recently, micro-video sharing platforms such as Kuaishou and Tiktok have become a major source of information for people's lives. Thanks to the large traffic volume, short video lifespan and streaming fashion of these services, it has become more and more pressing to improve the existing recommender systems to accommodate these challenges in a cost-effective way. In this paper, we propose a novel concept-aware denoising graph neural network (named CONDE) for micro-video recommendation. CONDE consists of a three-phase graph convolution process to derive user and micro-video representations: warm-up propagation, graph denoising and preference refinement. A heterogeneous tripartite graph is constructed by connecting user nodes with video nodes, and video nodes with associated concept nodes, extracted from captions and comments of the videos. To address the noisy information in the graph, we introduce a user-oriented graph denoising phase to extract a subgraph which can better reflect the user's preference. Despite the main focus of micro-video recommendation in this paper, we also show that our method can be generalized to other types of tasks. Therefore, we also conduct empirical studies on a well-known public E-commerce dataset. The experimental results suggest that the proposed CONDE achieves significantly better recommendation performance than the existing state-of-the-art solutions.

cs.IR↗

arXiv2021

Deep Learning Model for Demodulation Reference Signal based Channel Estimation

In this paper, we propose a deep learning model for Demodulation Reference Signal (DMRS) based channel estimation task. Specifically, a novel Denoise, Linear interpolation and Refine (DLR) pipeline is proposed to mitigate the noise propagation problem during channel information interpolation and to restore the nonlinear variation of wireless channel over time. At the same time, the Small-norm Sample Cost-sensitive (SSC) learning method is proposed to equalize the qualities of channel estimation under different kinds of wireless environments and improve the channel estimation reliability. The effectiveness of the propose DLR-SSC model is verified on WAIC Dataset. Compared with the well know ChannelNet channel estimation model, our DLR-SSC model reduced normalized mean square error (NMSE) by 27.2dB, 22.4dB and 16.8dB respectively at 0dB, 10dB, and 20dB SNR. The proposed model has won the second place in the 2nd Wireless Communication Artificial Intelligence Competition (WAIC). The code is about to open source.

eess.SP↗

arXiv2021

Extracting Complements and Substitutes from Sales Data: A Network Perspective

The complementarity and substitutability between products are essential concepts in retail and marketing. Qualitatively, two products are said to be substitutable if a customer can replace one product by the other, while they are complementary if they tend to be bought together. In this article, we take a network perspective to help automatically identify complements and substitutes from sales transaction data. Starting from a bipartite product-purchase network representation, with both transaction nodes and product nodes, we develop appropriate null models to infer significant relations, either complements or substitutes, between products, and design measures based on random walks to quantify their importance. The resulting unipartite networks between products are then analysed with community detection methods, in order to find groups of similar products for the different types of relationships. The results are validated by combining observations from a real-world basket dataset with the existing product hierarchy, as well as a large-scale flavour compound and recipe dataset.

cs.SI↗

arXiv2021

Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning

Anomaly detection with weakly supervised video-level labels is typically formulated as a multiple instance learning (MIL) problem, in which we aim to identify snippets containing abnormal events, with each video represented as a bag of video snippets. Although current methods show effective detection performance, their recognition of the positive instances, i.e., rare abnormal snippets in the abnormal videos, is largely biased by the dominant negative instances, especially when the abnormal events are subtle anomalies that exhibit only small differences compared with normal events. This issue is exacerbated in many methods that ignore important video temporal dependencies. To address this issue, we introduce a novel and theoretically sound method, named Robust Temporal Feature Magnitude learning (RTFM), which trains a feature magnitude learning function to effectively recognise the positive instances, substantially improving the robustness of the MIL approach to the negative instances from abnormal videos. RTFM also adapts dilated convolutions and self-attention mechanisms to capture long- and short-range temporal dependencies to learn the feature magnitude more faithfully. Extensive experiments show that the RTFM-enabled MIL model (i) outperforms several state-of-the-art methods by a large margin on four benchmark data sets (ShanghaiTech, UCF-Crime, XD-Violence and UCSD-Peds) and (ii) achieves significantly improved subtle anomaly discriminability and sample efficiency. Code is available at https://github.com/tianyu0207/RTFM.

cs.CV↗

arXiv2021

Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Images

Unsupervised anomaly detection (UAD) learns one-class classifiers exclusively with normal (i.e., healthy) images to detect any abnormal (i.e., unhealthy) samples that do not conform to the expected normal patterns. UAD has two main advantages over its fully supervised counterpart. Firstly, it is able to directly leverage large datasets available from health screening programs that contain mostly normal image samples, avoiding the costly manual labelling of abnormal samples and the subsequent issues involved in training with extremely class-imbalanced data. Further, UAD approaches can potentially detect and localise any type of lesions that deviate from the normal patterns. One significant challenge faced by UAD methods is how to learn effective low-dimensional image representations to detect and localise subtle abnormalities, generally consisting of small lesions. To address this challenge, we propose a novel self-supervised representation learning method, called Constrained Contrastive Distribution learning for anomaly detection (CCD), which learns fine-grained feature representations by simultaneously predicting the distribution of augmented data and image contexts using contrastive learning with pretext constraints. The learned representations can be leveraged to train more anomaly-sensitive detection models. Extensive experiment results show that our method outperforms current state-of-the-art UAD approaches on three different colonoscopy and fundus screening datasets. Our code is available at https://github.com/tianyu0207/CCD.

cs.CV↗

arXiv2021

RadioNet: Transformer based Radio Map Prediction Model For Dense Urban Environments

Radio Map Prediction (RMP), aiming at estimating coverage of radio wave, has been widely recognized as an enabling technology for improving radio spectrum efficiency. However, fast and reliable radio map prediction can be very challenging due to the complicated interaction between radio waves and the environment. In this paper, a novel Transformer based deep learning model termed as RadioNet is proposed for radio map prediction in urban scenarios. In addition, a novel Grid Embedding technique is proposed to substitute the original Position Embedding in Transformer to better anchor the relative position of the radiation source, destination and environment. The effectiveness of proposed method is verified on an urban radio wave propagation dataset. Compared with the SOTA model on RMP task, RadioNet reduces the validation loss by 27.3\%, improves the prediction reliability from 90.9\% to 98.9\%. The prediction speed is increased by 4 orders of magnitude, when compared with ray-tracing based method. We believe that the proposed method will be beneficial to high-efficiency wireless communication, real-time radio visualization, and even high-speed image rendering.

eess.SP↗

arXiv2021

Effect of the selective localization of carbon nanotubes and phase domain in immiscible blends on tunable microwave dielectric properties

In recent years, the immiscible polymer blend system has attracted much attention as the matrix of nanocomposites. Herein, from the perspective of dynamics, the control of the carbon nanotubes (CNTs) migration aided with the interface of polystyrene (PS) and poly(methyl methacrylate) (PMMA) blends was achieved through a facile melt mixing method. Thus, we revealed a comprehensive relationship between several typical CNTs migrating scenarios and the microwave dielectric properties of their nanocomposites. Based on the unique morphologies and phase domain structures of the immiscible matrix, we further investigated the multiple microwave dielectric relaxation processes and shed new light on the relation between relaxation peak position and the phase domain size distribution. Moreover, by integrating the CNTs interface localization control with the matrix co-continuous structure construction, we found that the interface promotes double percolation effect to achieve conductive percolation at low CNTs loading (~1.06 vol%). Overall, the present study provides a unique nanocomposite material design symphonizing both functional fillers dispersion and location as well as the matrix architecture optimization for microwave applications.

physics.app-ph↗

arXiv2021

A Good Image Generator Is What You Need for High-Resolution Video Synthesis

Image and video synthesis are closely related areas aiming at generating content from noise. While rapid progress has been demonstrated in improving image-based models to handle large resolutions, high-quality renderings, and wide variations in image content, achieving comparable video generation results remains problematic. We present a framework that leverages contemporary image generators to render high-resolution videos. We frame the video synthesis problem as discovering a trajectory in the latent space of a pre-trained and fixed image generator. Not only does such a framework render high-resolution videos, but it also is an order of magnitude more computationally efficient. We introduce a motion generator that discovers the desired trajectory, in which content and motion are disentangled. With such a representation, our framework allows for a broad range of applications, including content and motion manipulation. Furthermore, we introduce a new task, which we call cross-domain video synthesis, in which the image and motion generators are trained on disjoint datasets belonging to different domains. This allows for generating moving objects for which the desired video data is not available. Extensive experiments on various datasets demonstrate the advantages of our methods over existing video generation techniques. Code will be released at https://github.com/snap-research/MoCoGAN-HD.

cs.CV↗