arXiv subjects

Jian Sun

Publications and source records attributed to Jian Sun.

At least 361 records · Page 20Linked to original sources

arXiv2020

Content-Aware Unsupervised Deep Homography Estimation

Homography estimation is a basic image alignment method in many applications. It is usually conducted by extracting and matching sparse feature points, which are error-prone in low-light and low-texture images. On the other hand, previous deep homography approaches use either synthetic images for supervised learning or aerial images for unsupervised learning, both ignoring the importance of handling depth disparities and moving objects in real world applications. To overcome these problems, in this work we propose an unsupervised deep homography method with a new architecture design. In the spirit of the RANSAC procedure in traditional methods, we specifically learn an outlier mask to only select reliable regions for homography estimation. We calculate loss with respect to our learned deep features instead of directly comparing image content as did previously. To achieve the unsupervised training, we also formulate a novel triplet loss customized for our network. We verify our method by conducting comprehensive comparisons on a new dataset that covers a wide range of scenes with varying degrees of difficulties for the task. Experimental results reveal that our method outperforms the state-of-the-art including deep solutions and feature-based solutions.

cs.CV↗

arXiv2020

Angle-based Search Space Shrinking for Neural Architecture Search

In this work, we present a simple and general search space shrinking method, called Angle-Based search space Shrinking (ABS), for Neural Architecture Search (NAS). Our approach progressively simplifies the original search space by dropping unpromising candidates, thus can reduce difficulties for existing NAS methods to find superior architectures. In particular, we propose an angle-based metric to guide the shrinking process. We provide comprehensive evidences showing that, in weight-sharing supernet, the proposed metric is more stable and accurate than accuracy-based and magnitude-based metrics to predict the capability of child models. We also show that the angle-based metric can converge fast while training supernet, enabling us to get promising shrunk search spaces efficiently. ABS can easily apply to most of NAS approaches (e.g. SPOS, FairNAS, ProxylessNAS, DARTS and PDARTS). Comprehensive experiments show that ABS can dramatically enhance existing NAS approaches by providing a promising shrunk search space.

cs.NE↗

arXiv2020

Learning Delicate Local Representations for Multi-Person Pose Estimation

In this paper, we propose a novel method called Residual Steps Network (RSN). RSN aggregates features with the same spatial size (Intra-level features) efficiently to obtain delicate local representations, which retain rich low-level spatial information and result in precise keypoint localization. Additionally, we observe the output features contribute differently to final performance. To tackle this problem, we propose an efficient attention mechanism - Pose Refine Machine (PRM) to make a trade-off between local and global representations in output features and further refine the keypoint locations. Our approach won the 1st place of COCO Keypoint Challenge 2019 and achieves state-of-the-art results on both COCO and MPII benchmarks, without using extra training data and pretrained model. Our single model achieves 78.6 on COCO test-dev, 93.0 on MPII test dataset. Ensembled models achieve 79.2 on COCO test-dev, 77.1 on COCO test-challenge dataset. The source code is publicly available for further research at https://github.com/caiyuanhao1998/RSN/

cs.CV↗

arXiv2020

Single Path One-Shot Neural Architecture Search with Uniform Sampling

We revisit the one-shot Neural Architecture Search (NAS) paradigm and analyze its advantages over existing NAS approaches. Existing one-shot method, however, is hard to train and not yet effective on large scale datasets like ImageNet. This work propose a Single Path One-Shot model to address the challenge in the training. Our central idea is to construct a simplified supernet, where all architectures are single paths so that weight co-adaption problem is alleviated. Training is performed by uniform path sampling. All architectures (and their weights) are trained fully and equally. Comprehensive experiments verify that our approach is flexible and effective. It is easy to train and fast to search. It effortlessly supports complex search spaces (e.g., building blocks, channel, mixed-precision quantization) and different search constraints (e.g., FLOPs, latency). It is thus convenient to use for various needs. It achieves start-of-the-art performance on the large dataset ImageNet.

cs.CV↗

arXiv2020

Electron-phonon coupling and superconductivity in the doped topological-crystalline insulator (Pb$_{0.5}$Sn$_{0.5}$)$_{1-x}$In$_x$Te

We present a neutron scattering study of phonons in single crystals of (Pb$_{0.5}$Sn$_{0.5}$)$_{1-x}$In$_x$Te with $x=0$ (metallic, but nonsuperconducting) and $x=0.2$ (nonmetallic normal state, but superconducting). We map the phonon dispersions (more completely for $x=0$) and find general consistency with theoretical calculations, except for the transverse and longitudinal optical (TO and LO) modes at the Brillouin zone center. At low temperature, both modes are strongly damped but sit at a finite energy ($\sim4$ meV in both samples), shifting to higher energy at room temperature. These modes are soft due to a proximate structural instability driven by the sensitivity of Pb-Te and Sn-Te $p$-orbital hybridization to off-center displacements of the metal atoms. The impact of the soft optical modes on the low-energy acoustic modes is inferred from the low thermal conductivity, especially at low temperature. Given that the strongest electron-phonon coupling is predicted for the LO mode, which should be similar for both studied compositions, it is intriguing that only the In-doped crystal is superconducting. In addition, we observe elastic diffuse (Huang) scattering that is qualitatively explained by the difference in Pb-Te and Sn-Te bond lengths within the lattice of randomly distributed Pb and Sn sites. We also confirm the presence of anomalous diffuse low-energy atomic vibrations that we speculatively attribute to local fluctuations of individual Pb atoms between off-center sites.

cond-mat.supr-con↗

arXiv2020

Type-II Ising superconductivity and anomalous metallic state in macro-size ambient-stable ultrathin crystalline films

Recent emergence of two-dimensional (2D) crystalline superconductors has provided a promising platform to investigate novel quantum physics and potential applications. To reveal essential quantum phenomena therein, ultralow temperature transport investigation on high quality ultrathin superconducting films is critically required, although it has been quite challenging experimentally. Here we report a systematic transport study on the ultrathin crystalline PdTe2 films grown by molecular beam epitaxy (MBE). Interestingly, a new type of Ising superconductivity in 2D centrosymmetric materials is revealed by the detection of large in-plane critical field more than 7 times Pauli limit. Remarkably, in perpendicular magnetic field, we provide solid evidence of anomalous metallic state characterized by the resistance saturation at low temperatures with high quality filters. The robust superconductivity with intriguing quantum phenomena in the macro-size ambient-stable ultrathin PdTe2 films remains almost the same for 20 months, showing great potentials in electronic and spintronic applications.

cond-mat.supr-con↗

arXiv2020

A real-time multi-constraints obstacle avoidance method using LiDAR

Obstacle avoidance is one of the essential and indispensable functions for autonomous mobile robots. Most of the existing solutions are typically based on single condition constraint and cannot incorporate sensor data in a real-time manner, which often fail to respond to unexpected moving obstacles in dynamic unknown environments. In this paper, a novel real-time multi-constraints obstacle avoidance method using Light Detection and Ranging(LiDAR) is proposed, which is able to, based on the latest estimation of the robot pose and environment, find the sub-goal defined by a multi-constraints function within the explored region and plan a corresponding optimal trajectory at each time step iteratively, so that the robot approaches the goal over time. Meanwhile, at each time step, the improved Ant Colony Optimization(ACO) algorithm is also used to re-plan optimal paths from the latest robot pose to the latest defined sub-goal position. While ensuring convergence, planning in this method is done by repeated local optimizations, so that the latest sensor data from LiDAR and derived environment information can be fully utilized at each step until the robot reaches the desired position. This method facilitates real-time performance, also has little requirement on memory space or computational power due to its nature, thus our method has huge potentials to benefit small low-cost autonomous platforms. The method is evaluated against several existing technologies in both simulation and real-world experiments.

cs.RO↗

arXiv2020

Detection in Crowded Scenes: One Proposal, Multiple Predictions

We propose a simple yet effective proposal-based object detector, aiming at detecting highly-overlapped instances in crowded scenes. The key of our approach is to let each proposal predict a set of correlated instances rather than a single one in previous proposal-based frameworks. Equipped with new techniques such as EMD Loss and Set NMS, our detector can effectively handle the difficulty of detecting highly overlapped objects. On a FPN-Res50 baseline, our detector can obtain 4.9\% AP gains on challenging CrowdHuman dataset and 1.0\% $\text{MR}^{-2}$ improvements on CityPersons dataset, without bells and whistles. Moreover, on less crowed datasets like COCO, our approach can still achieve moderate improvement, suggesting the proposed method is robust to crowdedness. Code and pre-trained models will be released at https://github.com/megvii-model/CrowdDetection.

cs.CV↗

arXiv2020

Approximation algorithms for general cluster routing problem

Graph routing problems have been investigated extensively in operations research, computer science and engineering due to their ubiquity and vast applications. In this paper, we study constant approximation algorithms for some variations of the general cluster routing problem. In this problem, we are given an edge-weighted complete undirected graph $G=(V,E,c),$ whose vertex set is partitioned into clusters $C_{1},\dots ,C_{k}.$ We are also given a subset $V'$ of $V$ and a subset $E'$ of $E.$ The weight function $c$ satisfies the triangle inequality. The goal is to find a minimum cost walk $T$ that visits each vertex in $V'$ only once, traverses every edge in $E'$ at least once and for every $i\in [k]$ all vertices of $C_i$ are traversed consecutively.

cs.DS↗

arXiv2020

Online Reinforcement Learning Control by Direct Heuristic Dynamic Programming: from Time-Driven to Event-Driven

In this paper time-driven learning refers to the machine learning method that updates parameters in a prediction model continuously as new data arrives. Among existing approximate dynamic programming (ADP) and reinforcement learning (RL) algorithms, the direct heuristic dynamic programming (dHDP) has been shown an effective tool as demonstrated in solving several complex learning control problems. It continuously updates the control policy and the critic as system states continuously evolve. It is therefore desirable to prevent the time-driven dHDP from updating due to insignificant system event such as noise. Toward this goal, we propose a new event-driven dHDP. By constructing a Lyapunov function candidate, we prove the uniformly ultimately boundedness (UUB) of the system states and the weights in the critic and the control policy networks. Consequently we show the approximate control and cost-to-go function approaching Bellman optimality within a finite bound. We also illustrate how the event-driven dHDP algorithm works in comparison to the original time-driven dHDP.

eess.SY↗

arXiv2020

Structured and Localized Image Restoration

We present a novel approach to image restoration that leverages ideas from localized structured prediction and non-linear multi-task learning. We optimize a penalized energy function regularized by a sum of terms measuring the distance between patches to be restored and clean patches from an external database gathered beforehand. The resulting estimator comes with strong statistical guarantees leveraging local dependency properties of overlapping patches. We derive the corresponding algorithms for energies based on the mean-squared and Euclidean norm errors. Finally, we demonstrate the practical effectiveness of our model on different image restoration problems using standard benchmarks.

cs.LG↗

arXiv2020

Evidence for magnon-phonon coupling in the topological magnet Cu$_3$TeO$_6$

We perform thermodynamic and inelastic neutron scattering (INS) measurements to study the lattice dynamics (phonons) of a cubic collinear antiferromagnet Cu$_3$TeO$_6$ which hosts topological spin excitations (magnons). While the specific heat and thermal conductivity results show that the thermal transport is dominated by phonons, the deviation of the thermal conductivity from a pure phononic model indicates that there is a strong coupling between magnons and phonons. In the INS measurements, we find a mode in the excitation spectra at 4.5 K, which exhibits a slight downward dispersion around the Brillouin zone center. This mode disappears above the Néel temperature, and thus cannot be a phonon. Furthermore, the dispersion is distinct from that of a magnon. Instead, it can be explained by the magnon-polaron mode, which is new collective excitations resulting from the hybridization between magnons and phonons. We consider the suppression of the thermal conductivity and emergence of the magnon-polaron mode to be evidence for magnon-phonon coupling in Cu$_3$TeO$_6$.

cond-mat.str-el↗

arXiv2020

Finite-thickness effect and spin polarization of the even-denominator fractional quantum Hall states

The spin-polarized even-denominator fractional quantum Hall (FQH) states in the second Landau level (LL), i.e. 5/2 and 7/2, may possess novel quasi-particle excitations obeying non-Abelian statistics. However, the spin polarization of the 7/2 FQH state has not been investigated experimentally and the spin polarization of the 5/2 FQH state from tilted field experiments remains controversial. Using a piezo-driven sample rotator with the lowest electron temperature down to 25 mK, we studied the energy gap of the even-denominator FQH states in the second LL by precise control of the tilted angles with a resolution less than 0.1°. We observed two different energy gap dependences on the in-plane magnetic field for 5/2, 7/2, other FQH states (7/3 and 8/3) in the second LL and reentrant integer quantum Hall (RIQH) states in the third LL. Though the transition fields vary from states, their corresponding in-plane magnetic lengths are comparable to the quantum well thickness of the sample, which may result from the influence of the finite-thickness effect. At low in-plane magnetic fields, before the conjectured finite-thickness effect starts to dominate, the energy gaps of both 5/2 and 7/2 states show a non-decreasing behavior, supporting spin-polarized ground states. Our results also suggest that the 7/3, 8/3 FQH states, and the RIQH states in the third LL are spin-polarized or partially spin-polarized.

cond-mat.mes-hall↗

arXiv2020

Ferromagnetic MnSn monolayer epitaxially grown on silicon substrate

Two-dimensional (2D) ferromagnetic materials have been exhibiting promising potential in applications, such as spintronics devices. To grow epitaxial magnetic films on silicon substrate, in the single-layer limit, is practically important but challenging. In this study, we realized the epitaxial growth of MnSn monolayer on Si(111) substrate, with an atomically thin Sn/Si(111)-$2\sqrt{3}\times2\sqrt{3}$- buffer layer, and controlled the MnSn thickness with atomic-layer precision. We discovered the ferromagnetism in MnSn monolayer with the Curie temperature (Tc) of ~54 K. As the MnSn film is grown to 4 monolayers, Tc increases accordingly to ~235 K. The lattice of the epitaxial MnSn monolayer as well as the Sn/Si(111)-$2\sqrt{3}\times2\sqrt{3}$ is perfectly compatible with silicon, and thus an sharp interface is formed between MnSn, Sn and Si. This system provides a new platform for exploring the 2D ferromagnetism, integrating magnetic monolayers into silicon-based technology, and engineering the spintronics heterostructures.

cond-mat.mtrl-sci↗

arXiv2020

Gauss-Newton Unrolled Neural Networks and Data-driven Priors for Regularized PSSE with Robustness

Distributed renewable generation, elastic loads, and purposeful manipulation of meter readings challenge the monitoring and control of today's power systems (PS). In this context, to maintain a comprehensive view of the system in real time, fast and robust state estimation (SE) methods are urgently needed. Conventional PSSE solvers typically entail minimizing a nonlinear and nonconvex least-squares by e.g., the workhorse Gauss-Newton method. Those iterative solvers however, are sensitive to initialization and may get stuck in local minima. To overcome these hurdles and inspired by recent image denoising techniques, this paper advocates a learnable regularization term for PSSE that uses a deep neural network (DNN) prior. For the resultant regularized PSSE problem, a "Gauss-Newton-like" alternating minimization solver is first developed. To accommodate real-time monitoring, a novel end-to-end DNN is constructed by unrolling the proposed alternating minimization solver. Interestingly, the power network topology can be easily incorporated into the DNN by designing a graph neural network (GNN) based prior. To further endow the physics-based DNN with robustness against bad data, an adversarial DNN training method is discussed. Numerical tests using real load data on the IEEE $118$-bus benchmark system showcase the improved estimation and robustness performance of the proposed scheme compared with several state-of-the-art alternatives.

eess.SY↗

arXiv2020

Dynamic Memory Induction Networks for Few-Shot Text Classification

This paper proposes Dynamic Memory Induction Networks (DMIN) for few-shot text classification. The model utilizes dynamic routing to provide more flexibility to memory-based few-shot learning in order to better adapt the support sets, which is a critical capacity of few-shot classification models. Based on that, we further develop induction models with query information, aiming to enhance the generalization ability of meta-learning. The proposed model achieves new state-of-the-art results on the miniRCV1 and ODIC dataset, improving the best performance (accuracy) by 2~4%. Detailed analysis is further performed to show the effectiveness of each component.

cs.CL↗

arXiv2020

Power Cyber-Physical System Risk Area Prediction Using Dependent Markov Chain and Improved Grey Wolf Optimization

Existing power cyber-physical system (CPS) risk prediction results are inaccurate as they fail to reflect the actual physical characteristics of the components and the specific operational status. A new method based on dependent Markov chain for power CPS risk area prediction is proposed in this paper. The load and constraints of the non-uniform power CPS coupling network are first characterized, and can be utilized as a node state judgment standard. Considering the component node isomerism and interdependence between the coupled networks, a power CPS risk regional prediction model based on dependent Markov chain is then constructed. A cross-adaptive gray wolf optimization algorithm improved by adaptive position adjustment strategy and cross-optimal solution strategy is subsequently developed to optimize the prediction model. Simulation results using the IEEE 39-BA 110 test system verify the effectiveness and superiority of the proposed method.

cs.NI↗

arXiv2020

Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization

Batch Normalization (BN) is one of the most widely used techniques in Deep Learning field. But its performance can awfully degrade with insufficient batch size. This weakness limits the usage of BN on many computer vision tasks like detection or segmentation, where batch size is usually small due to the constraint of memory consumption. Therefore many modified normalization techniques have been proposed, which either fail to restore the performance of BN completely, or have to introduce additional nonlinear operations in inference procedure and increase huge consumption. In this paper, we reveal that there are two extra batch statistics involved in backward propagation of BN, on which has never been well discussed before. The extra batch statistics associated with gradients also can severely affect the training of deep neural network. Based on our analysis, we propose a novel normalization method, named Moving Average Batch Normalization (MABN). MABN can completely restore the performance of vanilla BN in small batch cases, without introducing any additional nonlinear operations in inference procedure. We prove the benefits of MABN by both theoretical analysis and experiments. Our experiments demonstrate the effectiveness of MABN in multiple computer vision tasks including ImageNet and COCO. The code has been released in https://github.com/megvii-model/MABN.

cs.CV↗