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
Engineering, Electrical & Electronic
Cen Chen et al.
Summary: This study proposes a hierarchical graph neural network (HGNN) for few-shot learning (FSL), which effectively learns multi-level relationships through bottom-up and top-down reasoning as well as skip connections. Experimental results demonstrate that HGNN outperforms other GNN-based methods in FSL tasks.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Lingling Zhang et al.
Summary: This article introduces a novel automatic attribute consistent network called Auto-ACNet to address the few-shot learning task in image recognition. By leveraging the attribute information of base and novel categories and utilizing neural architecture search technique, Auto-ACNet achieves significant improvement on two datasets.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Yuan Cao et al.
Summary: This paper proposes a principled Bayesian correlation filter learning method using a Gaussian scale mixture model for visual tracking. By decomposing CF coefficients into positive scalar multipliers and Gaussian random variables, the method achieves spatially adaptive regularization to handle various appearance-related uncertainty factors. By imposing a sparse prior over the multipliers, the method jointly learns the multipliers and CF coefficients, and utilizes structured GSM model to improve tracking performance.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Meng Cheng et al.
Summary: This paper introduces a new model for incremental few-shot object detection, which utilizes meta-learning to overcome the problem of catastrophic forgetting and adapt the model to unseen knowledge. Experimental results demonstrate that the proposed model outperforms state-of-the-art methods in both base classes and all classes detection, while achieving the best performance in detecting novel-class objects.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Rui Xu et al.
Summary: This research focuses on the problem of data scarcity and proposes two methods, IGL and GCT, to tackle the issue of feature extractor not adapting to novel data. IGL utilizes graph space and label space for prediction, reducing the dependence on features and the negative influence of noise. GCT strengthens the classifier by fusing multi-modal features and utilizing unlabeled samples. Experimental results demonstrate the outstanding performance of these methods in few-shot learning.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Yizeng Han et al.
Summary: Dynamic neural networks, which can adapt their structures or parameters to different inputs, have notable advantages in terms of accuracy, computational efficiency, and adaptiveness compared to static models. This survey comprehensively reviews the rapidly developing area of dynamic networks, categorizing them into sample-wise, spatial-wise, and temporal-wise models, and discusses important research problems and future directions.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Peyman Bateni et al.
Summary: We propose a transductive meta-learning method that utilizes unlabelled instances to enhance few-shot image classification performance. By combining a regularized Mahalanobis-distance-based soft k-means clustering procedure with an improved neural adaptive feature extractor, we achieve improved classification accuracy during test-time using unlabelled data. Our method has been evaluated on transductive few-shot learning tasks and has achieved state of the art performance on the Meta-Dataset, mini-ImageNet, and tiered-ImageNet benchmarks.
2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022)
(2022)
Article
Engineering, Electrical & Electronic
Wen Jiang et al.
Summary: This paper proposes a novel few-shot learning method called multi-scale metric learning (MSML) to tackle the classification problem in few-shot learning by extracting multi-scale features and learning multi-scale relationships. The method introduces a feature pyramid structure and a multi-scale relation generation network, and optimizes the deep network with the intra-class and inter-class relation loss, achieving superior performance in experimental results on mini ImageNet and tiered ImageNet.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Rishav Singh et al.
Summary: The study addresses the challenges of long-tailed distributions and lack of high-quality annotated images in medical datasets. By formulating a few-shot learning problem and proposing a meta-learning-based MetaMed approach, the model achieved promising results with an accuracy of over 70% on three medical datasets, showcasing improved generalization capability.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Artificial Intelligence
Baoquan Zhang et al.
Summary: The paper introduces a concept graph for weakly-supervised few-shot learning and proposes MetaConcept, a novel meta-learning framework. By training a universal meta-learner with advanced regularization and conceptual abstraction, it enhances classification performance on novel classes.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Information Systems
Xingxu Yao et al.
Summary: The paper introduces a method for processing affective images through adaptive deep metric learning, which enhances the recognition of emotional images by designing adaptive sentiment similarity loss and sentiment vector, while also proposing a unified multi-task deep framework.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Computer Science, Information Systems
Ge Song et al.
Summary: A new sequential learning method for real-world cross-modal retrieval is proposed in this study, which maintains a unified model to capture common knowledge of various modalities and learns in a sequential manner, adapting adaptively to the evolving distribution of different modalities without the need for alignment operations among multimodal data. Extensive experiments on multiple datasets show that the method achieves state-of-the-art cross-modal retrieval performance.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Computer Science, Information Systems
Yaohui Zhu et al.
Summary: This research proposes an attribute-guided two-layer learning framework for few-shot image recognition, which learns general feature representations and reduces sensitivity to novel categories. Experimental results demonstrate that this method effectively improves performance.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Computer Science, Information Systems
Huaxi Huang et al.
Summary: This study focuses on fine-grained classification with limited training data, proposing a novel Low-Rank Pairwise Alignment Bilinear Network (LRPABN) model. Comprehensive experiments on fine-grained classification datasets show that the LRPABN model outperforms state-of-the-art methods.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Computer Science, Information Systems
Yixiong Zou et al.
IEEE TRANSACTIONS ON MULTIMEDIA
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Limeng Qiao et al.
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Avinash Ravichandran et al.
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Xin Wang et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Hongyang Li et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Article
Engineering, Electrical & Electronic
Yuwu Lu et al.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2018)
Article
Psychology, Biological
Brenden M. Lake et al.
BEHAVIORAL AND BRAIN SCIENCES
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Yu Cheng et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017)
(2017)
Article
Computer Science, Artificial Intelligence
Olga Russakovsky et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2015)
Review
Multidisciplinary Sciences
Yann LeCun et al.
