arXiv subjects

Qian Zhang

Publications and source records attributed to Qian Zhang.

At least 343 records · Page 19Linked to original sources

arXiv2022

Learning Quality-aware Representation for Multi-person Pose Regression

Off-the-shelf single-stage multi-person pose regression methods generally leverage the instance score (i.e., confidence of the instance localization) to indicate the pose quality for selecting the pose candidates. We consider that there are two gaps involved in existing paradigm:~1) The instance score is not well interrelated with the pose regression quality.~2) The instance feature representation, which is used for predicting the instance score, does not explicitly encode the structural pose information to predict the reasonable score that represents pose regression quality. To address the aforementioned issues, we propose to learn the pose regression quality-aware representation. Concretely, for the first gap, instead of using the previous instance confidence label (e.g., discrete {1,0} or Gaussian representation) to denote the position and confidence for person instance, we firstly introduce the Consistent Instance Representation (CIR) that unifies the pose regression quality score of instance and the confidence of background into a pixel-wise score map to calibrates the inconsistency between instance score and pose regression quality. To fill the second gap, we further present the Query Encoding Module (QEM) including the Keypoint Query Encoding (KQE) to encode the positional and semantic information for each keypoint and the Pose Query Encoding (PQE) which explicitly encodes the predicted structural pose information to better fit the Consistent Instance Representation (CIR). By using the proposed components, we significantly alleviate the above gaps. Our method outperforms previous single-stage regression-based even bottom-up methods and achieves the state-of-the-art result of 71.7 AP on MS COCO test-dev set.

cs.CV↗

arXiv2021

AdaptivePose: Human Parts as Adaptive Points

Multi-person pose estimation methods generally follow top-down and bottom-up paradigms, both of which can be considered as two-stage approaches thus leading to the high computation cost and low efficiency. Towards a compact and efficient pipeline for multi-person pose estimation task, in this paper, we propose to represent the human parts as points and present a novel body representation, which leverages an adaptive point set including the human center and seven human-part related points to represent the human instance in a more fine-grained manner. The novel representation is more capable of capturing the various pose deformation and adaptively factorizes the long-range center-to-joint displacement thus delivers a single-stage differentiable network to more precisely regress multi-person pose, termed as AdaptivePose. For inference, our proposed network eliminates the grouping as well as refinements and only needs a single-step disentangling process to form multi-person pose. Without any bells and whistles, we achieve the best speed-accuracy trade-offs of 67.4% AP / 29.4 fps with DLA-34 and 71.3% AP / 9.1 fps with HRNet-W48 on COCO test-dev dataset.

cs.CV↗

arXiv2021

Record high $T_{\rm c}$ and robust superconductivity in transition metal $δ$-Ti phase at megabar pressure

We report a record high superconducting transition temperature ($T_{\rm c}$) up to 23.6 K under high pressure in the elemental metal Ti, one of the top ten most abundant elements in Earth's crust. The $T_{\rm c}$ increases monotonically from 2.3 K at 40.3 GPa to 23.6 K at 144.9 GPa, which surpasses all known records from elemental metals reported so far. With further compression, a robust $T_{\rm c}$ of ~23 K is observed between 144.9 and 183 GPa in the $δ$-Ti phase. The pressure-dependent $T_{\rm c}$ can be well described by the conventional electron-phonon coupling (EPC) mechanism. Density Functional Theory calculations show the Fermi nesting and the phonon softening of optical branches at the $γ$-Ti to $δ$-Ti phase transition pressure enhance EPC, which results in the record high $T_{\rm c}$. We attribute the robust superconductivity in $δ$-Ti to the apparent robustness of its strong EPC against lattice compression. These results provide new insight into exploring new high-$T_{\rm c}$ elemental metals and Ti-based superconducting alloys.

cond-mat.supr-con↗

arXiv2021

Road-aware Monocular Structure from Motion and Homography Estimation

Structure from motion (SFM) and ground plane homography estimation are critical to autonomous driving and other robotics applications. Recently, much progress has been made in using deep neural networks for SFM and homography estimation respectively. However, directly applying existing methods for ground plane homography estimation may fail because the road is often a small part of the scene. Besides, the performances of deep SFM approaches are still inferior to traditional methods. In this paper, we propose a method that learns to solve both problems in an end-to-end manner, improving performance on both. The proposed networks consist of a Depth-CNN, a Pose-CNN and a Ground-CNN. The Depth-CNN and Pose-CNN estimate dense depth map and ego-motion respectively, solving SFM, while the Pose-CNN and Ground-CNN followed by a homography layer solve the ground plane estimation problem. By enforcing coherency between SFM and homography estimation results, the whole network can be trained end to end using photometric loss and homography loss without any groundtruth except the road segmentation provided by an off-the-shelf segmenter. Comprehensive experiments are conducted on KITTI benchmark to demonstrate promising results compared with various state-of-the-art approaches.

cs.CV↗

arXiv2021

Pressure-Driven Magneto-Topological Phase Transition in a magnetic Weyl semimetal

The co-occurrence of phase transitions with local and global order parameters, such as the entangled magnetization and topological invariant, is attractive but has been seldom realized experimentally. Here, by using high-pressure in-situ X-ray diffraction, high-pressure electric transport measurements and high-pressure first-principles calculations, we report a magneto-topological phase transition, i.e., the phenomenon of magnetic materials undergoing different magnetic and topological phases during the process of pressure loading, in a recently discovered magnetic Weyl semimetal Co3Sn2S2. By considering both out-of-plane ferromagnetic and in-plane anti-ferromagnetic components, the calculated results can well fit the experimental data. The calculation results furtherly reveal a pristine Weyl phase with four more pairs of Weyl nodes under low pressures, and a generally-defined Z2 topological insulator phase after the restoration of time-reversal symmetry. Remarkably, the present magneto-topological phase transition involves a pair of crossing bands of two spin channels becoming degenerate. Thus, all the chiral Weyl nodes annihilate with their counterparts from another spin channel, in contrast to the typical annihilation of Weyl pairs from the same bands in inversion-asymmetric systems. Our experiments and theoretical calculations uncover a manner to modulate the diverse topological states by controlling the internal exchange splitting via external physical knobs in topological magnets.

cond-mat.mtrl-sci↗

arXiv2021

Spiking CapsNet: A Spiking Neural Network With A Biologically Plausible Routing Rule Between Capsules

Spiking neural network (SNN) has attracted much attention due to their powerful spatio-temporal information representation ability. Capsule Neural Network (CapsNet) does well in assembling and coupling features at different levels. Here, we propose Spiking CapsNet by introducing the capsules into the modelling of spiking neural networks. In addition, we propose a more biologically plausible Spike Timing Dependent Plasticity routing mechanism. By fully considering the spatio-temporal relationship between the low-level spiking capsules and the high-level spiking capsules, the coupling ability between them is further improved. We have verified experiments on the MNIST and FashionMNIST datasets. Compared with other excellent SNN models, our algorithm still achieves high performance. Our Spiking CapsNet fully combines the strengthens of SNN and CapsNet, and shows strong robustness to noise and affine transformation. By adding different Salt-Pepper and Gaussian noise to the test dataset, the experimental results demonstrate that our Spiking CapsNet shows a more robust performance when there is more noise, while the artificial neural network can not correctly clarify. As well, our Spiking CapsNet shows strong generalization to affine transformation on the AffNIST dataset.

cs.NE↗

arXiv2021

Spurious solutions for high order curl problems

We investigate numerical solutions of high order curl problems with various formulations and finite elements. We show that several classical conforming finite elements lead to spurious solutions, while mixed formulations with finite elements in complexes solve the problems correctly. To explain the numerical results, we clarify the cohomological structures in high order curl problems by relating the partial differential equations to the Hodge-Laplacian boundary problems of the gradcurl-complexes.

math.NA↗

arXiv2021

A family of finite element Stokes complexes in three dimensions

We construct finite element Stokes complexes on tetrahedral meshes in three-dimensional space. In the lowest order case, the finite elements in the complex have 4, 18, 16, and 1 degrees of freedom, respectively. As a consequence, we obtain gradcurl-conforming finite elements and inf-sup stable Stokes pairs on tetrahedra which fit into complexes. We show that the new elements lead to convergent algorithms for solving a gradcurl model problem as well as solving the Stokes system with precise divergence-free condition. We demonstrate the validity of the algorithms by numerical experiments.

math.NA↗

arXiv2021

Two-phase segmentation for intensity inhomogeneous images by the Allen-Cahn Local Binary Fitting Model

This paper proposes a new variational model by integrating the Allen-Cahn term with a local binary fitting energy term for segmenting images with intensity inhomogeneity and noise. An inhomogeneous graph Laplacian initialization method (IGLIM) is developed to give the initial contour for two-phase image segmentation problems. To solve the Allen-Cahn equation derived from the variational model, we adopt the exponential time differencing (ETD) method for temporal discretization, and the central finite difference method for spatial discretization. The energy stability of proposed numerical schemes can be proved. Experiments on various images demonstrate the necessity and superiority of proper initialization and verify the capability of our model for two-phase segmentation of images with intensity inhomogeneity and noise.

math.NA↗

arXiv2021

Autonomous Underwater Vehicle-Manipulator Systems Path Planning with RRTAUVMS Algorithm

Autonomous Underwater Vehicle-Manipulator systems (AUVMS) is a new tool for ocean exploration, the AUVMS path planning problem is addressed in this paper. AUVMS is a high dimension system with a large difference in inertia distribution, also it works in a complex environment with obstacles. By integrating the rapidly-exploring random tree(RRT) algorithm with the AUVMS kinematics model, the proposed RRTAUVMS algorithm could randomly sample in the configuration space(C-Space), and also grow the tree directly towards the workspace goal in the task space. The RRTAUVMS can also deal with the redundant mapping of workspace planning goal and configuration space goal. Compared with the traditional RRT algorithm, the efficiency of the AUVMS path planning can be significantly improved.

cs.RO↗

arXiv2021

Simple curl-curl-conforming finite elements in two dimensions

We construct smooth finite element de Rham complexes in two space dimensions. This leads to three families of curl-curl conforming finite elements, two of which contain two existing families. The simplest triangular and rectangular finite elements have only 6 and 8 degrees of freedom, respectively. Numerical experiments for each family demonstrate the convergence and efficiency of the elements for solving the quad-curl problem.

math.NA↗

arXiv2021

Hierarchical Aggregation for 3D Instance Segmentation

Instance segmentation on point clouds is a fundamental task in 3D scene perception. In this work, we propose a concise clustering-based framework named HAIS, which makes full use of spatial relation of points and point sets. Considering clustering-based methods may result in over-segmentation or under-segmentation, we introduce the hierarchical aggregation to progressively generate instance proposals, i.e., point aggregation for preliminarily clustering points to sets and set aggregation for generating complete instances from sets. Once the complete 3D instances are obtained, a sub-network of intra-instance prediction is adopted for noisy points filtering and mask quality scoring. HAIS is fast (only 410ms per frame) and does not require non-maximum suppression. It ranks 1st on the ScanNet v2 benchmark, achieving the highest 69.9% AP50 and surpassing previous state-of-the-art (SOTA) methods by a large margin. Besides, the SOTA results on the S3DIS dataset validate the good generalization ability. Code will be available at https://github.com/hustvl/HAIS.

cs.CV↗

arXiv2021

Deep Momentum Uncertainty Hashing

Combinatorial optimization (CO) has been a hot research topic because of its theoretic and practical importance. As a classic CO problem, deep hashing aims to find an optimal code for each data from finite discrete possibilities, while the discrete nature brings a big challenge to the optimization process. Previous methods usually mitigate this challenge by binary approximation, substituting binary codes for real-values via activation functions or regularizations. However, such approximation leads to uncertainty between real-values and binary ones, degrading retrieval performance. In this paper, we propose a novel Deep Momentum Uncertainty Hashing (DMUH). It explicitly estimates the uncertainty during training and leverages the uncertainty information to guide the approximation process. Specifically, we model bit-level uncertainty via measuring the discrepancy between the output of a hashing network and that of a momentum-updated network. The discrepancy of each bit indicates the uncertainty of the hashing network to the approximate output of that bit. Meanwhile, the mean discrepancy of all bits in a hashing code can be regarded as image-level uncertainty. It embodies the uncertainty of the hashing network to the corresponding input image. The hashing bit and image with higher uncertainty are paid more attention during optimization. To the best of our knowledge, this is the first work to study the uncertainty in hashing bits. Extensive experiments are conducted on four datasets to verify the superiority of our method, including CIFAR-10, NUS-WIDE, MS-COCO, and a million-scale dataset Clothing1M. Our method achieves the best performance on all of the datasets and surpasses existing state-of-the-art methods by a large margin.

cs.CV↗

arXiv2021

AOSLO-net: A deep learning-based method for automatic segmentation of retinal microaneurysms from adaptive optics scanning laser ophthalmoscope images

Microaneurysms (MAs) are one of the earliest signs of diabetic retinopathy (DR), a frequent complication of diabetes that can lead to visual impairment and blindness. Adaptive optics scanning laser ophthalmoscopy (AOSLO) provides real-time retinal images with resolution down to 2 $μm$ and thus allows detection of the morphologies of individual MAs, a potential marker that might dictate MA pathology and affect the progression of DR. In contrast to the numerous automatic models developed for assessing the number of MAs on fundus photographs, currently there is no high throughput image protocol available for automatic analysis of AOSLO photographs. To address this urgency, we introduce AOSLO-net, a deep neural network framework with customized training policies to automatically segment MAs from AOSLO images. We evaluate the performance of AOSLO-net using 87 DR AOSLO images and our results demonstrate that the proposed model outperforms the state-of-the-art segmentation model both in accuracy and cost and enables correct MA morphological classification.

eess.IV↗

arXiv2021

Securing IoT Devices by Exploiting Backscatter Propagation Signatures

The low-power radio technologies open up many opportunities to facilitate Internet-of-Things (IoT) into our daily life, while their minimalist design also makes IoT devices vulnerable to many active attacks. Recent advances use an antenna array to extract fine-grained physical-layer signatures to identify the attackers, which adds burdens in terms of energy and hardware cost to IoT devices. In this paper, we present ShieldScatter, a lightweight system that attaches low-cost tags to single-antenna devices to shield the system from active attacks. The key insight of ShieldScatter is to intentionally create multi-path propagation signatures with the careful deployment of tags. These signatures can be used to construct a sensitive profile to identify the location of the signals' arrival, and thus detect the threat. In addition, we also design a tag-random scheme and a multiple receivers combination approach to detect a powerful attacker who has the strong priori knowledge of the legitimate user. We prototype ShieldScatter with USRPs and tags to evaluate our system in various environments. The results show that even when the powerful attacker is close to the legitimate device, ShieldScatter can mitigate 95% of attack attempts while triggering false alarms on just 7% of legitimate traffic.

cs.CR↗

arXiv2021

Hyperspectral Image Denoising with Log-Based Robust PCA

It is a challenging task to remove heavy and mixed types of noise from Hyperspectral images (HSIs). In this paper, we propose a novel nonconvex approach to RPCA for HSI denoising, which adopts the log-determinant rank approximation and a novel $\ell_{2,\log}$ norm, to restrict the low-rank or column-wise sparse properties for the component matrices, respectively.For the $\ell_{2,\log}$-regularized shrinkage problem, we develop an efficient, closed-form solution, which is named $\ell_{2,\log}$-shrinkage operator, which can be generally used in other problems. Extensive experiments on both simulated and real HSIs demonstrate the effectiveness of the proposed method in denoising HSIs.

cs.CV↗

arXiv2021

Reducing Streaming ASR Model Delay with Self Alignment

Reducing prediction delay for streaming end-to-end ASR models with minimal performance regression is a challenging problem. Constrained alignment is a well-known existing approach that penalizes predicted word boundaries using external low-latency acoustic models. On the contrary, recently proposed FastEmit is a sequence-level delay regularization scheme encouraging vocabulary tokens over blanks without any reference alignments. Although all these schemes are successful in reducing delay, ASR word error rate (WER) often severely degrades after applying these delay constraining schemes. In this paper, we propose a novel delay constraining method, named self alignment. Self alignment does not require external alignment models. Instead, it utilizes Viterbi forced-alignments from the trained model to find the lower latency alignment direction. From LibriSpeech evaluation, self alignment outperformed existing schemes: 25% and 56% less delay compared to FastEmit and constrained alignment at the similar word error rate. For Voice Search evaluation,12% and 25% delay reductions were achieved compared to FastEmit and constrained alignment with more than 2% WER improvements.

eess.AS↗

arXiv2021

Two-phase image segmentation by the Allen-Cahn equation and a nonlocal edge detection operator

Based on a nonlocal Laplacian operator, a novel edge detection method of the grayscale image is proposed in this paper. This operator utilizes the information of neighbor pixels for a given pixel to obtain effective and delicate edge detection. The nonlocal edge detection method is used as an initialization for solving the Allen-Cahn equation to achieve two-phase segmentation of the grayscale image. Efficient exponential time differencing (ETD) solvers are employed in the time integration, and finite difference method is adopted in space discretization. The maximum bound principle and energy stability of the proposed numerical schemes are proved. The capability of our segmentation method has been verified in numerical experiments for different types of grayscale images.

math.NA↗