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
Dandan Zhu et al.
Summary: This paper proposes a novel Multi-scale Deep Feature Learning with correlation metric (MDFLCM) model to address the scale problem in Re-ID, by extracting multi-scale high-level features using a specially designed end-to-end multi-scale deep convolutional network (MS-DCN) and adding an extra correlation layer. Extensive comparative evaluations on four public datasets demonstrate the effectiveness of the proposed MDFLCM model in Re-ID.
KNOWLEDGE-BASED SYSTEMS
(2021)
Review
Computer Science, Artificial Intelligence
Eden Belouadah et al.
Summary: The paper investigates the open challenge of enhancing the capabilities of artificial agents when dealing with new data in artificial intelligence, focusing on two types of approaches to address catastrophic forgetting. The study shows that existing algorithms exhibit significant differences in performance under different evaluation settings, particularly in terms of whether a bounded memory of past classes is allowed.
Proceedings Paper
Computer Science, Artificial Intelligence
Anna Kukleva et al.
Summary: In this paper, a three-stage framework is proposed to effectively address the three major challenges in generalized and incremental few-shot learning. By learning different tasks in different stages, classifier calibration across all classes and prevention of catastrophic forgetting can be achieved. The framework achieves state-of-the-art results for both generalized and incremental few-shot learning on challenging benchmark datasets for image and video classification.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Eugene Lee et al.
Summary: The Attentive Independent Mechanisms (AIM) is a modular component designed for higher-order conceptual learning in deep neural networks. It competes to learn independent concepts to solve new tasks and incorporates the idea of learning using fast and slow weights to tackle challenges like fast adaptation to new tasks and catastrophic forgetting of old tasks.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Nan Pu et al.
Summary: The study introduces a new task of lifelong person re-identification (LReID) and proposes an Adaptive Knowledge Accumulation (AKA) framework with knowledge representation and operation abilities, which effectively alleviates catastrophic forgetting and demonstrates the ability to generalize to unseen domains.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Kai Zhu et al.
Summary: The study introduces an incremental prototype learning scheme that enhances the expression ability of new classes through a random episode selection strategy and a self-promoted prototype refinement mechanism, achieving remarkable incremental performance.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhong Zhang et al.
Summary: This paper proposes a novel deep graph model named HLGAT to model the inter-local relation and the intra-local relation in the completed local graph using attention mechanism to aggregate local features and emphasize the importance of different local features. Extensive experiments demonstrate that the proposed HLGAT outperforms the state-of-the-art methods in pedestrian reidentification.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Bo Zhao et al.
Summary: This paper introduces a new continual learning setting called continual representation learning, focusing on improving feature representation in a continuous way. Two large-scale biometric benchmarks are provided for better generalization of visual appearance. By applying knowledge distillation strategies, scalability and flexibility of the continual learning model are improved, achieving better results compared to competitors.
2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021)
(2021)
Article
Computer Science, Artificial Intelligence
Tharindu Fernando et al.
Article
Computer Science, Information Systems
Cairong Zhao et al.
IEEE TRANSACTIONS ON MULTIMEDIA
(2020)
Review
Computer Science, Artificial Intelligence
German I. Parisi et al.
Proceedings Paper
Computer Science, Artificial Intelligence
Yao Zhai et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2019)
(2019)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Yukun Huang et al.
PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19)
(2019)
Article
Computer Science, Artificial Intelligence
Zhizhong Li et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2018)
Article
Computer Science, Artificial Intelligence
Chen Change Loy et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2010)
