arXiv subjects

Jie Mei

Publications and source records attributed to Jie Mei.

At least 55 records · Page 3Linked to original sources

arXiv2024

Magnetic catalysis and diamagnetism from pion fluctuations

In the framework of Nambu--Jona-Lasinio model beyond mean field approximation, the effects of pion fluctuations on (inverse) magnetic catalysis and magnetic susceptibility are studied. The negative magnetic susceptibility at low temperature is observed when contributions from both neutral and charged pions are taken into account. In weak field approximation, it is observed that at finite temperature, the magnetic inhibition effect in the chiral limit, resulting from the difference between the transverse and longitudinal velocities of neutral pions, converts to weak magnetic catalysis when considering a non-zero current quark mass. Moreover, the magnetic catalysis is amplified by the charged pions.

hep-ph↗

arXiv2024

Few-Shot Object Detection with Sparse Context Transformers

Few-shot detection is a major task in pattern recognition which seeks to localize objects using models trained with few labeled data. One of the mainstream few-shot methods is transfer learning which consists in pretraining a detection model in a source domain prior to its fine-tuning in a target domain. However, it is challenging for fine-tuned models to effectively identify new classes in the target domain, particularly when the underlying labeled training data are scarce. In this paper, we devise a novel sparse context transformer (SCT) that effectively leverages object knowledge in the source domain, and automatically learns a sparse context from only few training images in the target domain. As a result, it combines different relevant clues in order to enhance the discrimination power of the learned detectors and reduce class confusion. We evaluate the proposed method on two challenging few-shot object detection benchmarks, and empirical results show that the proposed method obtains competitive performance compared to the related state-of-the-art.

cs.CV↗

arXiv2024

Digital Retina for IoV Towards 6G: Architecture, Opportunities, and Challenges

Vehicles are no longer isolated entities in traffic environments, thanks to the development of IoV powered by 5G networks and their evolution into 6G. However, it is not enough for vehicles in a highly dynamic and complex traffic environment to make reliable and efficient decisions. As a result, this paper proposes a cloud-edge-end computing system with multi-streams for IoV, referred to as Vehicular Digital Retina (VDR). Local computing and edge computing are effectively integrated in the VDR system through the aid of vehicle-to-everything (V2X) networks, resulting in a heterogeneous computing environment that improves vehicles' perception and decision-making abilities with collaborative strategies. Once the system framework is presented, various important functions in the VDR system are explained in detail, including V2X-aided collaborative perception, V2X-aided stream sharing for collaborative learning, and V2X-aided secured collaboration. All of them enable the development of efficient mechanisms of data sharing and information interaction with high security for collaborative intelligent driving. We also present a case study with simulation results to demonstrate the effectiveness of the proposed VDR system.

cs.NI↗

arXiv2023

Cascaded Interaction with Eroded Deep Supervision for Salient Object Detection

Deep convolutional neural networks have been widely applied in salient object detection and have achieved remarkable results in this field. However, existing models suffer from information distortion caused by interpolation during up-sampling and down-sampling. In response to this drawback, this article starts from two directions in the network: feature and label. On the one hand, a novel cascaded interaction network with a guidance module named global-local aligned attention (GAA) is designed to reduce the negative impact of interpolation on the feature side. On the other hand, a deep supervision strategy based on edge erosion is proposed to reduce the negative guidance of label interpolation on lateral output. Extensive experiments on five popular datasets demonstrate the superiority of our method.

cs.CV↗

arXiv2023

The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024

The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024 addresses maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicles (USV). Three challenges categories are considered: (i) UAV-based Maritime Object Tracking with Re-identification, (ii) USV-based Maritime Obstacle Segmentation and Detection, (iii) USV-based Maritime Boat Tracking. The USV-based Maritime Obstacle Segmentation and Detection features three sub-challenges, including a new embedded challenge addressing efficicent inference on real-world embedded devices. This report offers a comprehensive overview of the findings from the challenges. We provide both statistical and qualitative analyses, evaluating trends from over 195 submissions. All datasets, evaluation code, and the leaderboard are available to the public at https://macvi.org/workshop/macvi24.

cs.CV↗

arXiv2023

Sea You Later: Metadata-Guided Long-Term Re-Identification for UAV-Based Multi-Object Tracking

Re-identification (ReID) in multi-object tracking (MOT) for UAVs in maritime computer vision has been challenging for several reasons. More specifically, short-term re-identification (ReID) is difficult due to the nature of the characteristics of small targets and the sudden movement of the drone's gimbal. Long-term ReID suffers from the lack of useful appearance diversity. In response to these challenges, we present an adaptable motion-based MOT algorithm, called Metadata Guided MOT (MG-MOT). This algorithm effectively merges short-term tracking data into coherent long-term tracks, harnessing crucial metadata from UAVs, including GPS position, drone altitude, and camera orientations. Extensive experiments are conducted to validate the efficacy of our MOT algorithm. Utilizing the challenging SeaDroneSee tracking dataset, which encompasses the aforementioned scenarios, we achieve a much-improved performance in the latest edition of the UAV-based Maritime Object Tracking Challenge with a state-of-the-art HOTA of 69.5% and an IDF1 of 85.9% on the testing split.

cs.CV↗

arXiv2023

Look-Ahead Selective Plasticity for Continual Learning of Visual Tasks

Contrastive representation learning has emerged as a promising technique for continual learning as it can learn representations that are robust to catastrophic forgetting and generalize well to unseen future tasks. Previous work in continual learning has addressed forgetting by using previous task data and trained models. Inspired by event models created and updated in the brain, we propose a new mechanism that takes place during task boundaries, i.e., when one task finishes and another starts. By observing the redundancy-inducing ability of contrastive loss on the output of a neural network, our method leverages the first few samples of the new task to identify and retain parameters contributing most to the transfer ability of the neural network, freeing up the remaining parts of the network to learn new features. We evaluate the proposed methods on benchmark computer vision datasets including CIFAR10 and TinyImagenet and demonstrate state-of-the-art performance in the task-incremental, class-incremental, and domain-incremental continual learning scenarios.

cs.CV↗

arXiv2023

Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization

This paper presents Z-Code++, a new pre-trained language model optimized for abstractive text summarization. The model extends the state of the art encoder-decoder model using three techniques. First, we use a two-phase pre-training process to improve model's performance on low-resource summarization tasks. The model is first pre-trained using text corpora for language understanding, and then is continually pre-trained on summarization corpora for grounded text generation. Second, we replace self-attention layers in the encoder with disentangled attention layers, where each word is represented using two vectors that encode its content and position, respectively. Third, we use fusion-in-encoder, a simple yet effective method of encoding long sequences in a hierarchical manner. Z-Code++ creates new state of the art on 9 out of 13 text summarization tasks across 5 languages. Our model is parameter-efficient in that it outperforms the 600x larger PaLM-540B on XSum, and the finetuned 200x larger GPT3-175B on SAMSum. In zero-shot and few-shot settings, our model substantially outperforms the competing models.

cs.CL↗

arXiv2022

Mass spectra of neutral mesons $K_0,\ π_0,\ η,\ η'$ at finite magnetic field, temperature and baryon chemical potential

The mass spectra of neutral mesons $K_0, π_0, η, η'$ on temperature-quark chemical potential $(T-μ)$ plane in the presence of a constant magnetic field is investigated in the $SU(3)$ NJL model. As a Goldstone boson of chiral symmetry breaking, the mass of $K_0$ meson increases with temperature and/or quark chemical potential, and we observe two kinds of mass jumps of $K_0$ meson in media, which is induced by the mass jump of constituent quarks and the magnetic field, respectively. Due to the breaking of isospin symmetry between $u$ and $d$ quarks in magnetic fields, the mixing of $π_0-η- η'$ mesons occurs and this leads to rich structures of their mass spectra. For instance, $π_0$ mass is influenced by the strange quark. There appear the change of increase ratio of $π_0$ mass at high $μ$ and vanishing $T$ and the $π_0$ mass jump crossing over the threshold of two times of strange quark mass at finite $T$ and $μ$. The mass ordering of $π_0, \ η,\ η'$ mesons varies in media, due to their mass jumps, which are induced by the mass jump of constituent quarks or the magnetic field.

hep-ph↗

arXiv2022

Dynamic Beam-Based Random Access Scheme for M2M Communications in Massive MIMO Systems

Internet of things, supported by machine-to-machine (M2M) communications, is one of the most important applications for future 6th generation (6G) systems. A major challenge facing by 6G is enabling a massive number of M2M devices to access networks in a timely manner. Therefore, this paper exploits the spatial selectivity of massive multi-input multi-output (MIMO) to reduce the collision issue when massive M2M devices initiate random access simultaneously. In particular, a beam-based random access protocol is first proposed to make efficient use of the limited uplink resources for massive M2M devices. To address the non-uniform distribution of M2M devices in the space and time dimensions, an Markov decision process (MDP) problem with the objective of minimizing the average access delay is then formulated. Next, we present a dynamic beam-based access scheme based on the double deep Q network (DDQN) algorithm to solve the optimal policy. Finally, simulations are conducted to demonstrate the effectiveness of the proposed scheme including the model training and random access performance.

cs.IT↗

arXiv2022

NTIRE 2021 Multi-modal Aerial View Object Classification Challenge

In this paper, we introduce the first Challenge on Multi-modal Aerial View Object Classification (MAVOC) in conjunction with the NTIRE 2021 workshop at CVPR. This challenge is composed of two different tracks using EO andSAR imagery. Both EO and SAR sensors possess different advantages and drawbacks. The purpose of this competition is to analyze how to use both sets of sensory information in complementary ways. We discuss the top methods submitted for this competition and evaluate their results on our blind test set. Our challenge results show significant improvement of more than 15% accuracy from our current baselines for each track of the competition

cs.CV↗

arXiv2022

HCIL: Hierarchical Class Incremental Learning for Longline Fishing Visual Monitoring

The goal of electronic monitoring of longline fishing is to visually monitor the fish catching activities on fishing vessels based on cameras, either for regulatory compliance or catch counting. The previous hierarchical classification method demonstrates efficient fish species identification of catches from longline fishing, where fishes are under severe deformation and self-occlusion during the catching process. Although the hierarchical classification mitigates the laborious efforts of human reviews by providing confidence scores in different hierarchical levels, its performance drops dramatically under the class incremental learning (CIL) scenario. A CIL system should be able to learn about more and more classes over time from a stream of data, i.e., only the training data for a small number of classes have to be present at the beginning and new classes can be added progressively. In this work, we introduce a Hierarchical Class Incremental Learning (HCIL) model, which significantly improves the state-of-the-art hierarchical classification methods under the CIL scenario.

cs.CV↗

arXiv2022

Unsupervised Severely Deformed Mesh Reconstruction (DMR) from a Single-View Image

Much progress has been made in the supervised learning of 3D reconstruction of rigid objects from multi-view images or a video. However, it is more challenging to reconstruct severely deformed objects from a single-view RGB image in an unsupervised manner. Although training-based methods, such as specific category-level training, have been shown to successfully reconstruct rigid objects and slightly deformed objects like birds from a single-view image, they cannot effectively handle severely deformed objects and neither can be applied to some downstream tasks in the real world due to the inconsistent semantic meaning of vertices, which are crucial in defining the adopted 3D templates of objects to be reconstructed. In this work, we introduce a template-based method to infer 3D shapes from a single-view image and apply the reconstructed mesh to a downstream task, i.e., absolute length measurement. Without using 3D ground truth, our method faithfully reconstructs 3D meshes and achieves state-of-the-art accuracy in a length measurement task on a severely deformed fish dataset.

cs.CV↗

arXiv2021

A Fast Method for Steady-State Memristor Crossbar Array Circuit Simulation

In this work we propose an effective preconditioning technique to accelerate the steady-state simulation of large-scale memristor crossbar arrays (MCAs). We exploit the structural regularity of MCAs to develop a specially-crafted preconditioner that can be efficiently evaluated utilizing tensor products and block matrix inversion. Numerical experiments demonstrate the efficacy of the proposed technique compared to mainstream preconditioners.

cs.ET↗

arXiv2021

Semi-Decentralized Network Slicing for Reliable V2V Service Provisioning: A Model-free Deep Reinforcement Learning Approach

Applying of network slicing in vehicular networks becomes a promising paradigm to support emerging Vehicle-to-Vehicle (V2V) applications with diverse quality of service (QoS) requirements. However, achieving effective network slicing in dynamic vehicular communications still faces many challenges, particularly time-varying traffic of Vehicle-to-Vehicle (V2V) services and the fast-changing network topology. By leveraging the widely deployed LTE infrastructures, we propose a semi-decentralized network slicing framework in this paper based on the C-V2X Mode-4 standard to provide customized network slices for diverse V2V services. With only the long-term and partial information of vehicular networks, eNodeB (eNB) can infer the underlying network situation and then intelligently adjust the configuration for each slice to ensure the long-term QoS performance. Under the coordination of eNB, each vehicle can autonomously select radio resources for its V2V transmission in a decentralized manner. Specifically, the slicing control at the eNB is realized by a model-free deep reinforcement learning (DRL) algorithm, which is a convergence of Long Short Term Memory (LSTM) and actor-critic DRL. Compared to the existing DRL algorithms, the proposed DRL neither requires any prior knowledge nor assumes any statistical model of vehicular networks. Furthermore, simulation results show the effectiveness of our proposed intelligent network slicing scheme.

cs.IT↗

arXiv2021

Multi-Dimensional Multiple Access with Resource Utilization Cost Awareness for Individualized Service Provisioning in 6G

The increasingly diversified Quality-of-Service (QoS) requirements envisioned for future wireless networks call for more flexible and inclusive multiple access techniques for supporting emerging applications and communication scenarios. To achieve this, we propose a multi-dimensional multiple access (MDMA) protocol to meet individual User Equipment's (UE's) unique QoS demands while utilizing multi-dimensional radio resources cost-effectively. In detail, the proposed scheme consists of two new aspects, i.e., selection of a tailored multiple access mode for each UE while considering the UE-specific radio resource utilization cost; and multi-dimensional radio resource allocation among coexisting UEs under dynamic network conditions. To reduce the UE-specific resource utilization cost, the base station (BS) organizes UEs with disparate multi-domain resource constraints as UE coalition by considering each UE's specific resource availability, perceived quality, and utilization capability. Each UE within a coalition could utilize its preferred radio resources, which leads to low utilization cost while avoiding resource-sharing conflicts with remaining UEs. Furthermore, to meet UE-specific QoS requirements and varying resource conditions at the UE side, the multi-dimensional radio resource allocation among coexisting UEs is formulated as an optimization problem to maximize the summation of cost-aware utility functions of all UEs. A solution to solve this NP-hard problem with low complexity is developed using the successive convex approximation and the Lagrange dual decomposition methods. The effectiveness of our proposed scheme is validated by numerical simulation and performance comparison with state-of-the-art schemes. In particular, the simulation results demonstrate that our proposed scheme outperforms these benchmark schemes by large margins.

cs.IT↗

arXiv2021

JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and Segmentation

Recently, the coronavirus disease 2019 (COVID-19) has caused a pandemic disease in over 200 countries, influencing billions of humans. To control the infection, identifying and separating the infected people is the most crucial step. The main diagnostic tool is the Reverse Transcription Polymerase Chain Reaction (RT-PCR) test. Still, the sensitivity of the RT-PCR test is not high enough to effectively prevent the pandemic. The chest CT scan test provides a valuable complementary tool to the RT-PCR test, and it can identify the patients in the early-stage with high sensitivity. However, the chest CT scan test is usually time-consuming, requiring about 21.5 minutes per case. This paper develops a novel Joint Classification and Segmentation (JCS) system to perform real-time and explainable COVID-19 chest CT diagnosis. To train our JCS system, we construct a large scale COVID-19 Classification and Segmentation (COVID-CS) dataset, with 144,167 chest CT images of 400 COVID-19 patients and 350 uninfected cases. 3,855 chest CT images of 200 patients are annotated with fine-grained pixel-level labels of opacifications, which are increased attenuation of the lung parenchyma. We also have annotated lesion counts, opacification areas, and locations and thus benefit various diagnosis aspects. Extensive experiments demonstrate that the proposed JCS diagnosis system is very efficient for COVID-19 classification and segmentation. It obtains an average sensitivity of 95.0% and a specificity of 93.0% on the classification test set, and 78.5% Dice score on the segmentation test set of our COVID-CS dataset. The COVID-CS dataset and code are available at https://github.com/yuhuan-wu/JCS.

eess.IV↗

arXiv2021

MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization

MediaSum, a large-scale media interview dataset consisting of 463.6K transcripts with abstractive summaries. To create this dataset, we collect interview transcripts from NPR and CNN and employ the overview and topic descriptions as summaries. Compared with existing public corpora for dialogue summarization, our dataset is an order of magnitude larger and contains complex multi-party conversations from multiple domains. We conduct statistical analysis to demonstrate the unique positional bias exhibited in the transcripts of televised and radioed interviews. We also show that MediaSum can be used in transfer learning to improve a model's performance on other dialogue summarization tasks.

cs.CL↗