arXiv subjects

Peng Wang

Publications and source records attributed to Peng Wang.

At least 757 records · Page 42Linked to original sources

arXiv2021

Photon Spheres and Spherical Accretion Image of a Hairy Black Hole

In this paper, we first consider null geodesics of a class of charged, spherical and asymptotically flat hairy black holes in an Einstein-Maxwell-scalar theory with a non-minimal coupling for the scalar and electromagnetic fields. Remarkably, we show that there are two unstable circular orbits for a photon in a certain parameter regime, corresponding to two unstable photon spheres of different sizes outside the event horizon. To illustrate the optical appearance of photon spheres, we then consider a simple spherical model of optically thin accretion on the hairy black hole, and obtain the accretion image seen by a distant observer. In the single photon sphere case, only one bright ring appears in the image, and is identified as the edge of the black hole shadow. Whereas in the case with two photon spheres, there can be two concentric bright rings of different radii in the image, and the smaller one serves as the boundary of the shadow, whose radius goes to zero at the critical charge.

gr-qc↗

arXiv2021

Chop Chop BERT: Visual Question Answering by Chopping VisualBERT's Heads

Vision-and-Language (VL) pre-training has shown great potential on many related downstream tasks, such as Visual Question Answering (VQA), one of the most popular problems in the VL field. All of these pre-trained models (such as VisualBERT, ViLBERT, LXMERT and UNITER) are built with Transformer, which extends the classical attention mechanism to multiple layers and heads. To investigate why and how these models work on VQA so well, in this paper we explore the roles of individual heads and layers in Transformer models when handling $12$ different types of questions. Specifically, we manually remove (chop) heads (or layers) from a pre-trained VisualBERT model at a time, and test it on different levels of questions to record its performance. As shown in the interesting echelon shape of the result matrices, experiments reveal different heads and layers are responsible for different question types, with higher-level layers activated by higher-level visual reasoning questions. Based on this observation, we design a dynamic chopping module that can automatically remove heads and layers of the VisualBERT at an instance level when dealing with different questions. Our dynamic chopping module can effectively reduce the parameters of the original model by 50%, while only damaging the accuracy by less than 1% on the VQA task.

cs.CV↗

arXiv2021

Center Prediction Loss for Re-identification

The training loss function that enforces certain training sample distribution patterns plays a critical role in building a re-identification (ReID) system. Besides the basic requirement of discrimination, i.e., the features corresponding to different identities should not be mixed, additional intra-class distribution constraints, such as features from the same identities should be close to their centers, have been adopted to construct losses. Despite the advances of various new loss functions, it is still challenging to strike the balance between the need of reducing the intra-class variation and allowing certain distribution freedom. In this paper, we propose a new loss based on center predictivity, that is, a sample must be positioned in a location of the feature space such that from it we can roughly predict the location of the center of same-class samples. The prediction error is then regarded as a loss called Center Prediction Loss (CPL). We show that, without introducing additional hyper-parameters, this new loss leads to a more flexible intra-class distribution constraint while ensuring the between-class samples are well-separated. Extensive experiments on various real-world ReID datasets show that the proposed loss can achieve superior performance and can also be complementary to existing losses.

cs.CV↗

arXiv2021

CAT: Cross-Attention Transformer for One-Shot Object Detection

Given a query patch from a novel class, one-shot object detection aims to detect all instances of that class in a target image through the semantic similarity comparison. However, due to the extremely limited guidance in the novel class as well as the unseen appearance difference between query and target instances, it is difficult to appropriately exploit their semantic similarity and generalize well. To mitigate this problem, we present a universal Cross-Attention Transformer (CAT) module for accurate and efficient semantic similarity comparison in one-shot object detection. The proposed CAT utilizes transformer mechanism to comprehensively capture bi-directional correspondence between any paired pixels from the query and the target image, which empowers us to sufficiently exploit their semantic characteristics for accurate similarity comparison. In addition, the proposed CAT enables feature dimensionality compression for inference speedup without performance loss. Extensive experiments on COCO, VOC, and FSOD under one-shot settings demonstrate the effectiveness and efficiency of our method, e.g., it surpasses CoAE, a major baseline in this task by 1.0% in AP on COCO and runs nearly 2.5 times faster. Code will be available in the future.

cs.CV↗

arXiv2021

The lopsided distribution of satellites of isolated central galaxies

Satellites are not randomly distributed around their central galaxies but show polar and planar structures. In this paper, we investigate the axis-asymmetry or lopsidedness of satellite galaxy distributions around isolated galaxies in a hydrodynamic cosmological simulation. We find a statistically significant lopsided signal by studying the angular distribution of the satellite galaxies' projected positions around isolated central galaxies in a two-dimensional plane. The signal is dependent on galaxy mass, color and large-scale environment. Satellites that inhabit low-mass blue hosts, or located further from the hosts show the most lopsided signal. Galaxy systems with massive neighbors exhibit stronger lopsidedness. This satellite axis-asymmetry signal also decreases as the universe evolves. Our findings are in agreement with recent observational results, and they provide a useful perspective for studying galaxy evolution, especially on the satellite accretion, internal evolution and interaction with the cosmic large-scale structure.

astro-ph.GA↗

arXiv2021

Joule-Thomson expansion of Lower-dimensional black hole

The Joule-Thomson expansion is extended to the lower-dimensional regime by considering the rotating BTZ metric in the (2+1)-dimensional space-time. Specifically, the properties of three important aspects of the Joule-Thomson expansion, namely the Joule-Thomson coefficient, the inversion curve and the isenthalpic curve are focused on. The divergence point of the Joule-Thomson coefficient and the zero point of the Hawking temperature are studied. The inversion temperature curves and isenthalpic curves in the $T-P$ plane are obtained and the cooling-heating regions are determined. Furthermore, the minimum inversion temperature is found to be zero, and the black hole becomes an extremal black hole. The ratio between the minimum inversion temperature and the critical temperature for the BTZ black hole doesn't exist, since the BTZ black hole does not have the critical behavior in $P_c$, $T_c$ and $V_c$.

gr-qc↗

arXiv2021

PURE: Passive mUlti-peRson idEntification via Deep Footstep Separation and Recognition

Recently, \textit{passive behavioral biometrics} (e.g., gesture or footstep) have become promising complements to conventional user identification methods (e.g., face or fingerprint) under special situations, yet existing sensing technologies require lengthy measurement traces and cannot identify multiple users at the same time. To this end, we propose \systemname\ as a passive multi-person identification system leveraging deep learning enabled footstep separation and recognition. \systemname\ passively identifies a user by deciphering the unique "footprints" in its footstep. Different from existing gait-enabled recognition systems incurring a long sensing delay to acquire many footsteps, \systemname\ can recognize a person by as few as only one step, substantially cutting the identification latency. To make \systemname\ adaptive to walking pace variations, environmental dynamics, and even unseen targets, we apply an adversarial learning technique to improve its domain generalisability and identification accuracy. Finally, \systemname\ can defend itself against replay attack, enabled by the richness of footstep and spatial awareness. We implement a \systemname\ prototype using commodity hardware and evaluate it in typical indoor settings. Evaluation results demonstrate a cross-domain identification accuracy of over 90\%.

cs.CV↗

arXiv2021

Fully-Automated Liver Tumor Localization and Characterization from Multi-Phase MR Volumes Using Key-Slice ROI Parsing: A Physician-Inspired Approach

Using radiological scans to identify liver tumors is crucial for proper patient treatment. This is highly challenging, as top radiologists only achieve F1 scores of roughly 80% (hepatocellular carcinoma (HCC) vs. others) with only moderate inter-rater agreement, even when using multi-phase magnetic resonance (MR) imagery. Thus, there is great impetus for computer-aided diagnosis (CAD) solutions. A critical challenge is to robustly parse a 3D MR volume to localize diagnosable regions of interest (ROI), especially for edge cases. In this paper, we break down this problem using a key-slice parser (KSP), which emulates physician workflows by first identifying key slices and then localizing their corresponding key ROIs. To achieve robustness, the KSP also uses curve-parsing and detection confidence re-weighting. We evaluate our approach on the largest multi-phase MR liver lesion test dataset to date (430 biopsy-confirmed patients). Experiments demonstrate that our KSP can localize diagnosable ROIs with high reliability: 87% patients have an average 3D overlap of >= 40% with the ground truth compared to only 79% using the best tested detector. When coupled with a classifier, we achieve an HCC vs. others F1 score of 0.801, providing a fully-automated CAD performance comparable to top human physicians.

cs.CV↗

arXiv2021

Residual Gaussian Process: A Tractable Nonparametric Bayesian Emulator for Multi-fidelity Simulations

Challenges in multi-fidelity modeling relate to accuracy, uncertainty estimation and high-dimensionality. A novel additive structure is introduced in which the highest fidelity solution is written as a sum of the lowest fidelity solution and residuals between the solutions at successive fidelity levels, with Gaussian process priors placed over the low fidelity solution and each of the residuals. The resulting model is equipped with a closed-form solution for the predictive posterior, making it applicable to advanced, high-dimensional tasks that require uncertainty estimation. Its advantages are demonstrated on univariate benchmarks and on three challenging multivariate problems. It is shown how active learning can be used to enhance the model, especially with a limited computational budget. Furthermore, error bounds are derived for the mean prediction in the univariate case.

cs.LG↗

arXiv2021

An Adversarial Human Pose Estimation Network Injected with Graph Structure

Because of the invisible human keypoints in images caused by illumination, occlusion and overlap, it is likely to produce unreasonable human pose prediction for most of the current human pose estimation methods. In this paper, we design a novel generative adversarial network (GAN) to improve the localization accuracy of visible joints when some joints are invisible. The network consists of two simple but efficient modules, Cascade Feature Network (CFN) and Graph Structure Network (GSN). First, the CFN utilizes the prediction maps from the previous stages to guide the prediction maps in the next stage to produce accurate human pose. Second, the GSN is designed to contribute to the localization of invisible joints by passing message among different joints. According to GAN, if the prediction pose produced by the generator G cannot be distinguished by the discriminator D, the generator network G has successfully obtained the underlying dependence of human joints. We conduct experiments on three widely used human pose estimation benchmark datasets, LSP, MPII and COCO, whose results show the effectiveness of our proposed framework.

cs.CV↗

arXiv2021

A Holistic Representation Guided Attention Network for Scene Text Recognition

Reading irregular scene text of arbitrary shape in natural images is still a challenging problem, despite the progress made recently. Many existing approaches incorporate sophisticated network structures to handle various shapes, use extra annotations for stronger supervision, or employ hard-to-train recurrent neural networks for sequence modeling. In this work, we propose a simple yet strong approach for scene text recognition. With no need to convert input images to sequence representations, we directly connect two-dimensional CNN features to an attention-based sequence decoder which guided by holistic representation. The holistic representation can guide the attention-based decoder focus on more accurate area. As no recurrent module is adopted, our model can be trained in parallel. It achieves 1.5x to 9.4x acceleration to backward pass and 1.3x to 7.9x acceleration to forward pass, compared with the RNN counterparts. The proposed model is trained with only word-level annotations. With this simple design, our method achieves state-of-the-art or competitive recognition performance on the evaluated regular and irregular scene text benchmark datasets.

cs.CV↗

arXiv2021

Instance and Pair-Aware Dynamic Networks for Re-Identification

Re-identification (ReID) is to identify the same instance across different cameras. Existing ReID methods mostly utilize alignment-based or attention-based strategies to generate effective feature representations. However, most of these methods only extract general feature by employing single input image itself, overlooking the exploration of relevance between comparing images. To fill this gap, we propose a novel end-to-end trainable dynamic convolution framework named Instance and Pair-Aware Dynamic Networks in this paper. The proposed model is composed of three main branches where a self-guided dynamic branch is constructed to strengthen instance-specific features, focusing on every single image. Furthermore, we also design a mutual-guided dynamic branch to generate pair-aware features for each pair of images to be compared. Extensive experiments are conducted in order to verify the effectiveness of our proposed algorithm. We evaluate our algorithm in several mainstream person and vehicle ReID datasets including CUHK03, DukeMTMCreID, Market-1501, VeRi776 and VehicleID. In some datasets our algorithm outperforms state-of-the-art methods and in others, our algorithm achieves a comparable performance.

cs.CV↗

arXiv2021

Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification

Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases. Given the promising performance contrastive learning has shown recently in representation learning, in this work, we explore effective supervised contrastive learning strategies and tailor them to learn better image representations from imbalanced data in order to boost the classification accuracy thereon. Specifically, we propose a novel hybrid network structure being composed of a supervised contrastive loss to learn image representations and a cross-entropy loss to learn classifiers, where the learning is progressively transited from feature learning to the classifier learning to embody the idea that better features make better classifiers. We explore two variants of contrastive loss for feature learning, which vary in the forms but share a common idea of pulling the samples from the same class together in the normalized embedding space and pushing the samples from different classes apart. One of them is the recently proposed supervised contrastive (SC) loss, which is designed on top of the state-of-the-art unsupervised contrastive loss by incorporating positive samples from the same class. The other is a prototypical supervised contrastive (PSC) learning strategy which addresses the intensive memory consumption in standard SC loss and thus shows more promise under limited memory budget. Extensive experiments on three long-tailed classification datasets demonstrate the advantage of the proposed contrastive learning based hybrid networks in long-tailed classification.

cs.CV↗

arXiv2021

Quantum transport properties of beta-Bi4I4 near and well beyond the extreme quantum limit

We have investigated the magneto-transport properties of beta-Bi4I4 bulk crystal, which was recently theoretically proposed and experimentally demonstrated to be a topological insulator. At low temperature T and magnetic field B, a series of Shubnikov-De Haas(SdH) oscillations are observed on the magnetoresistivity (MR). The detailed analysis reveals a light cyclotron mass of 0.1 me, and the field angle dependence of MR reveals that the SdH oscillations originate from a convex Fermi surface. In the extreme quantum limit (EQL) region, there is a metal-insulator transition occurring soon after the EQL. We perform the scaling analysis, and all the isotherms fall onto a universal scaling with a fitted critical exponent of 6.5. The enormous value of critical exponent implies this insulating quantum phase originated from strong electron-electron interactions in high fields. However, in the far end of EQL, both the longitudinal and Hall resistivity increase exponentially with B, and the temperature dependence of the MR reveals an energy gap induced by the high magnetic field, signifying a magnetic freeze-out effect. Our findings indicate that bulk beta-Bi4I4 is an excellent candidate for a 3D topological system for exploring EQL physics and relevant exotic quantum phases.

cond-mat.mtrl-sci↗

arXiv2021

Hetero-Modal Learning and Expansive Consistency Constraints for Semi-Supervised Detection from Multi-Sequence Data

Lesion detection serves a critical role in early diagnosis and has been well explored in recent years due to methodological advancesand increased data availability. However, the high costs of annotations hinder the collection of large and completely labeled datasets, motivating semi-supervised detection approaches. In this paper, we introduce mean teacher hetero-modal detection (MTHD), which addresses two important gaps in current semi-supervised detection. First, it is not obvious how to enforce unlabeled consistency constraints across the very different outputs of various detectors, which has resulted in various compromises being used in the state of the art. Using an anchor-free framework, MTHD formulates a mean teacher approach without such compromises, enforcing consistency on the soft-output of object centers and size. Second, multi-sequence data is often critical, e.g., for abdominal lesion detection, but unlabeled data is often missing sequences. To deal with this, MTHD incorporates hetero-modal learning in its framework. Unlike prior art, MTHD is able to incorporate an expansive set of consistency constraints that include geometric transforms and random sequence combinations. We train and evaluate MTHD on liver lesion detection using the largest MR lesion dataset to date (1099 patients with >5000 volumes). MTHD surpasses the best fully-supervised and semi-supervised competitors by 10.1% and 3.5%, respectively, in average sensitivity.

cs.CV↗

arXiv2021

Higher Performance Visual Tracking with Dual-Modal Localization

Visual Object Tracking (VOT) has synchronous needs for both robustness and accuracy. While most existing works fail to operate simultaneously on both, we investigate in this work the problem of conflicting performance between accuracy and robustness. We first conduct a systematic comparison among existing methods and analyze their restrictions in terms of accuracy and robustness. Specifically, 4 formulations-offline classification (OFC), offline regression (OFR), online classification (ONC), and online regression (ONR)-are considered, categorized by the existence of online update and the types of supervision signal. To account for the problem, we resort to the idea of ensemble and propose a dual-modal framework for target localization, consisting of robust localization suppressing distractors via ONR and the accurate localization attending to the target center precisely via OFC. To yield a final representation (i.e, bounding box), we propose a simple but effective score voting strategy to involve adjacent predictions such that the final representation does not commit to a single location. Operating beyond the real-time demand, our proposed method is further validated on 8 datasets-VOT2018, VOT2019, OTB2015, NFS, UAV123, LaSOT, TrackingNet, and GOT-10k, achieving state-of-the-art performance.

cs.CV↗

arXiv2021

Real-Time Visual Object Tracking via Few-Shot Learning

Visual Object Tracking (VOT) can be seen as an extended task of Few-Shot Learning (FSL). While the concept of FSL is not new in tracking and has been previously applied by prior works, most of them are tailored to fit specific types of FSL algorithms and may sacrifice running speed. In this work, we propose a generalized two-stage framework that is capable of employing a large variety of FSL algorithms while presenting faster adaptation speed. The first stage uses a Siamese Regional Proposal Network to efficiently propose the potential candidates and the second stage reformulates the task of classifying these candidates to a few-shot classification problem. Following such a coarse-to-fine pipeline, the first stage proposes informative sparse samples for the second stage, where a large variety of FSL algorithms can be conducted more conveniently and efficiently. As substantiation of the second stage, we systematically investigate several forms of optimization-based few-shot learners from previous works with different objective functions, optimization methods, or solution space. Beyond that, our framework also entails a direct application of the majority of other FSL algorithms to visual tracking, enabling mutual communication between researchers on these two topics. Extensive experiments on the major benchmarks, VOT2018, OTB2015, NFS, UAV123, TrackingNet, and GOT-10k are conducted, demonstrating a desirable performance gain and a real-time speed.

cs.CV↗

arXiv2021

Electron-plasmon interaction induced plasmonic-polaron band replication in epitaxial perovskite SrIrO$_3$ films

Electron-boson interaction is fundamental to a thorough understanding of various exotic properties emerging in many-body physics. In photoemission spectroscopy, photoelectron emission due to photon absorption would trigger diverse collective excitations in solids, including the emergence of phonons, magnons, electron-hole pairs, and plasmons, which naturally provides a reliable pathway to study electron-boson couplings. While fingerprints of electron-phonon/-magnon interactions in this state-of-the-art technique have been well investigated, much less is known about electron-plasmon coupling, and direct observation of the band renormalization solely due to electron-plasmon interactions is extremely challenging. Here by utilizing integrated oxide molecular-beam epitaxy and angle-resolved photoemission spectroscopy, we discover the long sought-after pure electron-plasmon coupling-induced low-lying plasmonic-polaron replica bands in epitaxial semimetallic SrIrO$_3$ films, in which the characteristic low carrier concentration and narrow bandwidth combine to provide a unique platform where the electron-plasmon interaction can be investigated kinematically in photoemission spectroscopy. This finding enriches the forms of electron band normalization on collective modes in solids and demonstrates that, to obtain a complete understanding of the quasiparticle dynamics in 5d electron systems, the electron-plasmon interaction should be considered on equal footing with the acknowledged electron-electron interaction and spin-orbit coupling.

cond-mat.str-el↗