With the recent advancement of deep convolutional neural networks, significant progress has been made in general face recognition. However, the state-of-the-art general face recognition models do not generalize well to occluded face images, which are
exactly the common cases in real-world scenarios. The potential reasons are the absences of large-scale occluded face data for training and specific designs for tackling corrupted features brought by occlusions. This paper presents a novel face recognition method that is robust to occlusions based on a single end-to-end deep neural network. Our approach, named FROM (Face Recognition with Occlusion Masks), learns to discover the corrupted features from the deep convolutional neural networks, and clean them by the dynamically learned masks. In addition, we construct massive occluded face images to train FROM effectively and efficiently. FROM is simple yet powerful compared to the existing methods that either rely on external detectors to discover the occlusions or employ shallow models which are less discriminative. Experimental results on the LFW, Megaface challenge 1, RMF2, AR dataset and other simulated occluded/masked datasets confirm that FROM dramatically improves the accuracy under occlusions, and generalizes well on general face recognition.
With the recent success of deep neural networks, remarkable progress has been achieved on face recognition. However, collecting large-scale real-world training data for face recognition has turned out to be challenging, especially due to the label no
ise and privacy issues. Meanwhile, existing face recognition datasets are usually collected from web images, lacking detailed annotations on attributes (e.g., pose and expression), so the influences of different attributes on face recognition have been poorly investigated. In this paper, we address the above-mentioned issues in face recognition using synthetic face images, i.e., SynFace. Specifically, we first explore the performance gap between recent state-of-the-art face recognition models trained with synthetic and real face images. We then analyze the underlying causes behind the performance gap, e.g., the poor intra-class variations and the domain gap between synthetic and real face images. Inspired by this, we devise the SynFace with identity mixup (IM) and domain mixup (DM) to mitigate the above performance gap, demonstrating the great potentials of synthetic data for face recognition. Furthermore, with the controllable face synthesis model, we can easily manage different factors of synthetic face generation, including pose, expression, illumination, the number of identities, and samples per identity. Therefore, we also perform a systematically empirical analysis on synthetic face images to provide some insights on how to effectively utilize synthetic data for face recognition.
Soon after its theoretical prediction, striped-density states in the presence of synthetic spin-orbit coupling were realized in Bose-Einstein condensates of ultracold neutral atoms [J.-R. Li et al., Nature textbf{543}, 91 (2017)]. The achievement ope
ns avenues to explore the interplay of superfluidity and crystalline order in the search for supersolid features and materials. The system considered is essentially made of two linearly coupled Bose-Einstein condensates, that is a pseudo-spin-$1/2$ system, subject to a spin-dependent gauge field $sigma_z hbar k_ell$. Under these conditions the stripe phase is achieved when the linear coupling $hbarOmega/2$ is small against the gauge energy $mOmega/hbar k_ell^2<1$ . The resulting density stripes have been interpreted as a standing-wave, interference pattern with approximate wavenumber $2k_ell$. Here, we show that the emergence of the stripe phase is induced by an array of Josephson vortices living in the junction defined by the linear coupling. As happens in superconducting junctions subject to external magnetic fields, a vortex array is the natural response of the superfluid system to the presence of a gauge field. Also similar to superconductors, the Josephson currents and their associated vortices can be present as a metastable state in the absence of gauge field. We provide closed-form solutions to the 1D mean field equations that account for such vortex arrays. The underlying Josephson currents coincide with the analytical solutions to the sine-Gordon equation for the relative phase of superconducting junctions [C. Owen and D. Scalapino, Phys. Rev. textbf{164}, 538 (1967)].
Phase engineering techniques are used to control the dynamics of long-bosonic-Josephson-junction arrays built by linearly coupling Bose-Einstein condensates. Just at the middle point of the underlying discrete energy band of the system, unlocked-rela
tive-phase states are shown to be stationary along with the locked-relative-phase Bloch waves. In finite, experimentally-feasible systems, such states find ranges of dynamical stability that depend on the ratio of coupling to interaction energy. The same ratio determines different decay regimes, which include the recurrence of staggered-soliton trains in the condensates around Josephson loop currents at the junctions. These transient solitons are also found in their stationary configurations, which provide striped-density states by means of either dark-soliton or bright-soliton trains. Additionally, the preparation of maximally out-of-phase (or splay) states is demonstrated to evolve into an oscillation of the uniform density of the condensates that keeps constant the total density of the system and robust against noise at low coupling.
We present an approach to recover absolute 3D human poses from multi-view images by incorporating multi-view geometric priors in our model. It consists of two separate steps: (1) estimating the 2D poses in multi-view images and (2) recovering the 3D
poses from the multi-view 2D poses. First, we introduce a cross-view fusion scheme into CNN to jointly estimate 2D poses for multiple views. Consequently, the 2D pose estimation for each view already benefits from other views. Second, we present a recursive Pictorial Structure Model to recover the 3D pose from the multi-view 2D poses. It gradually improves the accuracy of 3D pose with affordable computational cost. We test our method on two public datasets H36M and Total Capture. The Mean Per Joint Position Errors on the two datasets are 26mm and 29mm, which outperforms the state-of-the-arts remarkably (26mm vs 52mm, 29mm vs 35mm). Our code is released at url{https://github.com/microsoft/multiview-human-pose-estimation-pytorch}.
We study the time evolution of two coupled many-body quantum systems one of which is assumed to be Bose condensed. Specifically, we consider two ultracold atomic clouds populating each two localized single-particle states, i.e. a two-component Bosoni
c Josephson junction. The cold atoms cloud can retain its coherence when coupled to the condensate and displays synchronization with the latter, differing from usual entrainment. We term this effect among the ultracold and the condensed clouds as {it hybrid synchronization}. The onset of synchronization, which we observe in the evolution of average properties of both gases when increasing their coupling, is found to be related to the many-body properties of the quantum gas, e.g. condensed fraction, quantum fluctuations of the particle number differences. We discuss the effects of different initial preparations, the influence of unequal particle numbers for the two clouds, and explore the dependence on the initial quantum state, e.g. coherent state, squeezed state and Fock state, finding essentially the same phenomenology in all cases.
Measure synchronization (MS) in a two-species bosonic Josephson junction (BJJ) is studied based on semi-classical theory. Six different scenarios for MS, including two in the Josephson oscillation regime (0 phase mode) and four in the self-trapping r
egime ($pi$ phase mode), have been clearly shown. Systematic investigations of the common features behind these different scenarios have been performed. We show that the average energies of the two species merge at the MS transition point. The scaling of the power law near the MS transition has been verified, and the critical exponent is 1/2 for all of the different scenarios for MS. We also illustrate MS in a three-dimensional phase space; from this illustration, more detailed information on the dynamical process can be obtained. Particularly, by analyzing the Poincare sections with changing interspecies interactions, we find that the two-species BJJ exhibits separatrix crossing behavior at MS transition point, and such behavior depicts the general mechanism behind the different scenarios for the MS transitions. The new critical behavior found in a two-species BJJ is expected to be found in real systems of atomic Bose gases.
We present a theory to describe domain formation observed very recently in a quenched Rb-87 gas, a typical ferromagnetic spinor Bose system. An overlap factor is introduced to characterize the symmetry breaking of M_F=pm 1 components for the F=1 ferr
omagnetic condensate. We demonstrate that the domain formation is a co-effect of the quantum coherence and the thermal relaxation. A thermally enhanced quantum-oscillation is observed during the dynamical process of the domain formation. And the spatial separation of domains leads to significant decay of the M_F=0 component fraction in an initial M_F=0 condensate.
