Related references
Note: Only part of the references are listed.
Article
Engineering, Electrical & Electronic
Runmin Cong et al.
Summary: In this paper, a new weakly-supervised salient object detection method is proposed, which addresses the issues of label noise and quantity imbalance through three training strategies. Experimental results demonstrate that our method achieves competitive performance against weakly-supervised/unsupervised methods both qualitatively and quantitatively.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Min Meng et al.
Summary: Unsupervised domain adaptation aims to address two challenging problems: thoroughly exploring fine-grained cluster structure knowledge in source and target domains, and effectively incorporating these structure knowledge for adaptation. The authors propose structural representation learning and a novel structural centroid-based label prediction method to tackle these problems, and adopt clustering learning to incorporate discriminative structure knowledge for adaptation. Comprehensive experiments demonstrate the superiority of the proposed framework.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Automation & Control Systems
Peiliang Huang et al.
Summary: Video object segmentation is a popular research topic in computer vision, but conventional methods require extensive manual annotations, which are time-consuming and labor-intensive. This paper proposes a method for video object segmentation using scribble-level supervision, which significantly reduces the need for manual annotation. By introducing a scribble attention module and a scribble-supervised loss, the proposed method achieves good performance with sparse and incomplete supervision information.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2022)
Article
Engineering, Multidisciplinary
Yang Ou et al.
Summary: This paper theoretically analyzes and summarizes the dynamic multi-physical processes between laser-Al/PTFE interactions and establishes a mathematical model to capture the dynamic interaction. The proposed model has been validated and provides a theoretical basis for further research on the heat and mass transfer of Al/PTFE materials.
APPLIED MATHEMATICAL MODELLING
(2022)
Article
Computer Science, Hardware & Architecture
Jian Shen et al.
Summary: This article proposes a multi-receiver secure data transmission protocol for wireless body area networks (WBANs), supporting multidisciplinary team treatment. The protocol utilizes a novel certificateless generalized signcryption scheme, ensuring various security properties.
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
(2022)
Article
Engineering, Electrical & Electronic
Yingjie Tian et al.
Summary: The research of semantic segmentation based on unsupervised domain adaptation addresses the issue of knowledge transfer between domains by reducing the high cost of manual annotation. Previous domain alignment strategies suffer from class asymmetry in practical training. By introducing partial domain adaptive method, category-level knowledge can be selectively learned to avoid negative transfer.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Yuyang Zhao et al.
Summary: In this work, the authors introduce a new concept called source-free open compound domain adaptation (SF-OCDA) and apply it to semantic segmentation. SF-OCDA is a more challenging but practical approach that addresses data privacy and storage issues, as well as multiple target domains and unseen open domains. The authors propose a framework that achieves state-of-the-art results on the C-Driving dataset and demonstrates leading performance on CityScapes for domain generalization. They also introduce a method called Cross-Patch Style Swap (CPSS) to improve model performance by diversifying samples and reducing the influence of noisy pseudo-labels.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhengkai Jiang et al.
Summary: In this paper, the authors propose a simple and efficient contrastive learning method called ProCA for unsupervised domain adaptive semantic segmentation. ProCA incorporates inter-class information into class-wise prototypes and adopts a class-centered distribution alignment approach. Experimental results show that ProCA achieves state-of-the-art performance on classical domain adaptation tasks.
COMPUTER VISION, ECCV 2022, PT XXXIV
(2022)
Article
Engineering, Civil
Haowen Tan et al.
Summary: This paper proposes a vehicle-assisted aggregate authentication mechanism for infrastructure-less vehicular networks, which enables data exchange and communication of validated entities with the assistance of neighboring vehicles. Compared with existing techniques, it has advantages in terms of security and performance.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Dingwen Zhang et al.
Summary: This study proposes a novel cross-modality deep feature learning framework for brain tumor segmentation from multi-modality MRI data. By incorporating cross-modality feature transition and fusion processes, the framework is able to effectively improve the performance of brain tumor segmentation.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Artificial Intelligence
Zhedong Zheng et al.
Summary: This paper proposes an approach to rectify pseudo label learning in unsupervised semantic segmentation adaptation by explicitly estimating prediction uncertainty during training and incorporating uncertainty into the optimization objective. Through extensive experiments, the proposed method achieves significant improvements on three benchmarks.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Article
Automation & Control Systems
Yun Liu et al.
Summary: The article aims to develop a lightweight SOD model inspired by the hierarchy perception learning in the primate visual cortex. The proposed HVPNet achieves highly competitive accuracy compared with state-of-the-art SOD methods while running at fast CPU and GPU speeds with only 1.23M parameters.
IEEE TRANSACTIONS ON CYBERNETICS
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Wangbo Zhao et al.
Summary: The study introduces a weakly supervised video salient object detection model based on relabeled fixation guided scribble annotations, alleviating the burden of data annotation. It utilizes an Appearance-motion fusion module and bidirectional ConvLSTM framework for effective multi-modal learning and long-term temporal context modeling, incorporating a novel loss function and boosting strategy to enhance model performance. Extensive experimental results verify the effectiveness of the solution on six benchmark video saliency detection datasets.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Francesco Barbato et al.
Summary: This paper introduces feature-level space-shaping regularization strategies to reduce domain discrepancy in semantic segmentation, achieving state-of-the-art results in the autonomous driving setting. By enforcing clustering objectives, perpendicularity constraints, and norm alignment goals on feature vectors corresponding to source and target samples, along with proposing a novel measure to capture the relative efficacy of adaptation strategies compared to supervised training, the effectiveness of such methods has been verified in multiple synthetic-to-real road scenes benchmarks.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Teo Spadotto et al.
Summary: Unsupervised Domain Adaptation (UDA) aims to improve the generalization capability of a model by adapting it from synthetic data to real world data distributions. The proposed approach in this paper uses an adversarial module and self-training strategy to align the two distributions, and proves effective in adapting a segmentation network trained on synthetic datasets to real world datasets.
2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)
(2021)
Article
Computer Science, Information Systems
Ping Gong et al.
Summary: This paper introduces a novel unsupervised domain adaptation network for cross-modality biomedical image segmentation, aiming to generalize models learned from labeled source domain to unlabeled target domain. The approach includes a conditional domain discriminator and a category-centric prototype aligner. Experimental results show significant performance improvement on the target domain.
Article
Computer Science, Artificial Intelligence
Liangchen Song et al.
PATTERN RECOGNITION
(2020)
Article
Computer Science, Artificial Intelligence
Shuang Li et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2020)
Article
Engineering, Electrical & Electronic
Jing Ling et al.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2020)
Article
Computer Science, Artificial Intelligence
Liangchen Song et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2020)
Article
Computer Science, Artificial Intelligence
Dingwen Zhang et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2020)
Article
Energy & Fuels
Tao Cui et al.
Article
Computer Science, Artificial Intelligence
Shuang Li et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2018)
Article
Computer Science, Artificial Intelligence
Liang-Chieh Chen et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2018)