arXiv subjects

Fei Shen

Publications and source records attributed to Fei Shen.

116 records · Page 7Linked to original sources

arXiv2022

HSGNet: Object Re-identification with Hierarchical Similarity Graph Network

Object re-identification method is made up of backbone network, feature aggregation, and loss function. However, most backbone networks lack a special mechanism to handle rich scale variations and mine discriminative feature representations. In this paper, we firstly design a hierarchical similarity graph module (HSGM) to reduce the conflict of backbone and re-identification networks. The designed HSGM builds a rich hierarchical graph to mine the mapping relationships between global-local and local-local. Secondly, we divide the feature map along with the spatial and channel directions in each hierarchical graph. The HSGM applies the spatial features and channel features extracted from different locations as nodes, respectively, and utilizes the similarity scores between nodes to construct spatial and channel similarity graphs. During the learning process of HSGM, we utilize a learnable parameter to re-optimize the importance of each position, as well as evaluate the correlation between different nodes. Thirdly, we develop a novel hierarchical similarity graph network (HSGNet) by embedding the HSGM in the backbone network. Furthermore, HSGM can be easily embedded into backbone networks of any depth to improve object re-identification ability. Finally, extensive experiments on three large-scale object datasets demonstrate that the proposed HSGNet is superior to state-of-the-art object re-identification approaches.

cs.CV↗

arXiv2022

A Competitive Method for Dog Nose-print Re-identification

Vision-based pattern identification (such as face, fingerprint, iris etc.) has been successfully applied in human biometrics for a long history. However, dog nose-print authentication is a challenging problem since the lack of a large amount of labeled data. For that, this paper presents our proposed methods for dog nose-print authentication (Re-ID) task in CVPR 2022 pet biometric challenge. First, considering the problem that each class only with few samples in the training set, we propose an automatic offline data augmentation strategy. Then, for the difference in sample styles between the training and test datasets, we employ joint cross-entropy, triplet and pair-wise circle losses function for network optimization. Finally, with multiple models ensembled adopted, our methods achieve 86.67\% AUC on the test set. Codes are available at https://github.com/muzishen/Pet-ReID-IMAG.

cs.CV↗

arXiv2021

A Competitive Method to VIPriors Object Detection Challenge

In this report, we introduce the technical details of our submission to the VIPriors object detection challenge. Our solution is based on mmdetction of a strong baseline open-source detection toolbox. Firstly, we introduce an effective data augmentation method to address the lack of data problem, which contains bbox-jitter, grid-mask, and mix-up. Secondly, we present a robust region of interest (ROI) extraction method to learn more significant ROI features via embedding global context features. Thirdly, we propose a multi-model integration strategy to refinement the prediction box, which weighted boxes fusion (WBF). Experimental results demonstrate that our approach can significantly improve the average precision (AP) of object detection on the subset of the COCO2017 dataset.

cs.CV↗

arXiv2020

Exploring Spatial Significance via Hybrid Pyramidal Graph Network for Vehicle Re-identification

Existing vehicle re-identification methods commonly use spatial pooling operations to aggregate feature maps extracted via off-the-shelf backbone networks. They ignore exploring the spatial significance of feature maps, eventually degrading the vehicle re-identification performance. In this paper, firstly, an innovative spatial graph network (SGN) is proposed to elaborately explore the spatial significance of feature maps. The SGN stacks multiple spatial graphs (SGs). Each SG assigns feature map's elements as nodes and utilizes spatial neighborhood relationships to determine edges among nodes. During the SGN's propagation, each node and its spatial neighbors on an SG are aggregated to the next SG. On the next SG, each aggregated node is re-weighted with a learnable parameter to find the significance at the corresponding location. Secondly, a novel pyramidal graph network (PGN) is designed to comprehensively explore the spatial significance of feature maps at multiple scales. The PGN organizes multiple SGNs in a pyramidal manner and makes each SGN handles feature maps of a specific scale. Finally, a hybrid pyramidal graph network (HPGN) is developed by embedding the PGN behind a ResNet-50 based backbone network. Extensive experiments on three large scale vehicle databases (i.e., VeRi776, VehicleID, and VeRi-Wild) demonstrate that the proposed HPGN is superior to state-of-the-art vehicle re-identification approaches.

cs.CV↗

arXiv2019

Governance on Social Media Data: Different Focuses between Government and Internet Company

How governments and Internet companies regulate user data on social media attracts public attention. This study tried to answer two questions: What kind of countries send more requests for Facebook user data? What kind of countries get more requests replies from Facebook? We aim to figure out how a country's economic, political and social factors affect its government requests for user data and Facebook's responses rate to those requests. Results show that countries with higher GDP per capita, a higher level of human freedom and a lower level of rule of law send more requests for user data; while Facebook tends to reply to government requests from countries with a higher level of human freedom and a lower level of political stability. In conclusion, governments and Facebook show different focuses on governance on social media data.

stat.OT↗

arXiv2018

Understanding the Temporal Fading in Wireless Industrial Networks: Measurements and Analyses

The wide deployment of wireless industrial networks still faces the challenge of unreliable service due to severe multipath fading in industrial environments. Such fading effects are not only caused by the massive metal surfaces existing within the industrial environment but also, more significantly, the moving objects including operators and logistical vehicles. As a result, the mature analytical framework of mobile fading channel may not be appropriate for the wireless industrial networks especially the majority fixed wireless links. In this paper, we propose a qualitative analysis framework to characterize the temporal fading effects of the fixed wireless links in industrial environments, which reveals the essential reason of correlated temporal variation of both the specular and scattered power. Extensive measurements with both the envelop distribution and impulse response from field experiments validate the proposed qualitative framework, which will be applicable to simulate the industrial multipath fading characteristics and to derive accurate link quality metrics to support reliable wireless network service in various industrial applications.

eess.SP↗

arXiv2016

A Stackelberg Game for Incentive Proactive Caching Mechanisms in Wireless Networks

In this paper, an incentive proactive cache mechanism in cache-enabled small cell networks (SCNs) is proposed, in order to motivate the content providers (CPs) to participate in the caching procedure. A network composed of a single mobile network operator (MNO) and multiple CPs is considered. The MNO aims to define the price it charges the CPs to maximize its revenue while the CPs compete to determine the number of files they cache at the MNO's small base stations (SBSs) to improve the quality of service (QoS) of their users. This problem is formulated as a Stackelberg game where a single MNO is considered as the leader and the multiple CPs willing to cache files are the followers. The followers game is modeled as a non-cooperative game and both the existence and uniqueness of a Nash equilibrium (NE) are proved. The closed-form expression of the NE which corresponds to the amount of storage each CP requests from the MNO is derived. An optimization problem is formulated at the MNO side to determine the optimal price that the MNO should charge the CPs. Simulation results show that at the equilibrium, the MNO and CPs can all achieve a utility that is up to 50% higher than the cases in which the prices and storage quantities are requested arbitrarily.

cs.IT↗

arXiv2012

Real Root Isolation of Polynomial Equations Based on Hybrid Computation

A new algorithm for real root isolation of polynomial equations based on hybrid computation is presented in this paper. Firstly, the approximate (complex) zeros of the given polynomial equations are obtained via homotopy continuation method. Then, for each approximate zero, an initial box relying on the Kantorovich theorem is constructed, which contains the corresponding accurate zero. Finally, the Krawczyk interval iteration with interval arithmetic is applied to the initial boxes so as to check whether or not the corresponding approximate zeros are real and to obtain the real root isolation boxes. Meanwhile, an empirical construction of initial box is provided for higher performance. Our experiments on many benchmarks show that the new hybrid method is more efficient, compared with the traditional symbolic approaches.

cs.SC↗