arXiv subjects

Lei Chen

Publications and source records attributed to Lei Chen.

At least 541 records · Page 30Linked to original sources

arXiv2020

Semi-Anchored Detector for One-Stage Object Detection

A standard one-stage detector is comprised of two tasks: classification and regression. Anchors of different shapes are introduced for each location in the feature map to mitigate the challenge of regression for multi-scale objects. However, the performance of classification can degrade due to the highly class-imbalanced problem in anchors. Recently, many anchor-free algorithms have been proposed to classify locations directly. The anchor-free strategy benefits the classification task but can lead to sup-optimum for the regression task due to the lack of prior bounding boxes. In this work, we propose a semi-anchored framework. Concretely, we identify positive locations in classification, and associate multiple anchors to the positive locations in regression. With ResNet-101 as the backbone, the proposed semi-anchored detector achieves 43.6% mAP on COCO data set, which demonstrates the state-of-art performance among one-stage detectors.

cs.CV↗

arXiv2020

Fragile Insulator and Electronic Nematicity in a Graphene Moire System

Strongly correlated quantum matter exhibits a rich variety of remarkable properties, but the organizing principles that underlie the behavior remain to be established. Graphene heterostructures, which can host narrow moire electron bands that amplify the correlation effect, represent a new setting to make progress on this overarching issue. In such correlated moire systems, an insulating state is a prominent feature of the phase diagram and may hold the key to understanding the basic physics. Here we advance the notion of a fragile insulator, a correlation-driven insulating state that is on the verge of a delocalization transition into a bad metal. Using a realistic multiorbital Hubbard model as a prototype for narrow band moire systems, we realize such a fragile insulator and demonstrate a nematic order in this state as well as in the nearby bad metal regime. Our results are consistent with the observed electronic anisotropy in the graphene moire systems and provide a natural understanding of what happens when the insulator is tuned into a bad metal. We propose the fragile insulator and the accompanying bad metal as competing states at integer fillings that analogously anchor the overall phase diagram of the correlated moire systems and beyond.

cond-mat.str-el↗

arXiv2020

DDSL: Efficient Subgraph Listing on Distributed and Dynamic Graphs

Subgraph listing is a fundamental problem in graph theory and has wide applications in areas like sociology, chemistry, and social networks. Modern graphs can usually be large-scale as well as highly dynamic, which challenges the efficiency of existing subgraph listing algorithms. Recent works have shown the benefits of partitioning and processing big graphs in a distributed system, however, there is only few work targets subgraph listing on dynamic graphs in a distributed environment. In this paper, we propose an efficient approach, called Distributed and Dynamic Subgraph Listing (DDSL), which can incrementally update the results instead of running from scratch. DDSL follows a general distributed join framework. In this framework, we use a Neighbor-Preserved storage for data graphs, which takes bounded extra space and supports dynamic updating. After that, we propose a comprehensive cost model to estimate the I/O cost of listing subgraphs. Then based on this cost model, we develop an algorithm to find the optimal join tree for a given pattern. To handle dynamic graphs, we propose an efficient left-deep join algorithm to incrementally update the join results. Extensive experiments are conducted on real-world datasets. The results show that DDSL outperforms existing methods in dealing with both static dynamic graphs in terms of the responding time.

cs.DB↗

arXiv2020

Multi-View Self-Attention for Interpretable Drug-Target Interaction Prediction

The drug discovery stage is a vital aspect of the drug development process and forms part of the initial stages of the development pipeline. In recent times, machine learning-based methods are actively being used to model drug-target interactions for rational drug discovery due to the successful application of these methods in other domains. In machine learning approaches, the numerical representation of molecules is critical to the performance of the model. While significant progress has been made in molecular representation engineering, this has resulted in several descriptors for both targets and compounds. Also, the interpretability of model predictions is a vital feature that could have several pharmacological applications. In this study, we propose a self-attention-based multi-view representation learning approach for modeling drug-target interactions. We evaluated our approach using three benchmark kinase datasets and compared the proposed method to some baseline models. Our experimental results demonstrate the ability of our method to achieve competitive prediction performance and offer biologically plausible drug-target interaction interpretations.

cs.LG↗

arXiv2020

Perfect Absorption in Complex Scattering Systems with or without Hidden Symmetries

Wavefront shaping (WFS) schemes for efficient energy deposition in weakly lossy targets is an ongoing challenge for many classical wave technologies relevant to next-generation telecommunications, long-range wireless power transfer, and electromagnetic warfare. In many circumstances these targets are embedded inside complicated enclosures which lack any type of (geometric or hidden) symmetry, such as complex networks, buildings, or vessels, where the hypersensitive nature of multiple interference paths challenges the viability of WFS protocols. We demonstrate the success of a new and general WFS scheme, based on coherent perfect absorption (CPA) electromagnetic protocols, by utilizing a network of coupled transmission lines with complex connectivity that enforces the absence of geometric symmetries. Our platform allows for control of the local losses inside the network and of the violation of time-reversal symmetry via a magnetic field; thus establishing CPA beyond its initial concept as the time-reversal of a laser cavity, while offering an opportunity for better insight into CPA formation via the implementation of semiclassical tools.

cond-mat.dis-nn↗

arXiv2020

SPL-MLL: Selecting Predictable Landmarks for Multi-Label Learning

Although significant progress achieved, multi-label classification is still challenging due to the complexity of correlations among different labels. Furthermore, modeling the relationships between input and some (dull) classes further increases the difficulty of accurately predicting all possible labels. In this work, we propose to select a small subset of labels as landmarks which are easy to predict according to input (predictable) and can well recover the other possible labels (representative). Different from existing methods which separate the landmark selection and landmark prediction in the 2-step manner, the proposed algorithm, termed Selecting Predictable Landmarks for Multi-Label Learning (SPL-MLL), jointly conducts landmark selection, landmark prediction, and label recovery in a unified framework, to ensure both the representativeness and predictableness for selected landmarks. We employ the Alternating Direction Method (ADM) to solve our problem. Empirical studies on real-world datasets show that our method achieves superior classification performance over other state-of-the-art methods.

cs.CV↗

arXiv2020

From pure braid groups to hyperbolic groups

In this note we show that any homomorphism from a pure surface braid group to a torsion-free hyperbolic group either has a cyclic image or factors through a forgetful map. This extends and gives a new proof of an earlier result of the author which works only when the target is a free group or a surface group. We also prove a similar rigidity result for the pure braid group of the disk.

math.GT↗

arXiv2020

Miniaturization of the Superconducting Memory Cell via a Three-Dimensional Nb Nano-Superconducting Quantum Interference Device

Scalable memories that can match the speeds of superconducting logic circuits have long been desired to enable a superconducting computer. A superconducting loop that includes a Josephson junction can store a flux quantum state in picoseconds. However, the requirement for the loop inductance to create a bi-state hysteresis sets a limit on the minimal area occupied by a single memory cell. Here, we present a miniaturized superconducting memory cell based on a Three-Dimensional (3D) Nb nano-Superconducting QUantum Interference Device (nano-SQUID). The major cell area here fits within an 8*9 μm^2 rectangle with a cross-selected function for memory implementation. The cell shows periodic tunable hysteresis between two neighbouring flux quantum states produced by bias current sweeping because of the large modulation depth of the 3D nano-SQUID (~66%). Furthermore, the measured Current-Phase Relations (CPRs) of nano-SQUIDs are shown to be skewed from a sine function, as predicted by theoretical modelling. The skewness and the critical current of 3D nano-SQUIDs are linearly correlated. It is also found that the hysteresis loop size is in a linear scaling relationship with the CPR skewness using the statistics from characterisation of 26 devices. We show that the CPR skewness range of π/4~3π/4 is equivalent to a large loop inductance in creating a stable bi-state hysteresis for memory implementation. Therefore, the skewed CPR of 3D nano-SQUID enables further superconducting memory cell miniaturization by overcoming the inductance limitation of the loop area.

cond-mat.mes-hall↗

arXiv2020

Noise-Sampling Cross Entropy Loss: Improving Disparity Regression Via Cost Volume Aware Regularizer

Recent end-to-end deep neural networks for disparity regression have achieved the state-of-the-art performance. However, many well-acknowledged specific properties of disparity estimation are omitted in these deep learning algorithms. Especially, matching cost volume, one of the most important procedure, is treated as a normal intermediate feature for the following softargmin regression, lacking explicit constraints compared with those traditional algorithms. In this paper, inspired by previous canonical definition of cost volume, we propose the noise-sampling cross entropy loss function to regularize the cost volume produced by deep neural networks to be unimodal and coherent. Extensive experiments validate that the proposed noise-sampling cross entropy loss can not only help neural networks learn more informative cost volume, but also lead to better stereo matching performance compared with several representative algorithms.

cs.CV↗

arXiv2020

Learning to Transfer Graph Embeddings for Inductive Graph based Recommendation

With the increasing availability of videos, how to edit them and present the most interesting parts to users, i.e., video highlight, has become an urgent need with many broad applications. As users'visual preferences are subjective and vary from person to person, previous generalized video highlight extraction models fail to tailor to users' unique preferences. In this paper, we study the problem of personalized video highlight recommendation with rich visual content. By dividing each video into non-overlapping segments, we formulate the problem as a personalized segment recommendation task with many new segments in the test stage. The key challenges of this problem lie in: the cold-start users with limited video highlight records in the training data and new segments without any user ratings at the test stage. In this paper, we propose an inductive Graph based Transfer learning framework for personalized video highlight Recommendation (TransGRec). TransGRec is composed of two parts: a graph neural network followed by an item embedding transfer network. Specifically, the graph neural network part exploits the higher-order proximity between users and segments to alleviate the user cold-start problem. The transfer network is designed to approximate the learned item embeddings from graph neural networks by taking each item's visual content as input, in order to tackle the new segment problem in the test phase. We design two detailed implementations of the transfer learning optimization function, and we show how the two parts of TransGRec can be efficiently optimized with different transfer learning optimization functions. Extensive experimental results on a real-world dataset clearly show the effectiveness of our proposed model.

cs.IR↗

arXiv2020

DR Loss: Improving Object Detection by Distributional Ranking

Most of object detection algorithms can be categorized into two classes: two-stage detectors and one-stage detectors. Recently, many efforts have been devoted to one-stage detectors for the simple yet effective architecture. Different from two-stage detectors, one-stage detectors aim to identify foreground objects from all candidates in a single stage. This architecture is efficient but can suffer from the imbalance issue with respect to two aspects: the inter-class imbalance between the number of candidates from foreground and background classes and the intra-class imbalance in the hardness of background candidates, where only a few candidates are hard to be identified. In this work, we propose a novel distributional ranking (DR) loss to handle the challenge. For each image, we convert the classification problem to a ranking problem, which considers pairs of candidates within the image, to address the inter-class imbalance problem. Then, we push the distributions of confidence scores for foreground and background towards the decision boundary. After that, we optimize the rank of the expectations of derived distributions in lieu of original pairs. Our method not only mitigates the intra-class imbalance issue in background candidates but also improves the efficiency for the ranking algorithm. By merely replacing the focal loss in RetinaNet with the developed DR loss and applying ResNet-101 as the backbone, mAP of the single-scale test on COCO can be improved from 39.1% to 41.7% without bells and whistles, which demonstrates the effectiveness of the proposed loss function. Code is available at \url{https://github.com/idstcv/DR_loss}.

cs.CV↗

arXiv2020

STAS: Adaptive Selecting Spatio-Temporal Deep Features for Improving Bias Correction on Precipitation

Numerical Weather Prediction (NWP) can reduce human suffering by predicting disastrous precipitation in time. A commonly-used NWP in the world is the European Centre for medium-range weather forecasts (EC). However, it is necessary to correct EC forecast through Bias Correcting on Precipitation (BCoP) since we still have not fully understood the mechanism of precipitation, making EC often have some biases. The existing BCoPs suffers from limited prior data and the fixed Spatio-Temporal (ST) scale. We thus propose an end-to-end deep-learning BCoP model named Spatio-Temporal feature Auto-Selective (STAS) model to select optimal ST regularity from EC via the ST Feature-selective Mechanisms (SFM/TFM). Given different input features, these two mechanisms can automatically adjust the spatial and temporal scales for correcting. Experiments on an EC public dataset indicate that compared with 8 published BCoP methods, STAS shows state-of-the-art performance on several criteria of BCoP, named threat scores (TS). Further, ablation studies justify that the SFM/TFM indeed work well in boosting the performance of BCoP, especially on the heavy precipitation.

cs.LG↗

arXiv2020

U-Net Using Stacked Dilated Convolutions for Medical Image Segmentation

This paper proposes a novel U-Net variant using stacked dilated convolutions for medical image segmentation (SDU-Net). SDU-Net adopts the architecture of vanilla U-Net with modifications in the encoder and decoder operations (an operation indicates all the processing for feature maps of the same resolution). Unlike vanilla U-Net which incorporates two standard convolutions in each encoder/decoder operation, SDU-Net uses one standard convolution followed by multiple dilated convolutions and concatenates all dilated convolution outputs as input to the next operation. Experiments showed that SDU-Net outperformed vanilla U-Net, attention U-Net (AttU-Net), and recurrent residual U-Net (R2U-Net) in all four tested segmentation tasks while using parameters around 40% of vanilla U-Net's, 17% of AttU-Net's, and 15% of R2U-Net's.

eess.IV↗

arXiv2020

Consistent and Complementary Graph Regularized Multi-view Subspace Clustering

This study investigates the problem of multi-view clustering, where multiple views contain consistent information and each view also includes complementary information. Exploration of all information is crucial for good multi-view clustering. However, most traditional methods blindly or crudely combine multiple views for clustering and are unable to fully exploit the valuable information. Therefore, we propose a method that involves consistent and complementary graph-regularized multi-view subspace clustering (GRMSC), which simultaneously integrates a consistent graph regularizer with a complementary graph regularizer into the objective function. In particular, the consistent graph regularizer learns the intrinsic affinity relationship of data points shared by all views. The complementary graph regularizer investigates the specific information of multiple views. It is noteworthy that the consistent and complementary regularizers are formulated by two different graphs constructed from the first-order proximity and second-order proximity of multiple views, respectively. The objective function is optimized by the augmented Lagrangian multiplier method in order to achieve multi-view clustering. Extensive experiments on six benchmark datasets serve to validate the effectiveness of the proposed method over other state-of-the-art multi-view clustering methods.

cs.LG↗

arXiv2020

Globally optimal consensus maximization for robust visual inertial localization in point and line map

Map based visual inertial localization is a crucial step to reduce the drift in state estimation of mobile robots. The underlying problem for localization is to estimate the pose from a set of 3D-2D feature correspondences, of which the main challenge is the presence of outliers, especially in changing environment. In this paper, we propose a robust solution based on efficient global optimization of the consensus maximization problem, which is insensitive to high percentage of outliers. We first introduce translation invariant measurements (TIMs) for both points and lines to decouple the consensus maximization problem into rotation and translation subproblems, allowing for a two-stage solver with reduced solution dimensions. Then we show that (i) the rotation can be calculated by minimizing TIMs using only 1-dimensional branch-and-bound (BnB), (ii) the translation can be found by running 1-dimensional search for three times with prioritized progressive voting. Compared with the popular randomized solver, our solver achieves deterministic global convergence without depending on an initial value. While compared with existing BnB based methods, ours is exponentially faster. Finally, by evaluating the performance on both simulation and real-world datasets, our approach gives accurate pose even when there are 90\% outliers (only 2 inliers).

cs.RO↗

arXiv2020

There are no exotic actions of diffeomorphism groups on 1-manifolds

Let $M$ be a manifold, $N$ a 1-dimensional manifold. Assuming $r \neq \dim(M)+1$, we show that any nontrivial homomorphism $ρ: \text{Diff}^r_c(M)\to \text{Homeo}(N)$ has a standard form: necessarily $M$ is $1$-dimensional, and there are countably many embeddings $ϕ_i: M\to N$ with disjoint images such that the action of $ρ$ is conjugate (via the product of the $ϕ_i$) to the diagonal action of $\text{Diff}^r_c(M)$ on $M \times M \times ...$ on $\bigcup_i ϕ_i(M)$, and trivial elsewhere. This solves a conjecture of Matsumoto. We also show that the groups $\text{Diff}^r_c(M)$ have no countable index subgroups.

math.GT↗

arXiv2020

CoinMagic: A Differential Privacy Framework for Ring Signature Schemes

By allowing users to obscure their transactions via including "mixins" (chaff coins), ring signature schemes have been widely used to protect a sender's identity of a transaction in privacy-preserving blockchain systems, like Monero and Bytecoin. However, recent works point out that the existing ring signature scheme is vulnerable to the "chain-reaction" analysis (i.e., the spent coin in a given ring signature can be deduced through elimination). Especially, when the diversity of mixins is low, the spent coin will have a high risk to be detected. To overcome the weakness, the ring signature should be consisted of a set of mixins with high diversity and produce observations having "similar" distributions for any two coins. In this paper, we propose a notion, namely $ε$-coin-indistinguishability ($ε$-CI), to formally define the "similar" distribution guaranteed through a differential privacy scheme. Then, we formally define the CI-aware mixins selection problem with disjoint-superset constraint (CIA-MS-DS), which aims to find a mixin set that has maximal diversity and satisfies the constraints of $ε$-CI and the budget. In CIA-MS-DS, each ring signature is either disjoint with or the superset of its preceding ring signatures. We prove that CIA-MS-DS is NP-hard and thus intractable. To solve the CIA-MS-DS problem, we propose two approximation algorithms, namely the Progressive Algorithm and the Game Theoretic Algorithm, with theoretic guarantees. Through extensive experiments on both real data sets and synthetic data sets, we demonstrate the efficiency and the effectiveness of our approaches.

cs.CR↗

arXiv2020

Global fixed points of mapping class group actions and a theorem of Markovic

We give a short and elementary proof of the non-realizability of the mapping class group via homeomorphisms. This was originally established by Markovic, resolving a conjecture of Thurston. With the tools established in this paper, we also obtain some rigidity results for actions of the mapping class group on Euclidean spaces.

math.GT↗