arXiv subjects
Publications and source records attributed to Zheng Zhu.
We establish point wise inequalities for Sobolev functions on a wider class of outward cuspidal domains. It is a generalization of an earlier result by the author and his collaborators
Recently, face recognition in the wild has achieved remarkable success and one key engine is the increasing size of training data. For example, the largest face dataset, WebFace42M contains about 2 million identities and 42 million faces. However, a massive number of faces raise the constraints in training time, computing resources, and memory cost. The current research on this problem mainly focuses on designing an efficient Fully-connected layer (FC) to reduce GPU memory consumption caused by a large number of identities. In this work, we relax these constraints by resolving the redundancy problem of the up-to-date face datasets caused by the greedily collecting operation (i.e. the core-set selection perspective). As the first attempt in this perspective on the face recognition problem, we find that existing methods are limited in both performance and efficiency. For superior cost-efficiency, we contribute a novel filtering strategy dubbed Face-NMS. Face-NMS works on feature space and simultaneously considers the local and global sparsity in generating core sets. In practice, Face-NMS is analogous to Non-Maximum Suppression (NMS) in the object detection community. It ranks the faces by their potential contribution to the overall sparsity and filters out the superfluous face in the pairs with high similarity for local sparsity. With respect to the efficiency aspect, Face-NMS accelerates the whole pipeline by applying a smaller but sufficient proxy dataset in training the proxy model. As a result, with Face-NMS, we successfully scale down the WebFace42M dataset to 60% while retaining its performance on the main benchmarks, offering a 40% resource-saving and 1.64 times acceleration. The code is publicly available for reference at https://github.com/HuangJunJie2017/Face-NMS.
During the COVID-19 coronavirus epidemic, almost everyone wears a facial mask, which poses a huge challenge to deep face recognition. In this workshop, we organize Masked Face Recognition (MFR) challenge and focus on bench-marking deep face recognition methods under the existence of facial masks. In the MFR challenge, there are two main tracks: the InsightFace track and the WebFace260M track. For the InsightFace track, we manually collect a large-scale masked face test set with 7K identities. In addition, we also collect a children test set including 14K identities and a multi-racial test set containing 242K identities. By using these three test sets, we build up an online model testing system, which can give a comprehensive evaluation of face recognition models. To avoid data privacy problems, no test image is released to the public. As the challenge is still under-going, we will keep on updating the top-ranked solutions as well as this report on the arxiv.
According to WHO statistics, there are more than 204,617,027 confirmed COVID-19 cases including 4,323,247 deaths worldwide till August 12, 2021. During the coronavirus epidemic, almost everyone wears a facial mask. Traditionally, face recognition approaches process mostly non-occluded faces, which include primary facial features such as the eyes, nose, and mouth. Removing the mask for authentication in airports or laboratories will increase the risk of virus infection, posing a huge challenge to current face recognition systems. Due to the sudden outbreak of the epidemic, there are yet no publicly available real-world masked face recognition (MFR) benchmark. To cope with the above-mentioned issue, we organize the Face Bio-metrics under COVID Workshop and Masked Face Recognition Challenge in ICCV 2021. Enabled by the ultra-large-scale WebFace260M benchmark and the Face Recognition Under Inference Time conStraint (FRUITS) protocol, this challenge (WebFace260M Track) aims to push the frontiers of practical MFR. Since public evaluation sets are mostly saturated or contain noise, a new test set is gathered consisting of elaborated 2,478 celebrities and 60,926 faces. Meanwhile, we collect the world-largest real-world masked test set. In the first phase of WebFace260M Track, 69 teams (total 833 solutions) participate in the challenge and 49 teams exceed the performance of our baseline. There are second phase of the challenge till October 1, 2021 and on-going leaderboard. We will actively update this report in the future.
We prove that a bi-Lipschitz image of a planar $BV$-extension domain is also a $BV$-extension domain, and that a bi-Lipschitz image of a planar $W^{1,1}$-extension domain is again a $W^{1,1}$-extension domain.
In this paper, we study the Sobolev extension property of Lp-quasidisks which are the generalizations of the classical quasidisks. After that, we also find some applications of their Sobolev extension property.
Inspired by the recent discovery of superconductivity in the nickelate Nd$_{1-x}$Sr$_x$NiO$_2$, we study a generalized $t-J$ model to investigate the correlated phases induced by doping spin-one Ni$^{2+}$ into a spin $1/2$ Mott insulator formed by Ni$^{1+}$. Based on a three-fermion parton mean field analysis, we identify a robust fractional Fermi liquid (FL*) phase for almost every doping level. The FL* state is characterized by a small Fermi pocket on top of a spin liquid, which violates the Luttinger theorem of a conventional Fermi liquid and is an example of a symmetric pseudogap metal. Furthermore, we verify our theory in one dimension through density matrix renormalization group (DMRG) simulations on both the generalized $t-J$ model and a two-orbital Hubbard model. The fractional Fermi liquid reduces to fractional Luttinger liquid (LL*) in one dimension, which is connected to the conventional Luttinger liquid through a continuous quantum phase transition by tuning interaction strength. Our findings offer new insights into correlated electron phenomena in nickelate superconductors and other multi-orbital transition metal oxide with spin-triplet $d^8$ state.
The practical application requests both accuracy and efficiency on multi-person pose estimation algorithms. But the high accuracy and fast inference speed are dominated by top-down methods and bottom-up methods respectively. To make a better trade-off between accuracy and efficiency, we propose a novel multi-person pose estimation framework, SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation (SIMPLE). Specifically, in the training process, we enable SIMPLE to mimic the pose knowledge from the high-performance top-down pipeline, which significantly promotes SIMPLE's accuracy while maintaining its high efficiency during inference. Besides, SIMPLE formulates human detection and pose estimation as a unified point learning framework to complement each other in single-network. This is quite different from previous works where the two tasks may interfere with each other. To the best of our knowledge, both mimicking strategy between different method types and unified point learning are firstly proposed in pose estimation. In experiments, our approach achieves the new state-of-the-art performance among bottom-up methods on the COCO, MPII and PoseTrack datasets. Compared with the top-down approaches, SIMPLE has comparable accuracy and faster inference speed.
Face clustering is a promising method for annotating unlabeled face images. Recent supervised approaches have boosted the face clustering accuracy greatly, however their performance is still far from satisfactory. These methods can be roughly divided into global-based and local-based ones. Global-based methods suffer from the limitation of training data scale, while local-based ones are difficult to grasp the whole graph structure information and usually take a long time for inference. Previous approaches fail to tackle these two challenges simultaneously. To address the dilemma of large-scale training and efficient inference, we propose the STructure-AwaRe Face Clustering (STAR-FC) method. Specifically, we design a structure-preserved subgraph sampling strategy to explore the power of large-scale training data, which can increase the training data scale from ${10^{5}}$ to ${10^{7}}$. During inference, the STAR-FC performs efficient full-graph clustering with two steps: graph parsing and graph refinement. And the concept of node intimacy is introduced in the second step to mine the local structural information. The STAR-FC gets 91.97 pairwise F-score on partial MS1M within 310s which surpasses the state-of-the-arts. Furthermore, we are the first to train on very large-scale graph with 20M nodes, and achieve superior inference results on 12M testing data. Overall, as a simple and effective method, the proposed STAR-FC provides a strong baseline for large-scale face clustering. Code is available at \url{https://sstzal.github.io/STAR-FC/}.
In this paper, we contribute a new million-scale face benchmark containing noisy 4M identities/260M faces (WebFace260M) and cleaned 2M identities/42M faces (WebFace42M) training data, as well as an elaborately designed time-constrained evaluation protocol. Firstly, we collect 4M name list and download 260M faces from the Internet. Then, a Cleaning Automatically utilizing Self-Training (CAST) pipeline is devised to purify the tremendous WebFace260M, which is efficient and scalable. To the best of our knowledge, the cleaned WebFace42M is the largest public face recognition training set and we expect to close the data gap between academia and industry. Referring to practical scenarios, Face Recognition Under Inference Time conStraint (FRUITS) protocol and a test set are constructed to comprehensively evaluate face matchers. Equipped with this benchmark, we delve into million-scale face recognition problems. A distributed framework is developed to train face recognition models efficiently without tampering with the performance. Empowered by WebFace42M, we reduce relative 40% failure rate on the challenging IJB-C set, and ranks the 3rd among 430 entries on NIST-FRVT. Even 10% data (WebFace4M) shows superior performance compared with public training set. Furthermore, comprehensive baselines are established on our rich-attribute test set under FRUITS-100ms/500ms/1000ms protocol, including MobileNet, EfficientNet, AttentionNet, ResNet, SENet, ResNeXt and RegNet families. Benchmark website is https://www.face-benchmark.org.
Being a fundamental component in training and inference, data processing has not been systematically considered in human pose estimation community, to the best of our knowledge. In this paper, we focus on this problem and find that the devil of human pose estimation evolution is in the biased data processing. Specifically, by investigating the standard data processing in state-of-the-art approaches mainly including coordinate system transformation and keypoint format transformation (i.e., encoding and decoding), we find that the results obtained by common flipping strategy are unaligned with the original ones in inference. Moreover, there is a statistical error in some keypoint format transformation methods. Two problems couple together, significantly degrade the pose estimation performance and thus lay a trap for the research community. This trap has given bone to many suboptimal remedies, which are always unreported, confusing but influential. By causing failure in reproduction and unfair in comparison, the unreported remedies seriously impedes the technological development. To tackle this dilemma from the source, we propose Unbiased Data Processing (UDP) consist of two technique aspect for the two aforementioned problems respectively (i.e., unbiased coordinate system transformation and unbiased keypoint format transformation). As a model-agnostic approach and a superior solution, UDP successfully pushes the performance boundary of human pose estimation and offers a higher and more reliable baseline for research community. Code is public available in https://github.com/HuangJunJie2017/UDP-Pose
Let $n\geq 2$ and $1\leq q 2$, then $|\partialΩ|=0$. In the case $1\leq q 0$.
Both appearance cue and constraint cue are vital for human pose estimation. However, there is a tendency in most existing works to overfitting the former and overlook the latter. In this paper, we propose Augmentation by Information Dropping (AID) to verify and tackle this dilemma. Alone with AID as a prerequisite for effectively exploiting its potential, we propose customized training schedules, which are designed by analyzing the pattern of loss and performance in training process from the perspective of information supplying. In experiments, as a model-agnostic approach, AID promotes various state-of-the-art methods in both bottom-up and top-down paradigms with different input sizes, frameworks, backbones, training and testing sets. On popular COCO human pose estimation test set, AID consistently boosts the performance of different configurations by around 0.6 AP in top-down paradigm and up to 1.5 AP in bottom-up paradigm. On more challenging CrowdPose dataset, the improvement is more than 1.5 AP. As AID successfully pushes the performance boundary of human pose estimation problem by considerable margin and sets a new state-of-the-art, we hope AID to be a regular configuration for training human pose estimators. The source code will be publicly available for further research.
Ride-hailing platforms generally provide various service options to customers, such as solo ride services, shared ride services, etc. It is generally expected that demands for different service modes are correlated, and the prediction of demand for one service mode can benefit from historical observations of demands for other service modes. Moreover, an accurate joint prediction of demands for multiple service modes can help the platforms better allocate and dispatch vehicle resources. Although there is a large stream of literature on ride-hailing demand predictions for one specific service mode, little efforts have been paid towards joint predictions of ride-hailing demands for multiple service modes. To address this issue, we propose a deep multi-task multi-graph learning approach, which combines two components: (1) multiple multi-graph convolutional (MGC) networks for predicting demands for different service modes, and (2) multi-task learning modules that enable knowledge sharing across multiple MGC networks. More specifically, two multi-task learning structures are established. The first one is the regularized cross-task learning, which builds cross-task connections among the inputs and outputs of multiple MGC networks. The second one is the multi-linear relationship learning, which imposes a prior tensor normal distribution on the weights of various MGC networks. Although there are no concrete bridges between different MGC networks, the weights of these networks are constrained by each other and subject to a common prior distribution. Evaluated with the for-hire-vehicle datasets in Manhattan, we show that our propose approach outperforms the benchmark algorithms in prediction accuracy for different ride-hailing modes.
This paper proposes a new convolutional neural network with multiscale processing for detecting ground-glass opacity (GGO) nodules in 3D computed tomography (CT) images, which is referred to as PiaNet for short. PiaNet consists of a feature-extraction module and a prediction module. The former module is constructed by introducing pyramid multiscale source connections into a contracting-expanding structure. The latter module includes a bounding-box regressor and a classifier that are employed to simultaneously recognize GGO nodules and estimate bounding boxes at multiple scales. To train the proposed PiaNet, a two-stage transfer learning strategy is developed. In the first stage, the feature-extraction module is embedded into a classifier network that is trained on a large data set of GGO and non-GGO patches, which are generated by performing data augmentation from a small number of annotated CT scans. In the second stage, the pretrained feature-extraction module is loaded into PiaNet, and then PiaNet is fine-tuned using the annotated CT scans. We evaluate the proposed PiaNet on the LIDC-IDRI data set. The experimental results demonstrate that our method outperforms state-of-the-art counterparts, including the Subsolid CAD and Aidence systems and S4ND and GA-SSD methods. PiaNet achieves a sensitivity of 91.75% with only one false positive per scan
We develop a proposal to realise a widely tunable and clean quantum phase transition in bilayer graphene between two paradigmatic fractionalized phases of matter: the Moore-Read fractional quantum Hall state and the composite Fermi liquid metal. This transition can be realized at total fillings $ν=\pm 3+1/2$ and the critical point can be controllably accessed by tuning either the interlayer electric bias or the perpendicular magnetic field values over a wide range of parameters. We study the transition numerically within a model that contains all leading single particle corrections to the band-structure of bilayer graphene and includes the fluctuations between the $n=0$ and $n=1$ cyclotron orbitals of its zeroth Landau level to delineate the most favorable region of parameters to experimentally access this unconventional critical point. We also find evidence for a new anisotropic gapless phase stabilized near the level crossing of $n=0/1$ orbits.
We investigate the ground state properties of the spin S=1 Kitaev honeycomb model under a magnetic field based on the density matrix renormalization group (DMRG) calculation. With the time reversal symmetry breaking due to the magnetic field, a gapped Kitaev spin liquid is identified for both ferromagnetic (FM) and antiferromagnetic (AFM) Kitaev couplings. The topological nature of such Kitaev spin liquid is manifested by the nearly quantized Wilson loop, degeneracy in the entanglement spectra and existence of edge modes. While the FM Kitaev spin liquid is destroyed by a weaker magnetic field $H_*^\text{FM}$, the AFM one demonstrates a robustness up to an order of magnitude larger critical field $H_*^\text{AFM}$. Moreover, an intermediate nonmagnetic phase appears only for the AFM case at larger fields, $H_*^\text{AFM} < H < H_{**}^\text{AFM}$, before the transition to a high-field polarized paramagnet. The stability of the Kitaev spin liquid against the Heisenberg interactions is also examined. Our findings may further inspire the investigation of recently proposed S=1 Kitaev materials.
We investigate the $2k_F$ density-wave instability of non-Fermi liquid states by combining exact diagonalization with renormalization group analysis. At the half-filled zeroth Landau level, we study the fate of the composite Fermi liquid in the presence of the mass anisotropy and mixed Landau level form factors. These two experimentally accessible knobs trigger a phase transition towards a unidirectional charge-density-wave state with a wavevector equal to $2k_F$ of the composite Fermi liquid. Based on exact diagonalization, we identify such a transition by examining both the energy spectra and the static structure factor of charge density-density correlations. Moreover, the renormalization group analysis reveals that gauge fluctuations render the non-Fermi liquid state unstable against density-wave orders, consistent with numerical observations. Possible experimental probes of the density-wave instability are also discussed.