检索结果-内蒙古大学图书馆

Selectively Augmented Attention Network for few-shot image classification

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第2期35卷 1180-1192页

作者： Li, Xiaoxu Wang, Xiangyang Zhu, Rui Ma, Zhanyu Cao, Jie Xue, Jing-Hao Lanzhou Univ Technol Sch Comp & Commun Lanzhou 730050 Peoples R China City St Georges Univ London Fac Actuarial Sci & Insurance Bayes Business Sch London England Beijing Univ Posts & Telecommun Sch Artificial Intelligence Pattern Recognit & Intelligent Syst Lab Beijing 100876 Peoples R China UCL Dept Stat Sci London WC1E 6BT England

few-shot image classification is a challenging task that aims to learn from a limited number of labelled training images a classification model that can be generalised to unseen classes. Two strategies are usually taken to improve the classification performances of few-shot image classifiers: either applying data augmentation to enlarge the sample size of the training set and reduce overfitting, or involving attention mechanisms to highlight discriminative spatial regions or channels. However, naively applying them to few-shot classifiers directly and separately may lead to undesirable results;for example, some augmented images may focus majorly on the background rather than the object, which brings additional noises to the training process. In this paper, we propose a unified framework, the selectively augmented attention (SAA) network, that carefully integrates the best of the two approaches in an end-to-end fashion via a selective best match module to select the most representative images from the augmented training set. The selected images tend to concentrate on the objects with less irrelevant background, which can assist the subsequent calculation of attentions by alleviating the interference from background. Moreover, we design a joint attention module to jointly learn both the spatial and channel-wise attentions. Experimental results on four benchmark datasets showcase the superior classification performance of the proposed SAA network compared with the state-of-the-arts.

关键词： Measurement Training Attention mechanisms Training data Noise Data augmentation Circuits and systems few shot learning Feature extraction Benchmark testing few-shot image classification data augmentation attention mechanism metric-based methods

来源：评论

学校读者我要写书评

暂无评论

Learning to Calibrate Prototypes for few-shot image classification

引用

COGNITIVE COMPUTATION 2025年第1期17卷 1-13页

作者： Liang, Chenchen Jiang, Chenyi Wang, Shidong Zhang, Haofeng Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Jiangsu Peoples R China Newcastle Univ Sch Engn Newcastle Upon Tyne NE17RU England

few-shot learning (FSL) aims to generalise the model to novel classes by using a limited amount of discriminative samples (a.k.a., prototypes). With few labelled samples, there is much uncertainty and randomness in the data, which makes it more difficult for the model to learn the complete underlying patterns. This paper proposes a Discriminative Property Calibration Network (DPCNet) to enable model building in linear space with robust separability. Concretely, the property features of samples are extracted to facilitate filtering out low-informative key points at the instance level, and then the key points are further refined from the perspective of property features to retain those dimensions that contain the most relevant properties. Furthermore, the discriminative key properties are re-weighted by accounting for the correlation between images, thus forcing the model to focus more on the key property information. Moreover, a new margin algorithm is proposed to optimise the data distribution of features by dynamically adjusting the distance between classes. We conduct extensive experiments on four datasets, i.e., miniimageNet, tiredimagenet, CUB-200-2011 and CIFAR-FS, achieving the accuracies of 67.96%, 72.57%, 79.6% and 74.56%, respectively, on the 5-way 1-shot setting, and the same very competitive performance on the 5-way 5-shot setting. The proposed method can well extract the most relevant and discriminative properties, the re-weighted features further emphasise the discrimination and the dynamic margin algorithm enhances the stability and generalisation ability. The proposed method achieves the state-of-the-art performance, and it will have meaningful inspiration for future works.

关键词： few-shot image classification Representation learning Prototype calibration Rank-based re-weighting

来源：评论

学校读者我要写书评

暂无评论

Adaptive feature recalibration transformer for enhancing few-shot image classification

引用

VISUAL COMPUTER 2025年 1-15页

作者： Song, Wei Huang, Yaobin Jiangnan Univ Sch Artificial Intelligence & Comp Sci Jiangsu Prov Engn Lab Pattern Recognit & Computat Wuxi 214122 Peoples R China

few-shot image classification aims to generalize prior knowledge from abundant base classes to novel categories with limited labeled samples. Current semantic alignment methods struggle with irrelevant regions interference, while task-aware approaches suffer from the deficiency of losing crucial inter-class structural information. To address the above issues, we propose an adaptive feature recalibration transformer (AFRT) for few-shot classification. During the pre-training phase, the feature encoder learns semantic information beyond image labels and contextual relationships of local regions from masked image modeling (MIM). During the meta-finetuning phase, our method comprises a task-driven salient region refinement module (TSRR) and a bidirectional interactive feature calibration module (BIFC). TSRR establishes local semantic relationships within the support set and filters out regions that contribute more to inference, weakening the expression of irrelevant regions. BIFC facilitates bidirectional interaction between local regions of support class features and query instance features, further focusing on more subtle and discriminative shared features. Extensive experiments show that our method achieves competitive performance on four widely used few-shot image classification benchmarks. Our code is available at https://***/leolensg/AFRT.

关键词： few-shot image classification Transformer Local features Self-supervision

来源：评论

学校读者我要写书评

暂无评论

Cluster-HGNN: Deep Local Features Clustering for few-shot image classification With Hybrid Graph Neural Networks

引用

IEEE ACCESS 2025年 13卷 30965-30975页

作者： Wu, Hongxuan Xin, Like Nanjing Normal Univ Sch Comp & Elect Informat Nanjing 210023 Peoples R China Nanjing Normal Univ Sch Math Sci Nanjing 210023 Peoples R China

Graph neural networks (GNNs) have shown great promise in few-shot learning, where they typically represent the entire feature of a sample as a node. However, this approach can overlook finer details within the sample, as GNNs usually measure the distance between nodes to determine overall differences, making them prone to background noise interference. To alleviate this limitation, we propose a novel framework based on a hybrid graph neural network for few-shot image classification, incorporating deep local features clustering (Cluster-HGNN). This framework comprises two types of GNNs: a global feature GNN and a local feature GNN. The former applies traditional label propagation to classify query nodes, while the latter treats feature embeddings as multiple deep local features, aggregating these by analyzing the categories of each query node's K nearest neighbours to infer the sample's category. The proposed design incorporates local features to rectify the final classification outcome, even in scenarios where the global features may inaccurately assess the current sample. Furthermore, the framework integrates multi-scale techniques and clustering to expand the feature space and reduce the influence of background noise on classification performance. As a result, Cluster-HGNN achieves state-of-the-art results on standard few-shot image classification benchmarks.

关键词： Graph neural networks image classification Training Feature extraction Vectors Hands Convolution Prototypes Metalearning few shot learning Deep learning deep local features few-shot image classification graph neural network

来源：评论

学校读者我要写书评

暂无评论

PrototypeFormer: Learning to explore prototype relationships for few-shot image classification

引用

NEUROCOMPUTING 2025年 640卷

作者： Su, Meijuan He, Feihong Li, Gang Li, Fanzhang Soochow Univ Sch Comp Sci & Technol Suzhou 215006 Peoples R China Sun Yat Sen Univ Sch Cyberspace Secur Shenzhen 518107 Peoples R China Chinese Acad Sci Inst Software Beijing 100190 Peoples R China

few-shot image classification has received considerable attention for overcoming the challenge of limited classification performance with limited samples in novel classes. Most existing works employ sophisticated learning strategies and feature learning modules to alleviate this challenge. In this paper, we propose a novel method called PrototypeFormer, exploring the relationships among category prototypes in the few-shot scenario. Specifically, we utilize a transformer architecture to build a prototype extraction module, aiming to extract class representations that are more discriminative for few-shot classification. Moreover, during the model training process, we propose a contrastive learning-based optimization approach to optimize prototype features in few-shot learning scenarios. Despite its simplicity, our method performs remarkably well, with no bells and whistles. We have experimented with our approach on several popular few-shot image classification benchmark datasets, which shows that our method outperforms most of current state-of-the-art methods. In particular, our method achieves 90.88% and 97.07% on 5-way 1-shot and 5-way 5-shot tasks of miniimageNet, which surpasses the state-of-the-art results with accuracy of 6.84% and 0.57%, respectively.

关键词： few-shot image classification Metric learning Vision transformer Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

TST_MFL: Two-stage training based metric fusion learning for few-shot image classification

引用

INFORMATION FUSION 2025年 113卷

作者： Sun, Zhe Zheng, Wang Guo, Pengfei Wang, Mingyang Yanshan Univ Dept Informat Sci & Engn Qinhuangdao Peoples R China

Addressing the limitations of most few-shot learning (FSL) methods, particularly their insufficient single-feature discriminability and generalization during pre-training encoding, this paper introduces a novel approach: Two-Stage Training based Metric Fusion Learning (TST_MFL) for few-shot image classification. TST_MFL innovatively integrates a two-stage fusion metric learning strategy, enhancing both pre-training and meta- training phases to overcome the prevalent focus on single-level feature extraction in current few-shot image classification methods. In pre-training stage, we employ prediction distillation loss and local difference loss to facilitate mutual learning between global and local features, thus obtaining more discriminative features. Moreover, meta-training further enhances feature generalization and integrates global-local metrics to improve few-shot classification accuracy. Our approach demonstrates competitive performance across three fine-grained datasets and one coarse-grained dataset. Notably, experimental results in 1-shot and 5-shot settings of finegrained datasets underscore the superiority of TST_MFL. The code for this work is available at: https://github. com/ZitZhengWang/TST_MFL.

关键词： few-shot image classification Two-stage training Metric fusion learning Prediction distillation loss Local difference loss

来源：评论

学校读者我要写书评

暂无评论

Variational Neuron Shifting for few-shot image classification Across Domains

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2024年 26卷 1460-1473页

作者： Zuo, Liyun Wang, Baoyan Zhang, Lei Xu, Jun Zhen, Xiantong Guangdong Univ Petrochem Technol Maoming 525011 Peoples R China Nankai Univ Sch Stat & Data Sci Tianjin 300071 Peoples R China

few-shot image classification aims to recognize unseen classes with few labeled samples. Existing meta-learning models learn the ability of learning good representation or model parameters, in order to adapt to new tasks with a few training samples. However, when there exists a domain gap between training and test tasks, the learned ability often does not generalize well across domains, resulting in degraded performance on new tasks. In this article, we propose variational neuron shifting to generate adapted feature representations for few-shot learning. To do so, we introduce a working memory module to store the shifted neurons from the support set, which will be accessed to generate adapted feature representations of query samples. Under the meta-learning paradigm, the model is learned to acquire the ability of adaptation with single sample at meta-training time so as to further adapt itself to each single test sample at meta-test time. We formulate the adaptation process as a variational Bayesian inference problem, which incorporates the test sample as the condition into the generation of the model neuron shifting. We conduct extensive experiments on both within and across domain few-shot classification tasks. The new state-of-the-art performance substantiates the effectiveness of our variational neuron shifting. The thorough ablation studies further demonstrate the benefit of each component in our model.

关键词： Meta learning few-shot image classification domain generalization variational inference

来源：评论

学校读者我要写书评

暂无评论

KGTN-ens: few-shot image classification with knowledge graph ensembles

引用

APPLIED INTELLIGENCE 2024年第2期54卷 1893-1908页

作者： Filipiak, Dominik Fensel, Anna Filipowska, Agata Univ Innsbruck Innrain 52 A-6020 Innsbruck Austria Univ Warsaw Krakowskie Przedmiescie 26-28 PL-00927 Warsaw Poland Wageningen Univ & Res Bioinformat Droevendaalsesteeg 2 NL-6708 PB Wageningen Netherlands Poznan Univ Econ & Business Fac Econ Dept Microecon Al Niepodległosci 10 PL-61875 Poznan Poland

We propose KGTN-ens, a framework extending the recent Knowledge GraphTransferNetwork (KGTN) in order to incorporate multiple knowledge graph embeddings at a small cost. There are many real-world scenarios in which the amount of data is severely limited (e.g. health industry, rare anomalies). Prior knowledge can be used to tackle this task. In KGTN, one can use a single knowledge source at once. The purpose of this study is to investigate the possibility of combining multiple knowledge sources. We evaluate it with different embeddings in a few-shot image classification task. Our model is partially trained on k. {1, 2, 5, 10} samples. We also construct a new knowledge source - Wikidata embeddings - and evaluate it with KGTN and KGTN-ens. With ResNet50, our approach outperforms KGTN in terms of the top-5 accuracy on the imageNet-FS dataset for the majority of tested settings. For k. {1, 2, 5, 10} respectively, we obtained +0.63/+0.58/+0.43/+0.26 pp. (novel classes) and +0.26/+0.25/+0.32/-0.04 pp. (all classes).

关键词： few-shot image classification Knowledge Graph Enabled AI Ensemble Learning

来源：评论

学校读者我要写书评

暂无评论

few-shot image classification via hybrid representation

引用

PATTERN RECOGNITION 2024年 155卷

作者： Liu, Bao-Di Shao, Shuai Zhao, Chunyan Xing, Lei Liu, Weifeng Cao, Weijia Zhou, Yicong China Univ Petr Coll Control Sci & Engn Qingdao 266580 Peoples R China Zhejiang Lab Hangzhou 311121 Zhejiang Peoples R China Suzhou Centennial Coll Suzhou Peoples R China Qingdao ChryStar Elect Technol Co Ltd Qingdao 266580 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Beijing 100094 Peoples R China Univ Macau Fac Sci & Technol Dept Comp & Informat Sci Taipa Macau Peoples R China

few -shot image classification aims to learn an embedding model on the base datasets and design a base learner to recognize novel categories. The few -shot image classification framework is a two-phase process. First, the pre -train phase utilizes the base data to train a CNN -based feature extractor. Next, in the meta -test phase, the frozen feature extractor is applied to novel data with categories different from the base data. A base learner is then designed for recognition. Several simple base learners, including nearest neighbor, support vector machine, and logistic regression classifiers, have been recently introduced for few -shot learning tasks. However, these base learners are separately designed to consider specific representations (e.g., the class center) or shared representations (e.g., the boundaries). This paper mainly focuses on exploring the representationresidual base learners, which aim to represent a query sample with the support set and predict the query sample's label based on the minimal residual error. We first introduce two representation -residual base learners: a specific representation base learner and a shared representation base learner. Then, we propose a novel hybrid representation base learner that combines both base learners to generate competitive representation. Additionally, we extend our approach by incorporating a self -training framework to utilize the query data fully. We evaluate our proposed method on several benchmark few -shot image classification datasets, such as miniimageNet, tieredimageNet, CIFAR-FS, FC100, and CUB datasets. The experimental results indicate that our proposed approach shows a significant performance improvement.

关键词： few-shot image classification Specific representation Shared representation

来源：评论

学校读者我要写书评

暂无评论

Class-Irrelevant Feature Removal for few-shot image classification

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2025年第5期36卷 9577-9591页

作者： Hao, Fusheng Liu, Liu Wu, Fuxiang Zhang, Qieshi Cheng, Jun Chinese Acad Sci Shenzhen Inst Adv Technol Guangdong Hong Kong Macao Joint Lab Human Machine Shenzhen 518055 Peoples R China Chinese Acad Sci Shenzhen Peoples R China

Most existing few-shot image classification methods employ global pooling to aggregate class-relevant local features in a data-drive manner. Due to the difficulty and inaccuracy in locating class-relevant regions in complex scenarios, as well as the large semantic diversity of local features, the class-irrelevant information could reduce the robustness of the representations obtained by performing global pooling. Meanwhile, the scarcity of labeled images exacerbates the difficulties of data-hungry deep models in identifying class-relevant regions. These issues severely limit deep models' few-shot learning ability. In this work, we propose to remove the class-irrelevant information by making local features class relevant, thus bypassing the big challenge of identifying which local features are class irrelevant. The resulting class-irrelevant feature removal (CIFR) method consists of three phases. First, we employ the masked image modeling strategy to build an understanding of images' internal structures that generalizes well. Second, we design a semantic-complementary feature propagation module to make local features class relevant. Third, we introduce a weighted dense-connected similarity measure, based on which a loss function is raised to fine-tune the entire pipeline, with the aim of further enhancing the semantic consistency of the class-relevant local features. Visualization results show that CIFR achieves the removal of class-irrelevant information by making local features related to classes. Comparison results on four benchmark datasets indicate that CIFR yields very promising performance.

关键词： Task analysis image classification Semantics Measurement Computational modeling Loss measurement image representation Class-irrelevant feature removal (CIFR) deep models few-shot image classification metric learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：