arXiv subjects

Xin Jin

Publications and source records attributed to Xin Jin.

At least 379 records · Page 21Linked to original sources

arXiv2020

Strange hidden-charm tetraquarks in constituent quark models

Inspired by the newly reported $Z_{cs}(3985)^{-}$ by the BESIII Collaboration, we systematically investigate the strange hidden-charm tetraquark systems $cs\bar{c}\bar{u}$ with two structures: meson-meson and diquark-antidiquark. Two quark models: the chiral quark model (ChQM) and the quark delocalization color screening model (QDCSM) are used here. Similar results are obtained in both two quark models. There is no any bound state in either ChQM or QDCSM, which excludes the molecular state explanation ($D_{s}D^{*}/D_{s}^{*}D/D_{s}^{*}D^{*}$) of the reported $Z_{cs}(3985)^{-}$. However, the effective potentials for the diquark-antidiquark $cs\bar{c}\bar{u}$ systems shows the possibility of some resonance states with mass range of $3916.5\sim 3964.6$ MeV for $IJ^{P}=\frac{1}{2} 0^{+}$, $4008.8\sim 4091.2$ MeV for $IJ^{P}=\frac{1}{2} 1^{+}$, $4246.8\sim 4418.1$ MeV for $IJ^{P}=\frac{1}{2} 2^{+}$. So the observed $Z_{cs}(3985)^{-}$ state is possible to be explained as a compact resonance state composed of $cs\bar{c}\bar{u}$ with $IJ^{P}=\frac{1}{2} 0^{+}$ or $IJ^{P}=\frac{1}{2} 1^{+}$. The study of the scattering process of corresponding open channels is under way to check this conclusion.

hep-ph↗

arXiv2020

Multi-level Chaotic Maps for 3D Textured Model Encryption

With rapid progress of Virtual Reality and Augmented Reality technologies, 3D contents are the next widespread media in many applications. Thus, the protection of 3D models is primarily important. Encryption of 3D models is essential to maintain confidentiality. Previous work on encryption of 3D surface model often consider the point clouds, the meshes and the textures individually. In this work, a multi-level chaotic maps models for 3D textured encryption was presented by observing the different contributions for recognizing cipher 3D models between vertices (point cloud), polygons and textures. For vertices which make main contribution for recognizing, we use high level 3D Lu chaotic map to encrypt them. For polygons and textures which make relatively smaller contributions for recognizing, we use 2D Arnold's cat map and 1D Logistic map to encrypt them, respectively. The experimental results show that our method can get similar performance with the other method use the same high level chaotic map for point cloud, polygons and textures, while we use less time. Besides, our method can resist more method of attacks such as statistic attack, brute-force attack, correlation attack.

cs.CV↗

arXiv2020

Deep Multimodality Learning for UAV Video Aesthetic Quality Assessment

Despite the growing number of unmanned aerial vehicles (UAVs) and aerial videos, there is a paucity of studies focusing on the aesthetics of aerial videos that can provide valuable information for improving the aesthetic quality of aerial photography. In this article, we present a method of deep multimodality learning for UAV video aesthetic quality assessment. More specifically, a multistream framework is designed to exploit aesthetic attributes from multiple modalities, including spatial appearance, drone camera motion, and scene structure. A novel specially designed motion stream network is proposed for this new multistream framework. We construct a dataset with 6,000 UAV video shots captured by drone cameras. Our model can judge whether a UAV video was shot by professional photographers or amateurs together with the scene type classification. The experimental results reveal that our method outperforms the video classification methods and traditional SVM-based methods for video aesthetics. In addition, we present three application examples of UAV video grading, professional segment detection and aesthetic-based UAV path planning using the proposed method.

cs.CV↗

arXiv2020

RackSched: A Microsecond-Scale Scheduler for Rack-Scale Computers (Technical Report)

Low-latency online services have strict Service Level Objectives (SLOs) that require datacenter systems to support high throughput at microsecond-scale tail latency. Dataplane operating systems have been designed to scale up multi-core servers with minimal overhead for such SLOs. However, as application demands continue to increase, scaling up is not enough, and serving larger demands requires these systems to scale out to multiple servers in a rack. We present RackSched, the first rack-level microsecond-scale scheduler that provides the abstraction of a rack-scale computer (i.e., a huge server with hundreds to thousands of cores) to an external service with network-system co-design. The core of RackSched is a two-layer scheduling framework that integrates inter-server scheduling in the top-of-rack (ToR) switch with intra-server scheduling in each server. We use a combination of analytical results and simulations to show that it provides near-optimal performance as centralized scheduling policies, and is robust for both low-dispersion and high-dispersion workloads. We design a custom switch data plane for the inter-server scheduler, which realizes power-of-k-choices, ensures request affinity, and tracks server loads accurately and efficiently. We implement a RackSched prototype on a cluster of commodity servers connected by a Barefoot Tofino switch. End-to-end experiments on a twelve-server testbed show that RackSched improves the throughput by up to 1.44x, and scales out the throughput near linearly, while maintaining the same tail latency as one server until the system is saturated.

cs.DC↗

arXiv2020

A Deep Drift-Diffusion Model for Image Aesthetic Score Distribution Prediction

The task of aesthetic quality assessment is complicated due to its subjectivity. In recent years, the target representation of image aesthetic quality has changed from a one-dimensional binary classification label or numerical score to a multi-dimensional score distribution. According to current methods, the ground truth score distributions are straightforwardly regressed. However, the subjectivity of aesthetics is not taken into account, that is to say, the psychological processes of human beings are not taken into consideration, which limits the performance of the task. In this paper, we propose a Deep Drift-Diffusion (DDD) model inspired by psychologists to predict aesthetic score distribution from images. The DDD model can describe the psychological process of aesthetic perception instead of traditional modeling of the results of assessment. We use deep convolution neural networks to regress the parameters of the drift-diffusion model. The experimental results in large scale aesthetic image datasets reveal that our novel DDD model is simple but efficient, which outperforms the state-of-the-art methods in aesthetic score distribution prediction. Besides, different psychological processes can also be predicted by our model.

cs.CV↗

arXiv2020

Grid-Interactive Multi-Zone Building Control Using Reinforcement Learning with Global-Local Policy Search

In this paper, we develop a grid-interactive multi-zone building controller based on a deep reinforcement learning (RL) approach. The controller is designed to facilitate building operation during normal conditions and demand response events, while ensuring occupants comfort and energy efficiency. We leverage a continuous action space RL formulation, and devise a two-stage global-local RL training framework. In the first stage, a global fast policy search is performed using a gradient-free RL algorithm. In the second stage, a local fine-tuning is conducted using a policy gradient method. In contrast to the state-of-the-art model predictive control (MPC) approach, the proposed RL controller does not require complex computation during real-time operation and can adapt to non-linear building models. We illustrate the controller performance numerically using a five-zone commercial building.

eess.SY↗

arXiv2020

CaseNet: Content-Adaptive Scale Interaction Networks for Scene Parsing

Objects at different spatial positions in an image exhibit different scales. Adaptive receptive fields are expected to capture suitable ranges of context for accurate pixel level semantic prediction. Recently, atrous convolution with different dilation rates has been used to generate features of multi-scales through several branches which are then fused for prediction. However, there is a lack of explicit interaction among the branches of different scales to adaptively make full use of the contexts. In this paper, we propose a Content-Adaptive Scale Interaction Network (CASINet) to exploit the multi-scale features for scene parsing. We build CASINet based on the classic Atrous Spatial Pyramid Pooling (ASPP) module, followed by a proposed contextual scale interaction (CSI) module, and a scale adaptation (SA) module. Specifically, in the CSI module, for each spatial position of some scale, instead of being limited by a fixed set of convolutional filters that are shared across different spatial positions for feature learning, we promote the adaptivity of the convolutional filters to spatial positions. We achieve this by the context interaction among the features of different scales. The SA module explicitly and softly selects the suitable scale for each spatial position and each channel. Ablation studies demonstrate the effectiveness of the proposed modules. We achieve state-of-the-art performance on three scene parsing benchmarks Cityscapes, ADE20K and LIP.

cs.CV↗

arXiv2020

FAN: Frequency Aggregation Network for Real Image Super-resolution

Single image super-resolution (SISR) aims to recover the high-resolution (HR) image from its low-resolution (LR) input image. With the development of deep learning, SISR has achieved great progress. However, It is still a challenge to restore the real-world LR image with complicated authentic degradations. Therefore, we propose FAN, a frequency aggregation network, to address the real-world image super-resolu-tion problem. Specifically, we extract different frequencies of the LR image and pass them to a channel attention-grouped residual dense network (CA-GRDB) individually to output corresponding feature maps. And then aggregating these residual dense feature maps adaptively to recover the HR image with enhanced details and textures. We conduct extensive experiments quantitatively and qualitatively to verify that our FAN performs well on the real image super-resolution task of AIM 2020 challenge. According to the released final results, our team SR-IM achieves the fourth place on the X4 track with PSNR of 31.1735 and SSIM of 0.8728.

eess.IV↗

arXiv2020

Microlocal sheaf categories and the $J$-homomorphism

Let $X$ be a smooth manifold and $\mathbf{k}$ be a commutative (or at least $\mathbb{E}_2$) ring spectrum. Given a smooth exact Lagrangian $L\hookrightarrow T^*X$, the microlocal sheaf theory (following Kashiwara--Schapira) naturally assigns a locally constant sheaf of categories on $L$ with fiber equivalent to the category of $\mathbf{k}$-spectra $\mathrm{Mod}(\mathbf{k})$. We show that the classifying map for the local system of categories factors through the stable Gauss map $L\rightarrow U/O$ and the delooping of the $J$-homomorphism $U/O\rightarrow B\mathrm{Pic}(\mathbf{S})$. As an application, combining with previous results of Guillermou [Gui], we recover a result of Abouzaid--Kragh [AbKr] on the triviality of the composition $L\rightarrow U/O\rightarrow B\mathrm{Pic}(\mathbf{S})$, when $L$ is in addition compact.

math.SG↗

arXiv2020

On Efficient Constructions of Checkpoints

Efficient construction of checkpoints/snapshots is a critical tool for training and diagnosing deep learning models. In this paper, we propose a lossy compression scheme for checkpoint constructions (called LC-Checkpoint). LC-Checkpoint simultaneously maximizes the compression rate and optimizes the recovery speed, under the assumption that SGD is used to train the model. LC-Checkpointuses quantization and priority promotion to store the most crucial information for SGD to recover, and then uses a Huffman coding to leverage the non-uniform distribution of the gradient scales. Our extensive experiments show that LC-Checkpoint achieves a compression rate up to $28\times$ and recovery speedup up to $5.77\times$ over a state-of-the-art algorithm (SCAR).

cs.LG↗

arXiv2020

AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results

This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020. This challenge involves three tracks to super-resolve an input image for $\times$2, $\times$3 and $\times$4 scaling factors, respectively. The goal is to attract more attention to realistic image degradation for the SR task, which is much more complicated and challenging, and contributes to real-world image super-resolution applications. 452 participants were registered for three tracks in total, and 24 teams submitted their results. They gauge the state-of-the-art approaches for real image SR in terms of PSNR and SSIM.

cs.CV↗

arXiv2020

Tetraquarks with open charm favor

Inspired by the recent report of the exotic states $X_{0}(2900)$ and $X_{1}(2900)$ with four different quark flavors in the $D^{-}K^{+}$ invariant mass distributions of the decay process $B^{+}\rightarrow D^{+}D^{-}K^{+}$ by the LHCb collaboration, we systematically investigate the tetraquarks composed of $ud\bar{s}\bar{c}$ with meson-meson and diquark-antidiquark structures in the quark delocalization color screening model. We find that the $X_{0}(2900)$ can be interpreted as the molecular state $\bar{D^{*}}K^{*}$ with $IJ^{P}=00^{+}$. Moreover, two bound states are obtained by the channel coupling calculation, with energies $2341.2$ MeV for $IJ^{P}=00^{+}$ and $2489.7$ MeV for $IJ^{P}=01^{+}$, respectively. We also extend our study to the $uc\bar{d}\bar{s}$ systems and find that there is no any bound state, so the $D_{s0}(2317)$ cannot be identified as the $DK$ molecular state in present calculation. Besides, several resonance states with the diquark-antidiquark configuration are possible in both $ud\bar{s}\bar{c}$ and $uc\bar{d}\bar{s}$ systems. All these open charm bound states and resonances are worth searching in the future experiments.

hep-ph↗

arXiv2020

Hierarchical Context Embedding for Region-based Object Detection

State-of-the-art two-stage object detectors apply a classifier to a sparse set of object proposals, relying on region-wise features extracted by RoIPool or RoIAlign as inputs. The region-wise features, in spite of aligning well with the proposal locations, may still lack the crucial context information which is necessary for filtering out noisy background detections, as well as recognizing objects possessing no distinctive appearances. To address this issue, we present a simple but effective Hierarchical Context Embedding (HCE) framework, which can be applied as a plug-and-play component, to facilitate the classification ability of a series of region-based detectors by mining contextual cues. Specifically, to advance the recognition of context-dependent object categories, we propose an image-level categorical embedding module which leverages the holistic image-level context to learn object-level concepts. Then, novel RoI features are generated by exploiting hierarchically embedded context information beneath both whole images and interested regions, which are also complementary to conventional RoI features. Moreover, to make full use of our hierarchical contextual RoI features, we propose the early-and-late fusion strategies (i.e., feature fusion and confidence fusion), which can be combined to boost the classification accuracy of region-based detectors. Comprehensive experiments demonstrate that our HCE framework is flexible and generalizable, leading to significant and consistent improvements upon various region-based detectors, including FPN, Cascade R-CNN and Mask R-CNN.

cs.CV↗

arXiv2020

Learning Disentangled Feature Representation for Hybrid-distorted Image Restoration

Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions. Existing HD-IR approaches usually ignore the inherent interference among hybrid distortions which compromises the restoration performance. To decompose such interference, we introduce the concept of Disentangled Feature Learning to achieve the feature-level divide-and-conquer of hybrid distortions. Specifically, we propose the feature disentanglement module (FDM) to distribute feature representations of different distortions into different channels by revising gain-control-based normalization. We also propose a feature aggregation module (FAM) with channel-wise attention to adaptively filter out the distortion representations and aggregate useful content information from different channels for the construction of raw image. The effectiveness of the proposed scheme is verified by visualizing the correlation matrix of features and channel responses of different distortions. Extensive experimental results also prove superior performance of our approach compared with the latest HD-IR schemes.

cs.CV↗

arXiv2020

Global Distance-distributions Separation for Unsupervised Person Re-identification

Supervised person re-identification (ReID) often has poor scalability and usability in real-world deployments due to domain gaps and the lack of annotations for the target domain data. Unsupervised person ReID through domain adaptation is attractive yet challenging. Existing unsupervised ReID approaches often fail in correctly identifying the positive samples and negative samples through the distance-based matching/ranking. The two distributions of distances for positive sample pairs (Pos-distr) and negative sample pairs (Neg-distr) are often not well separated, having large overlap. To address this problem, we introduce a global distance-distributions separation (GDS) constraint over the two distributions to encourage the clear separation of positive and negative samples from a global view. We model the two global distance distributions as Gaussian distributions and push apart the two distributions while encouraging their sharpness in the unsupervised training process. Particularly, to model the distributions from a global view and facilitate the timely updating of the distributions and the GDS related losses, we leverage a momentum update mechanism for building and maintaining the distribution parameters (mean and variance) and calculate the loss on the fly during the training. Distribution-based hard mining is proposed to further promote the separation of the two distributions. We validate the effectiveness of the GDS constraint in unsupervised ReID networks. Extensive experiments on multiple ReID benchmark datasets show our method leads to significant improvement over the baselines and achieves the state-of-the-art performance.

cs.CV↗

arXiv2020

Is Network the Bottleneck of Distributed Training?

Recently there has been a surge of research on improving the communication efficiency of distributed training. However, little work has been done to systematically understand whether the network is the bottleneck and to what extent. In this paper, we take a first-principles approach to measure and analyze the network performance of distributed training. As expected, our measurement confirms that communication is the component that blocks distributed training from linear scale-out. However, contrary to the common belief, we find that the network is running at low utilization and that if the network can be fully utilized, distributed training can achieve a scaling factor of close to one. Moreover, while many recent proposals on gradient compression advocate over 100x compression ratio, we show that under full network utilization, there is no need for gradient compression in 100 Gbps network. On the other hand, a lower speed network like 10 Gbps requires only 2x--5x gradients compression ratio to achieve almost linear scale-out. Compared to application-level techniques like gradient compression, network-level optimizations do not require changes to applications and do not hurt the performance of trained models. As such, we advocate that the real challenge of distributed training is for the network community to develop high-performance network transport to fully utilize the network capacity and achieve linear scale-out.

cs.DC↗

arXiv2020

Full-heavy tetraquarks in constituent quark models

The full-heavy tetraquarks $bb\bar{b}\bar{b}$ and $cc\bar{c}\bar{c}$ are systematically investigated within the chiral quark model and the quark delocalization color screening model. Two structures, meson-meson and diquark-antidiquark, are considered. For the full-beauty $bb\bar{b}\bar{b}$ systems, there is no any bound state or resonance state in two structures in the chiral quark model, while the wide resonances with masses around 19.25 GeV and the quantum numbers $J^{P}=0^{+}$, $1^{+}$, and $2^{+}$ are possible in the quark delocalization color screening model. For the full-charm $cc\bar{c}\bar{c}$ systems, the results are qualitative consistent in two quark models. No bound state can be found in the meson-meson configuration, while in the diquark-antidiquark configuration there may exist the resonance states, with masses range between $6.3$ GeV to $7.4$ GeV, and the quantum numbers $J^{P}=0^{+}$, $1^{+}$, and $2^{+}$. And the separation between the diquark and the antidiquark indicates that these states may be the compact resonance states. All these full-charm resonance states are consistent with the latest results at LHCb collaboration and are worth searching in the experiments further.

hep-ph↗

arXiv2020

Feature Alignment and Restoration for Domain Generalization and Adaptation

For domain generalization (DG) and unsupervised domain adaptation (UDA), cross domain feature alignment has been widely explored to pull the feature distributions of different domains in order to learn domain-invariant representations. However, the feature alignment is in general task-ignorant and could result in degradation of the discrimination power of the feature representation and thus hinders the high performance. In this paper, we propose a unified framework termed Feature Alignment and Restoration (FAR) to simultaneously ensure high generalization and discrimination power of the networks for effective DG and UDA. Specifically, we perform feature alignment (FA) across domains by aligning the moments of the distributions of attentively selected features to reduce their discrepancy. To ensure high discrimination, we propose a Feature Restoration (FR) operation to distill task-relevant features from the residual information and use them to compensate for the aligned features. For better disentanglement, we enforce a dual ranking entropy loss constraint in the FR step to encourage the separation of task-relevant and task-irrelevant features. Extensive experiments on multiple classification benchmarks demonstrate the high performance and strong generalization of our FAR framework for both domain generalization and unsupervised domain adaptation.

cs.CV↗