检索结果-内蒙古大学图书馆

10th International Conference on Advanced Cloud and Big Data (CBD)

作者： Li, Xiang Xu, Zhuoming Xu, Qi Tang, Yan Hohai Univ Coll Comp & Informat Nanjing Peoples R China

ISBN: (纸本)9798350309713

image classification is a typical task in big data applications. As a few-shot learning (FSL) task, the few-shot image classification attempts to learn a new visual concept from limited labelled images. The existing few-shot image classification methods usually fail to effectively eliminate the interference of image background information, thus affecting the accuracy of image classification. To overcome the shortcomings of existing methods and eliminate the interference of background information, this paper proposes a novel method named Unsupervised Semantic Segmentation with Feature Enhancement (USSFE) for few-shot image classification. USSFE uses the dense contrastive learning to train a robust unsupervised semantic segmentation model for foreground segmentation, and enhances feature representations of the foreground feature maps by extracting the shape and texture features of the foreground images. Our experimental results on two benchmark datasets, miniimageNet and tieredimageNet, show that the proposed USSFE method achieves better performance than the state-of-the-art methods.

关键词： few-shot image classification few-shot learning N-way K-shot metric-based learning unsupervised semantic segmentation feature enhancement

来源：评论

学校读者我要写书评

暂无评论

A Differentiable Architecture Search Approach for few-shot image classification 31st

A Differentiable Architecture Search Approach for Few-Shot I...

引用

31st International Conference on Artificial Neural Networks (ICANN)

作者： He, Chunmao Zhang, Lingyun Huang, Songqing Zhang, Pingjian Guangdong Prov Key Lab High Performance Servo Sys Zhuhai Peoples R China GREE Elect Appliances Inc Zhuhai Zhuhai Peoples R China South China Univ Technol Guangzhou Peoples R China

ISBN: (纸本)9783031159374;9783031159367

few-shot image classification is to learn models to distinguish between unseen categories, even though only a few labeled samples are involved in the training process. To alleviate the over-fitting problem caused by insufficient samples, researchers typically utilize artificially designed simple convolutional neural networks to extract features. However, the feature extraction capability of these networks is not strong enough to extract abstract semantic features, which will affect subsequent feature processing and significantly degrade performance when transferred to other datasets. This paper aims to design a general feature extraction network for few-shot image classification by improving the differentiable architecture search process. We propose a search space regularization method based on DropBlock and an early-stopping strategy based on pooling operation. Through the end-to-end search on the fewshot image dataset CUB, we obtain a light-weighted model FSLNet with excellent generalization ability. In addition, we propose a spatial pyramid self-attention mechanism to optimize the feature expression capability of FSLNet. Experiments show that the FSLNet searched in this paper achieves significant performance. The optimized FSLNet reaches state-of-the-art accuracy on the standard few-shot image classification datasets and in a cross-domain setting.

关键词： few-shot image classification Differentiable architecture search Spatial pyramid self-attention mechanism Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Global- and local-aware feature augmentation with semantic orthogonality for few-shot image classification

引用

PATTERN RECOGNITION 2023年第1期142卷

作者： Shi, Boyao Li, Wenbin Huo, Jing Zhu, Pengfei Wang, Lei Gao, Yang Nanjing Univ State Key Lab Novel Software Technol Nanjing 210023 Peoples R China Tianjin Univ Coll Intelligence & Comp Tianjin 300354 Peoples R China Univ Wollongong Sch Comp & Informat Technol Wollongong 2522 Australia

As for few-shot image classification, recently, some works revisit the standard transfer learning paradigm, i.e., pre-training and fine-tuning, and have achieved some success. However, we find that this kind of methods heavily relies on a naive image-level data augmentation (e.g., cropping and flipping) at the fine-tuning stage, which will easily suffer from the overfitting problem because of the limited-data regime. To tackle this issue, in this paper, we attempt to perform a novel feature-level semantic augmentation at the fine-tuning stage and propose a Global- and Local-aware Feature Augmentation method (GLFA) from both the channel- and spatial-wise perspectives. In addition, at the pre-training stage, we further propose a Semantic Orthogonal Learning Framework (SOLF) to make the learned feature channels more independently, orthogonal and diverse. Extensive experiments demonstrate that the proposed method can obtain significant performance improvements over the state of the arts. Code is available at https://***/onlyyao/GLFA-SOLF.

关键词： few-shot image classification Transfer learning Feature augmentation Semantic orthogonal learning

来源：评论

学校读者我要写书评

暂无评论

Transductive clustering optimization learning for few-shot image classification

引用

JOURNAL OF ELECTRONIC IMAGING 2023年第4期32卷 043005-043005页

作者： Wang, Yi Bian, Xiong Zhu, Songhao Nanjing Univ Posts & Telecommun Coll Automat & Artificial Intelligence Nanjing Peoples R China

few-shot image classification aims to perform image classification on new categories with only a small amount of labeled training data. However, it is difficult to complete such a task under the existing conditions. Therefore, the current few-shot learning methods are built on the paradigm of transfer learning, where the core idea is to learn a priori that can solve unknown new tasks. The idea of meta-learning is fast learning, which is similar to the idea of few-shot learning. Therefore, conventional few-shot learning methods generally adopt a meta-training approach with episodic training to construct knowledge prior. However, research work indicates that an embedding model with powerful feature representations is simpler and more effective than the existing sophisticated few-shot learning methods. Inspired by this insight, we propose a few-shot image classification method based on the transductive clustering optimization learning. First, memory block is introduced to store the internal feature structure of each category, namely comprehensive representation of various features. Second, during the training process, sample features are compared with the memory content to further expand the differences between different categories and improve the performance of feature extractor. Finally, in the transductive few-shot setting, a clustering optimization module has been introduced to select appropriate samples for clustering to alleviate the fundamental problem of sample scarcity. A large number of experimental results show that the proposed few-shot image classification method based on the transductive clustering optimization learning effectively improves the classification accuracy under various training conditions. (c) 2023 SPIE and IS&T

关键词： few-shot image classification transductive learning clustering optimization

来源：评论

学校读者我要写书评

暂无评论

Res-SVDNet: A Metric Learning Method for few-shot image classification 40

Res-SVDNet: A Metric Learning Method for Few-shot Image Clas...

引用

40th Chinese Control Conference (CCC)

作者： Zhang, He Liang, Lili Xian Univ Technol Fac Automat & Informat Engn Xian 710048 Peoples R China

ISBN: (纸本)9789881563804

Metric learning based few-shot image classification has recently received much attention for simplicity and efficiency. Its performance depends highly on the feature extractor and classifier. In this paper, we propose an alternative metric learning method for few-shot image classification-Res-SVDNet. Taking the advantages of good representation and anti-overfitting, the proposed Res-SVDNet utilizes ResNet-18 architecture as the backbone to extract image features. As for the classifier, Euclidean distance is employed to meet the few-shot classification preference for simple inductive bias. Considering the requirement of Euclidean distance for orthogonality, singular value decomposition (SVD) is further involved between feature extraction and classification to improve the classification performance of Res-SVDNet. Experimental results on Mini-imageNet and Tired-imageNet demonstrate that the proposed Res-SVDNet outperforms the state-of- the-art methods such as prototypical networks by 2%similar to 6%.

关键词： few-shot image classification ResNet18 SVD Euclidean distance classifier

来源：评论

学校读者我要写书评

暂无评论

CoCoOpter: Pre-train, prompt, and fine-tune the vision-language model for few-shot image classification

引用

INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL 2023年第2期12卷 27-27页

作者： Yan, Jie Xie, Yuxiang Guo, Yanming Wei, Yingmei Zhang, Xiaoping Luan, Xidao Natl Univ Def Technol Coll Syst Engn Changsha 410000 Peoples R China Toronto Metropolitan Univ Ryerson Univ Finance Dept Dept Elect Comp & Biomed EngnTed Rogers Sch Manag Toronto ON Canada Changsha Univ Coll Comp Engn & Appl Math Changsha 410000 Peoples R China

few-shot image classification aims at learning to generalize to unseen new categories from a few training samples. Transfer learning is one prominent approach to the task, which first learns a backbone from the base classes and then trains a classifier on new classes with the prior learned knowledge. Typically, the convolutional neural network (CNN) is the preferred backbone. However, when the samples are limited, the representation ability of the feature extracted by CNN will decrease, thus leading to the performance degradation of few-shot image classification. Recently, the pre-trained large-scale vision-language model like CLIP has shown non-trivial potential, which can be used as a backbone for zero or few-shot transfer on a series of downstream tasks with the prompt. To fully explore the few-shot image classification performance of vision-language models, we propose CoCoOpter, a novel "pre-training + prompt tuning + fine-tuning" paradigm based on CLIP. CoCoOpter alleviates the overfitting and ensures generalizability in unseen new categories. Specifically, it learns an input-specific neural network to relieve overfitting by drawing attention away from a specific category to each specific input sample. Then, to establish connection between the visual and textual signals, it introduces the previously learned visual representations to perform automatic prompt tuning in the middle of the pre-trained CLIP, enabling learning input-specified prompt vectors. Moreover, two learnable lightweight neural networks are added at the end of CLIP to guide information propagation between different classes by fine-tuning both the visual and textual features. We perform extensive experiments on 11 image classification datasets. The results show that CoCoOpter is more generalizable in unseen classes and achieves superior few-shot classification performance with a straightforward design.

关键词： few-shot image classification Contrastive vision-language pre-training Prompt tuning Multi-modal

来源：评论

学校读者我要写书评

暂无评论

Complementing Representation Deficiency in few-shot image classification: A Meta-Learning Approach 25

Complementing Representation Deficiency in Few-shot Image Cl...

引用

25th International Conference on Pattern Recognition (ICPR)

作者： Zhong, Xian Gu, Cheng Huang, Wenxin Li, Lin Chen, Shuqin Lin, Chia-Wen Wuhan Univ Technol Hubei Key Lab Transportat Internet Things Wuhan Peoples R China Wuhan Univ Technol Sch Comp Sci & Technol Wuhan Peoples R China Wuhan Univ Sch Comp Sci Wuhan Peoples R China Natl Tsing Hua Univ Dept Elect Engn Hsinchu Taiwan Natl Tsing Hua Univ Inst Commun Engn Hsinchu Taiwan

ISBN: (纸本)9781728188089

few-shot learning is a challenging problem that has attracted more and more attention recently since abundant training samples are difficult to obtain in practical applications. Meta-learning has been proposed to address this issue, which focuses on quickly adapting a predictor as a base-learner to new tasks, given limited labeled samples. However, a critical challenge for meta-learning is the representation deficiency since it is hard to discover common information from a small number of training samples or even one, as is the representation of key features from such little information. As a result, a meta-learner cannot be trained well in a high-dimensional parameter space to generalize to new tasks. Existing methods mostly resort to extracting less expressive features so as to avoid the representation deficiency. Aiming at learning better representations, we propose a meta-learning approach with complemented representations network (MCRNet) for few-shot image classification. In particular, we embed a latent space, where latent codes are reconstructed with extra representation information to complement the representation deficiency. Furthermore, the latent space is established with variational inference, collaborating well with different base-learners, and can be extended to other models. Finally, our end-to-end framework achieves the state-of-the-art performance in image classification on three standard few-shot learning datasets.

关键词： few-shot image classification Meta-learning Representation deficiency Latent space Variational inference

来源：评论

学校读者我要写书评

暂无评论

Layer-Wise Adaptive Updating for few-shot image classification

引用

IEEE SIGNAL PROCESSING LETTERS 2020年 27卷 2044-2048页

作者： Qin, Yunxiao Zhang, Weiguo Wang, Zezheng Zhao, Chenxu Shi, Jingping Northwestern Polytech Univ Xian 710129 Peoples R China Beijing Kwai Technol Beijing 102600 Peoples R China MiningLamp Technol Beijing 100000 Peoples R China

few-shot image classification (FSIC), which requires a model to recognize new categories via learning from few images of these categories, has attracted lots of attention. Recently, meta-learning based methods have been shown is promising for FSIC. Commonly, they train a meta-learner to learn easy fine-tuning weight for FSIC. When solving an FSIC task, the meta-learner efficiently updates itself on few images of the task and turns to a task-specific model. In this letter, we propose a novel meta-learning based layer-wise adaptive updating (LWAU) method for FSIC. LWAU is inspired by an interesting finding that compared with common deep models, the meta-learners pay much more attention to update their top layers when learning from few images. According to this finding, we assume that the meta-learners may greatly prefer updating their top layers to updating their bottom layers for better FSIC performance. Therefore, in LWAU, the meta-learner is trained to learn not only the easy fine-tuning weight but also its favorite layer-wise adaptive updating rule. Extensive experiments show that compared with existing few-shot classification methods, the proposed LWAU: 1) achieves better FSIC performance with a clear margin;2) almost updates only its top layer when solving FSIC, which indicates the learned feature extractor is much more generalizable;3) learns sparser feature extractor;4) learns from few images more efficiently by at least 5 times.

关键词： Deep learning few-shot image classification layer-wise adaptive updating meta-learning

来源：评论

学校读者我要写书评

暂无评论

SCNet: few-shot image classification via self-correlational and cross spatial-correlation attention

引用

Engineering Science and Technology, an International Journal 2025年 67卷

作者： He, Congqing Xu, Ding Gong, Ke Guo, Fusen Wei, Dapeng School of Computer Sciences Universiti Sains Malaysia Penang 11800 Malaysia Computer Science Department Harbin Institute of Technology Harbin 150000 China College of Mechanical Engineering North University of China Taiyuan 030000 China School of Science Computing and Engineering Technologies Swinburne University of Technology Melbourne 3122 Australia School of Design & Arts Beijing Institute of Technology Beijing 100081 China

Recently, few-shot learning has gained significant attention across various industries due to its ability to rapidly adapt and learn new tasks with few labeled training data. However, existing methods often struggle with capturing feature diversity within classes and aligning features between support and query images, leading to sub-optimal performance. To tackle these challenges, we propose SCNet, a novel few-shot image classification framework that leverages self-correlational and cross spatial-correlation attention mechanisms to enhance feature extraction and alignment. Specifically, we introduce a Self-Correlational Attention module that focuses on critical local features by locating target regions within basic image features, enhancing the extraction of discriminative features from each image independently. Additionally, we design a Cross Spatial-Correlation Attention module to capture shared features between support and query images, generating an informative co-attention map that improves feature alignment across different images. Furthermore, we introduce a novel loss function that combines label-based classification loss and metric-based loss, which mitigates overfitting during meta-testing and enhances alignment of query embeddings with category prototypes. Experiments on three few-shot benchmark datasets show that the proposed SCNet model significantly outperforms state-of-the-art few-shot image classification models. © 2025

关键词： Cross spatial-correlation attention few-shot image classification Label-based classification loss Metric-based loss Self-correlational attention

来源：评论

学校读者我要写书评

暂无评论

Res-SVDNet: A Metric Learning Method for few-shot image classification

Res-SVDNet: A Metric Learning Method for Few-shot Image Clas...

引用

第40届中国控制会议

作者： He Zhang Lili Liang Faculty of Automation and Information Engineering Xi’an University of Technology

Metric learning based few-shot image classification has recently received much attention for simplicity and *** performance depends highly on the feature extractor and classifier. In this paper, we propose an alternative metric learning method for few-shot image classification––Res-SVDNet. Taking the advantages of good representation and anti-overfitting, the proposed Res-SVDNet utilizes ResNet-18 architecture as the backbone to extract image features. As for the classifier, Euclidean distance is employed to meet the few-shot classification preference for simple inductive bias. Considering the requirement of Euclidean distance for orthogonality, singular value decomposition（SVD） is further involved between feature extraction and classification to improve the classification performance of Res-SVDNet. Experimental results on Mini-imageNet and Tired-imageNet demonstrate that the proposed Res-SVDNet outperforms the state-of-the-art methods such as prototypical networks by 2%～6%.

关键词： few-shot image classification ResNet18 SVD Euclidean distance classifier

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：