相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Binhui Xie et al.
Summary: This paper proposes a unified framework called Collaborative Alignment Framework (CAF), which reduces global domain discrepancy and preserves local semantic consistency for cross-domain knowledge transfer. It utilizes adversarial training or Wasserstein distance to learn domain-level invariant representations and enhances the features of target data to be consistent with the source data class-wise. Experimental results demonstrate the superiority of the proposed methods over existing methods on popular benchmarks.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Naimeh Alipour et al.
Summary: The paper introduces a novel method called SDA-PPLS for heterogeneous domain adaptation, which aligns statistical distributions and progressively selects pseudo labels to map source and target domains into a shared feature space effectively.
APPLIED INTELLIGENCE
(2022)
Article
Computer Science, Hardware & Architecture
Huan Wang et al.
Summary: This study proposes a novel structural evolution-based anomaly detection method (SeaDM) for generalized evolving social networks with limited structural information. SeaDM combines an evolutional state construction algorithm and an optimized evolutional observation algorithm to evaluate state change and detect anomalies.
Article
Computer Science, Artificial Intelligence
Peishu Wu et al.
Summary: In this paper, a novel face mask detection framework called FMDYolo is proposed for monitoring whether people wear masks correctly in public. Experimental results demonstrate the superiority of FMDYolo in face mask detection.
IMAGE AND VISION COMPUTING
(2022)
Review
Computer Science, Artificial Intelligence
Sicheng Zhao et al.
Summary: This article reviews the latest single-source deep unsupervised domain adaptation (DA) methods for visual tasks and discusses new perspectives for future research. The article starts with the definitions of different DA strategies and descriptions of existing benchmark datasets, then summarizes and compares different categories of methods, and finally discusses future research directions.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Engineering, Industrial
Xiaofeng Xu et al.
Summary: This study addresses the refined oil distribution problem with shortages using a multi-objective optimization approach, including a robust optimization model (ROM) to manage uncertainty in demand and a multi-objective particle swarm optimization (MOPSO) algorithm. Results show that these models and algorithms effectively improve station satisfaction, reduce operation costs and overtime penalties, providing possibilities for the efficient distribution of scarce resources.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2022)
Article
Biology
Mei Yu et al.
Summary: The article introduces a weakly supervised segmentation neural network approach that addresses segmentation issues in medical images using a dual branch soft erase module and scale feature adaptation module, while further enhancing the nodule edge segmentation effect with an edge-based attention mechanism.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Biology
Qiu Guan et al.
Summary: In this paper, a new medical image augmentation method called TMP-GAN is proposed, which utilizes joint training of multiple channels, adversarial learning-based texture discrimination loss, and progressive generation mechanism to improve the quality of synthesized images for lesion detection. Experimental results show that the detector trained on the TMP-GAN augmented dataset outperforms other data augmentation methods in terms of precision, recall, and F1-score.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Computer Science, Artificial Intelligence
Han Li et al.
Summary: In the context of the global COVID-19 pandemic, a computer aided diagnosis model called Cov-Net is proposed for accurate recognition of COVID-19 from chest X-ray images. Experimental results demonstrate the high feasibility and accuracy of the model in identifying COVID-19. Compared to other algorithms, Cov-Net exhibits superior performance and competitiveness in this task.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Chemistry, Multidisciplinary
Wei Dang et al.
Summary: Machine sense of smell plays an important role in various scenarios, but it relies on data and algorithms for support. This study proposes a semi-supervised extreme learning machine algorithm, SELMWK, which combines weighted kernel with SKELM to handle a small amount of labeled data and a large amount of unlabeled data, achieving good classification performance.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Information Systems
Xiaomei Qin et al.
Summary: In the era of big data, analyzing user behavior patterns on social networking sites can predict their personality models and improve the accuracy and efficiency of predictions.
Article
Computer Science, Hardware & Architecture
Guiyang Luo et al.
Summary: Mobile networks (MNs) are becoming increasingly complex, presenting challenges in deployment, management, operation, optimization, and maintenance. The application of artificial intelligence (AI) in MNs has shown potential in understanding and making intelligent decisions. This article proposes an AI-powered MN architecture and discusses the challenges and potential solutions associated with cognition complexity and decision-making. It also introduces a deep learning approach to map the state of an MN to perceived QoS, improving decision-making for operators.
Article
Computer Science, Software Engineering
Yongqi Zhang et al.
Summary: The study proposes an automatic approach to jointly design workspaces and workplans by optimizing performance and workload factors, generating Pareto-optimal design solutions for different work scenarios. Evaluation experiments validate the efficacy of the approach in synthesizing effective workspaces and workplans.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Article
Computer Science, Artificial Intelligence
Qiang Zhou et al.
Summary: Domain adaptation is a powerful tool for transferring knowledge from source domains to target tasks, but most existing methods focus on single-source-single-target adaptation settings, ignoring the potential of multiple source domains. This paper introduces a new theoretical generalization bound for multiple source domain adaptation and a new algorithm, DAN_MA, which outperforms other methods on three public datasets by utilizing adversarial networks to learn domain invariant representations and eliminate domain characteristics among different source domains.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Sicheng Zhao et al.
Summary: This paper introduces a novel multi-source adversarial domain adaptation framework to address challenges such as pixel-level alignment and misalignment among different sources, improving model performance. Experimental results demonstrate that the proposed model performs exceptionally well on digit recognition, object classification, and semantic segmentation tasks.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Article
Computer Science, Artificial Intelligence
Guoxi Liang et al.
Summary: Automated essay scoring is an exciting task in natural language processing where researchers have been exploring the detection of creative essays. This paper proposes a method using a generative adversarial network framework to judge the creativity of essays by masking part of the content. Experimental results show the feasibility of the proposed approach in identifying creative essays.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Software Engineering
Xiaoxue Wu et al.
Summary: This study reveals the presence of mislabeled instances in datasets for security bug report prediction, which has negatively impacted the performance of previous models. However, after cleaning the datasets, the performance of classification models has significantly improved.
IEEE TRANSACTIONS ON SOFTWARE ENGINEERING
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Eduardo Fernandes Montesuma et al.
Summary: The study introduces a key technique for training models on data from multiple probability distributions, proposes the Wasserstein Barycenter Transport method, and conducts experiments in object and face recognition as well as music genre recognition and music-speech discrimination.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Ni Xiao et al.
Summary: This paper proposes Dynamic Weighted Learning (DWL) to address the issue of negative transfer in unsupervised domain adaptation, caused by insufficient balance between domain alignment and class discrimination. By dynamically weighting the learning losses and considering the problem of sample imbalance across domains, DWL demonstrates excellent performance on several benchmark datasets.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yunsheng Li et al.
Summary: This paper introduces dynamic transfer to address domain conflicts by adapting model parameters to samples, transforming multi-source domains into a single-source domain and simplifying alignment between source and target domains. Experimental results demonstrate that dynamic transfer outperforms the state-of-the-art method on the large multi-source domain adaptation dataset DomainNet.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Article
Automation & Control Systems
Xiangxiang Zeng et al.
IEEE TRANSACTIONS ON CYBERNETICS
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Youshan Zhang et al.
2020 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WORKSHOPS (WACVW)
(2020)
Article
Computer Science, Artificial Intelligence
Ievgen Redko et al.
Article
Mathematics
Lenaic Chizat et al.
JOURNAL OF FUNCTIONAL ANALYSIS
(2018)
Article
Computer Science, Artificial Intelligence
Olga Russakovsky et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2015)
