arXiv subjects

Xing Xu

Publications and source records attributed to Xing Xu.

71 records · Page 4Linked to original sources

arXiv2022

Communication-Efficient Consensus Mechanism for Federated Reinforcement Learning

The paper considers independent reinforcement learning (IRL) for multi-agent decision-making process in the paradigm of federated learning (FL). We show that FL can clearly improve the policy performance of IRL in terms of training efficiency and stability. However, since the policy parameters are trained locally and aggregated iteratively through a central server in FL, frequent information exchange incurs a large amount of communication overheads. To reach a good balance between improving the model's convergence performance and reducing the required communication and computation overheads, this paper proposes a system utility function and develops a consensus-based optimization scheme on top of the periodic averaging method, which introduces the consensus algorithm into FL for the exchange of a model's local gradients. This paper also provides novel convergence guarantees for the developed method, and demonstrates its superior effectiveness and efficiency in improving the system utility value through theoretical analyses and numerical simulation results.

cs.LG↗

arXiv2021

Charge resolution in the isochronous mass spectrometry and the mass of $^{51}$Co

Isochronous mass spectrometry (IMS) of heavyion storage rings is a powerful tool for the mass measurements of short-lived nuclei. In IMS experiments, masses are determined through precision measurements of the revolution times of the ions stored in the ring. However, the revolution times cannot be resolved for particles with nearly the same mass-to-charge (m/q) ratios. To overcome this limitation and to extract the accurate revolution times for such pairs of ion species with very close m/q ratios, in our early work on particle identification, we analyzed the amplitudes of the timing signals from the detector based on the emission of secondary electrons. Here, the previous data analysis method is further improved by considering the signal amplitudes, detection efficiencies, and number of stored ions in the ring. A sensitive Z-dependent parameter is introduced in the data analysis, leading to a better resolution of $^{34}$Ar$^{18+}$ and $^{51}$Co$^{27+}$ with A/Z=17/9. The mean revolution times of $^{34}$Ar$^{18+}$ and $^{51}$Co$^{27+}$ are deduced, although their time difference is merely 1.8 ps. The uncorrected, overlapped peak of these ions has a full width at half maximum of 7.7 ps. The mass excess of $^{51}$Co was determined to be -27332(41) keV, which is in agreement with the previous value of -27342(48) keV.

nucl-ex↗

arXiv2021

I-WKNN: Fast-Speed and High-Accuracy WIFI Positioning for Intelligent Stadiums

Based on various existing wireless fingerprint location algorithms in intelligent sports venues, a high-precision and fast indoor location algorithm improved weighted k-nearest neighbor (I-WKNN) is proposed. In order to meet the complex environment of sports venues and the demand of high-speed sampling, this paper proposes an AP selection algorithm for offline and online stages. Based on the characteristics of the signal intensity distribution in intelligent venues, an asymmetric Gaussian filter algorithm is proposed. This paper introduces the application of the positioning algorithm in the intelligent stadium system, and completes the data acquisition and real-time positioning of the stadium. Compared with traditional WKNN and KNN algorithms, the I-WKNN algorithm has advantages in fingerprint positioning database processing, environmental noise adaptability, real-time positioning accuracy and positioning speed, etc. The experimental results show that the I-WKNN algorithm has obvious advantages in positioning accuracy and positioning time in a complex noise environment and has obvious application potential in a smart stadium.

cs.LG↗

arXiv2021

From General to Specific: Informative Scene Graph Generation via Balance Adjustment

The scene graph generation (SGG) task aims to detect visual relationship triplets, i.e., subject, predicate, object, in an image, providing a structural vision layout for scene understanding. However, current models are stuck in common predicates, e.g., "on" and "at", rather than informative ones, e.g., "standing on" and "looking at", resulting in the loss of precise information and overall performance. If a model only uses "stone on road" rather than "blocking" to describe an image, it is easy to misunderstand the scene. We argue that this phenomenon is caused by two key imbalances between informative predicates and common ones, i.e., semantic space level imbalance and training sample level imbalance. To tackle this problem, we propose BA-SGG, a simple yet effective SGG framework based on balance adjustment but not the conventional distribution fitting. It integrates two components: Semantic Adjustment (SA) and Balanced Predicate Learning (BPL), respectively for adjusting these imbalances. Benefited from the model-agnostic process, our method is easily applied to the state-of-the-art SGG models and significantly improves the SGG performance. Our method achieves 14.3%, 8.0%, and 6.1% higher Mean Recall (mR) than that of the Transformer model at three scene graph generation sub-tasks on Visual Genome, respectively. Codes are publicly available.

cs.CV↗

arXiv2021

Feature Space Targeted Attacks by Statistic Alignment

By adding human-imperceptible perturbations to images, DNNs can be easily fooled. As one of the mainstream methods, feature space targeted attacks perturb images by modulating their intermediate feature maps, for the discrepancy between the intermediate source and target features is minimized. However, the current choice of pixel-wise Euclidean Distance to measure the discrepancy is questionable because it unreasonably imposes a spatial-consistency constraint on the source and target features. Intuitively, an image can be categorized as "cat" no matter the cat is on the left or right of the image. To address this issue, we propose to measure this discrepancy using statistic alignment. Specifically, we design two novel approaches called Pair-wise Alignment Attack and Global-wise Alignment Attack, which attempt to measure similarities between feature maps by high-order statistics with translation invariance. Furthermore, we systematically analyze the layer-wise transferability with varied difficulties to obtain highly reliable attacks. Extensive experiments verify the effectiveness of our proposed method, and it outperforms the state-of-the-art algorithms by a large margin. Our code is publicly available at https://github.com/yaya-cheng/PAA-GAA.

cs.CV↗

arXiv2021

Electrostatic-lenses position-sensitive TOF MCP detector for beam diagnostics and new scheme for mass measurements at HIAF

A foil-microchannel plate (MCP) detector, which uses electrostatic lenses and possesses both good position and timing resolutions, has been designed and simulated for beam diagnostics and mass measurements at the next-generation heavy-ion-beam facility HIAF in China. Characterized by low energy loss and good performances of timing and position measurements, it would be located at focal planes in fragment separator HFRS for position monitoring, beam turning, B$ρ$ measurement, and trajectory reconstruction. Moreover, it will benefit the building-up of a magnetic-rigidity-energy-loss-time-of-flight (B$ρ$-$Δ$E-TOF) method at HFRS for high-precision in-flight particle identification (PID) of radioactive isotope (RI) beams on an event-by-event basis. Most importantly, the detector can be utilized for in-ring TOF and position measurements, beam-line TOF measurements at two achromatic foci, and position measurements at a dispersive focus of HFRS, thus making it possible to use two complementary mass measurement methods (isochronous mass spectrometry (IMS) at the storage ring SRing and magnetic-rigidity-time-of-flight (B$ρ$-TOF) at the beam-line HFRS) in one single experimental run.

physics.ins-det↗

arXiv2021

Stigmergic Independent Reinforcement Learning for Multi-Agent Collaboration

With the rapid evolution of wireless mobile devices, there emerges an increased need to design effective collaboration mechanisms between intelligent agents, so as to gradually approach the final collective objective through continuously learning from the environment based on their individual observations. In this regard, independent reinforcement learning (IRL) is often deployed in multi-agent collaboration to alleviate the problem of a non-stationary learning environment. However, behavioral strategies of intelligent agents in IRL can only be formulated upon their local individual observations of the global environment, and appropriate communication mechanisms must be introduced to reduce their behavioral localities. In this paper, we address the problem of communication between intelligent agents in IRL by jointly adopting mechanisms with two different scales. For the large scale, we introduce the stigmergy mechanism as an indirect communication bridge between independent learning agents, and carefully design a mathematical method to indicate the impact of digital pheromone. For the small scale, we propose a conflict-avoidance mechanism between adjacent agents by implementing an additionally embedded neural network to provide more opportunities for participants with higher action priorities. In addition, we present a federal training method to effectively optimize the neural network of each agent in a decentralized manner. Finally, we establish a simulation scenario in which a number of mobile agents in a certain area move automatically to form a specified target shape. Extensive simulations demonstrate the effectiveness of our proposed method.

cs.AI↗

arXiv2020

Universal Weighting Metric Learning for Cross-Modal Matching

Cross-modal matching has been a highlighted research topic in both vision and language areas. Learning appropriate mining strategy to sample and weight informative pairs is crucial for the cross-modal matching performance. However, most existing metric learning methods are developed for unimodal matching, which is unsuitable for cross-modal matching on multimodal data with heterogeneous features. To address this problem, we propose a simple and interpretable universal weighting framework for cross-modal matching, which provides a tool to analyze the interpretability of various loss functions. Furthermore, we introduce a new polynomial loss under the universal weighting framework, which defines a weight function for the positive and negative informative pairs respectively. Experimental results on two image-text matching benchmarks and two video-text matching benchmarks validate the efficacy of the proposed method.

cs.CV↗

arXiv2020

Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking

A major challenge in matching images and text is that they have intrinsically different data distributions and feature representations. Most existing approaches are based either on embedding or classification, the first one mapping image and text instances into a common embedding space for distance measuring, and the second one regarding image-text matching as a binary classification problem. Neither of these approaches can, however, balance the matching accuracy and model complexity well. We propose a novel framework that achieves remarkable matching performance with acceptable model complexity. Specifically, in the training stage, we propose a novel Multi-modal Tensor Fusion Network (MTFN) to explicitly learn an accurate image-text similarity function with rank-based tensor fusion rather than seeking a common embedding space for each image-text instance. Then, during testing, we deploy a generic Cross-modal Re-ranking (RR) scheme for refinement without requiring additional training procedure. Extensive experiments on two datasets demonstrate that our MTFN-RR consistently achieves the state-of-the-art matching performance with much less time complexity. The implementation code is available at https://github.com/Wangt-CN/MTFN-RR-PyTorch-Code.

cs.CV↗

arXiv2020

Internet of Intelligence: The Collective Advantage for Advancing Communications and Intelligence

The fifth-generation cellular networks (5G) has boosted the unprecedented convergence between the information world and physical world. On the other hand, empowered with the enormous amount of data and information, artificial intelligence (AI) has been universally applied and pervasive AI is believed to be an integral part of the six-generation cellular networks (6G). Consequently, benefiting from the advancement in communication technology and AI, we boldly argue that the conditions for collective intelligence (CI) will be mature in the 6G era and CI will emerge among the widely connected beings and things. Afterwards, we highlight the potential huge impact of CI on both communications and intelligence. In particular, we introduce a regular language (i.e., the information economy metalanguage) supporting the future collective communications to augment human intelligence and explain its potential applications in naming Internet information and pushing information centric networks forward. Meanwhile, we propose a stigmergy-based federated collective intelligence and demonstrate its achievement in a simulated scenario where the agents collectively work together to form a pattern through simple indirect communications. In a word, CI could advance both communications and intelligence.

cs.AI↗

arXiv2019

Reducing Storage in Large-Scale Photo Sharing Services using Recompression

The popularity of photo sharing services has increased dramatically in recent years. Increases in users, quantity of photos, and quality/resolution of photos combined with the user expectation that photos are reliably stored indefinitely creates a growing burden on the storage backend of these services. We identify a new opportunity for storage savings with application-specific compression for photo sharing services: photo recompression. We explore new photo storage management techniques that are fast so they do not adversely affect photo download latency, are complementary to existing distributed erasure coding techniques, can efficiently be converted to the standard JPEG user devices expect, and significantly increase compression. We implement our photo recompression techniques in two novel codecs, ROMP and L-ROMP. ROMP is a lossless JPEG recompression codec that compresses typical photos 15% over standard JPEG. L-ROMP is a lossy JPEG recompression codec that distorts photos in a perceptually un-noticeable way and typically achieves 28% compression over standard JPEG. We estimate the benefits of our approach on Facebook's photo stack and find that our approaches can reduce the photo storage by 0.3-0.9x the logical size of the stored photos, and offer additional, collateral benefits to the photo caching stack, including 5-11% fewer requests to the backend storage, 15-31% reduction in wide-area bandwidth, and 16% reduction in external bandwidth.

eess.IV↗

arXiv2019

Temporal Reasoning Graph for Activity Recognition

Despite great success has been achieved in activity analysis, it still has many challenges. Most existing work in activity recognition pay more attention to design efficient architecture or video sampling strategy. However, due to the property of fine-grained action and long term structure in video, activity recognition is expected to reason temporal relation between video sequences. In this paper, we propose an efficient temporal reasoning graph (TRG) to simultaneously capture the appearance features and temporal relation between video sequences at multiple time scales. Specifically, we construct learnable temporal relation graphs to explore temporal relation on the multi-scale range. Additionally, to facilitate multi-scale temporal relation extraction, we design a multi-head temporal adjacent matrix to represent multi-kinds of temporal relations. Eventually, a multi-head temporal relation aggregator is proposed to extract the semantic meaning of those features convolving through the graphs. Extensive experiments are performed on widely-used large-scale datasets, such as Something-Something and Charades, and the results show that our model can achieve state-of-the-art performance. Further analysis shows that temporal relation reasoning with our TRG can extract discriminative features for activity recognition.

cs.CV↗

arXiv2019

Cooperative Cross-Stream Network for Discriminative Action Representation

Spatial and temporal stream model has gained great success in video action recognition. Most existing works pay more attention to designing effective features fusion methods, which train the two-stream model in a separate way. However, it's hard to ensure discriminability and explore complementary information between different streams in existing works. In this work, we propose a novel cooperative cross-stream network that investigates the conjoint information in multiple different modalities. The jointly spatial and temporal stream networks feature extraction is accomplished by an end-to-end learning manner. It extracts this complementary information of different modality from a connection block, which aims at exploring correlations of different stream features. Furthermore, different from the conventional ConvNet that learns the deep separable features with only one cross-entropy loss, our proposed model enhances the discriminative power of the deeply learned features and reduces the undesired modality discrepancy by jointly optimizing a modality ranking constraint and a cross-entropy loss for both homogeneous and heterogeneous modalities. The modality ranking constraint constitutes intra-modality discriminative embedding and inter-modality triplet constraint, and it reduces both the intra-modality and cross-modality feature variations. Experiments on three benchmark datasets demonstrate that by cooperating appearance and motion feature extraction, our method can achieve state-of-the-art or competitive performance compared with existing results.

cs.CV↗

arXiv2017

Deep Region Hashing for Efficient Large-scale Instance Search from Images

Instance Search (INS) is a fundamental problem for many applications, while it is more challenging comparing to traditional image search since the relevancy is defined at the instance level. Existing works have demonstrated the success of many complex ensemble systems that are typically conducted by firstly generating object proposals, and then extracting handcrafted and/or CNN features of each proposal for matching. However, object bounding box proposals and feature extraction are often conducted in two separated steps, thus the effectiveness of these methods collapses. Also, due to the large amount of generated proposals, matching speed becomes the bottleneck that limits its application to large-scale datasets. To tackle these issues, in this paper we propose an effective and efficient Deep Region Hashing (DRH) approach for large-scale INS using an image patch as the query. Specifically, DRH is an end-to-end deep neural network which consists of object proposal, feature extraction, and hash code generation. DRH shares full-image convolutional feature map with the region proposal network, thus enabling nearly cost-free region proposals. Also, each high-dimensional, real-valued region features are mapped onto a low-dimensional, compact binary codes for the efficient object region level matching on large-scale dataset. Experimental results on four datasets show that our DRH can achieve even better performance than the state-of-the-arts in terms of MAP, while the efficiency is improved by nearly 100 times.

cs.CV↗

arXiv2016

Bidirectional Long-Short Term Memory for Video Description

Video captioning has been attracting broad research attention in multimedia community. However, most existing approaches either ignore temporal information among video frames or just employ local contextual temporal knowledge. In this work, we propose a novel video captioning framework, termed as \emph{Bidirectional Long-Short Term Memory} (BiLSTM), which deeply captures bidirectional global temporal structure in video. Specifically, we first devise a joint visual modelling approach to encode video data by combining a forward LSTM pass, a backward LSTM pass, together with visual features from Convolutional Neural Networks (CNNs). Then, we inject the derived video representation into the subsequent language model for initialization. The benefits are in two folds: 1) comprehensively preserving sequential and visual information; and 2) adaptively learning dense visual features and sparse semantic representations for videos and sentences, respectively. We verify the effectiveness of our proposed video captioning framework on a commonly-used benchmark, i.e., Microsoft Video Description (MSVD) corpus, and the experimental results demonstrate that the superiority of the proposed approach as compared to several state-of-the-art methods.

cs.MM↗

arXiv2016

Direct mass measurements of neutron-rich $^{86}$Kr projectile fragments and the persistence of neutron magic number $N$ = 32 in Sc isotopes

In this paper, we present direct mass measurements of neutron-rich $^{86}$Kr projectile fragments conducted at the HIRFL-CSR facility in Lanzhou by employing the Isochronous Mass Spectrometry (IMS) method. The new mass excesses of $^{52-54}$Sc nuclides are determined to be -40492(82), -38928(114), -34654(540) keV, which show a significant increase of binding energy compared to the reported ones in the Atomic Mass Evaluation 2012 (AME12). In particular, $^{53}$Sc and $^{54}$Sc are more bound by 0.8 MeV and 1.0 MeV, respectively. The behavior of the two neutron separation energy with neutron numbers indicates a strong sub-shell closure at neutron number $N$ = 32 in Sc isotopes.

nucl-ex↗

arXiv2016

A data analysis method for isochronous mass spectrometry using two time-of-flight detectors at CSRe

The concept of isochronous mass spectrometry (IMS) applying two time-of-flight (TOF) detectors originated many years ago at GSI. However, the corresponding method for data analysis has never been discussed in detail. Recently, two TOF detectors have been installed at CSRe and the new working mode of the ring is under test. In this paper, a data analysis method for this mode is introduced and tested with a series of simulations. The results show that the new IMS method can significantly improve mass resolving power via the additional velocity information of stored ions. This improvement is especially important for nuclides with Lorentz factor $γ$-value far away from the transition point $γ_t$ of the storage ring CSRe.

physics.ins-det↗