检索结果-内蒙古大学图书馆

Semantic-Aware Feature Aggregation for few-shot image classification

NEURAL PROCESSING LETTERS 2023年第5期55卷 6595-6609页

作者： Hao, Fusheng Wu, Fuxiang He, Fengxiang Zhang, Qieshi Song, Chengqun Cheng, Jun Shenzhen Inst Adv Technol Chinese Acad Sci Guangdong Hong Kong Macao Joint Lab Human Machine Shenzhen Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China JD Explore Acad JD com Beijing Peoples R China

Generating features from the most relevant image regions has shown great potential in solving the challenging few-shot image classification problem. Most of existing methods aggregate image regions weighted with attention maps to obtain category-specific features. Instead of using attention maps to indicate the relevance of image regions, we directly model the interdependencies between prototype features and image regions, resulting in a novel Semantic-Aware Feature Aggregation (SAFA) framework that can place more weights on category-relevant image regions. Specifically, we first design a "reduce and expand" block to extract category-relevant prototype features for each image. Then, we introduce an additive attention mechanism to highlight category-relevant image regions while suppressing the others. Finally, the weighted image regions are aggregated and used for classification. Extensive experiments show that our SAFA places more weights on category-relevant image regions and achieves state-of-the-art performance.

关键词： few-shot image classification Metric learning Semantic-aware feature aggregation Neural network

来源：评论

学校读者我要写书评

暂无评论

Unsupervised few-shot image classification via one-vs-all contrastive learning

引用

APPLIED INTELLIGENCE 2023年第7期53卷 7833-7847页

作者： Zheng, Zijun Feng, Xiang Yu, Huiqun Li, Xiuquan Gao, Mengqi East China Univ Sci & Technol Dept Comp Sci & Engn Shanghai 200237 Peoples R China Shanghai Engn Res Ctr Smart Energy Shanghai 200237 Peoples R China Chinese Acad Sci & Technol Dev Beijing 100038 Peoples R China

Human beings innately possess the ability to perceive novel concepts from only a few samples. As a setting to imitate the learned ability of human beings, few-shot image classification (FSIC) has recently aroused a research boom. FSIC aims to distinguish the novel class when given scarce samples. However, most of the existing few-shot methods build on the assumption that an adequate labeled dataset is provided in the source domain, ie, the base class dataset. Due to the expensive burden of labeled samples in the base class, this assumption may not be practical in a real-world application. To solve this labeled burden, in the paper, we propose a novel unsupervised few-shot image classification via One-vs-All contrastive learning. In this approach, to generate positive pairs in each instance, we first adopt a data augmentation technique to build the instance invariance. With the positive pairs, a neural projection with only a fully connected layer is then applied to maintain the structure consistent with the corresponding features of positive pairs. Finally, the One-Vs-All (OVA) contrastive learning is devised to pull one positive pair close while pushing all negative pairs away in a minibatch. By doing this OVA contrastive learning, the model can effectively acquire the discriminative feature and improve the generalization ability to recognize the novel class. We also further develop a theory of the generalized upper bound of the model for the OVA contrastive loss. Our experimental analyses suggest that the proposed approach achieves better performance compared to most existing few-shot methods, and various modules in the approach demonstrate their utility by conducting ablation studies.

关键词： few-shot image classification One-vs-all contrastive loss Instance invariance Neural projection

来源：评论

学校读者我要写书评

暂无评论

Query-Specific Embedding Co-Adaptation Improve few-shot image classification

引用

IEEE SIGNAL PROCESSING LETTERS 2023年 30卷 783-787页

作者： Fu, Wen Zhou, Li Chen, Jie Chinese Acad Sci Inst Microelect Beijing 100029 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

few-shot image classification (FSIC) aims to identify unseen categories by a limited number of instances. Recently, some metric-based methods have attempted to generate more discriminative task-specific embeddings by embedding adaptation strategies. However, the generated embeddings are either query-agnostic or ignore local relations between instances in each category, resulting in limited performance improvement. To address the above issues, in this letter, we propose QS-CAN, a Query-Specific embedding Co-Adaptation Network, which generates task- and query-specific embeddings by fusing inter-class and intra-class information. The core modules of QS-CAN are Inter-Class Adapter(Inter-A) and Intra-Class Adapter(Intra-A). The Inter-Class Adapter encodes the global relationship within the task, pushing the different categories away from each other. At the same time, the Intra-Class Adapter focuses on modeling the local relationship within each category, pulling the instances within a category closer. Moreover, an Adaptive Fusion Module (AFM) is proposed to integrate two co-adapted embeddings to get a more discriminative space. Experiments show that our method performs comparably to other advanced methods on three widely used datasets.

关键词： Deep learning transformer few-shot image classification embedding adaptation

来源：评论

学校读者我要写书评

暂无评论

Semantic-Aligned Attention With Refining Feature Embedding for few-shot image classification

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第12期23卷 25458-25468页

作者： Xu, Xianda Xu, Xing Shen, Fumin Li, Yujie Univ Elect Sci & Technol China Ctr Future Multimedia Chengdu 611731 Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Peoples R China Carnegie Mellon Univ Sch Comp Sci Pittsburgh PA 15213 USA Yangzhou Univ Sch Informat Engn Yangzhou 225002 Jiangsu Peoples R China

Autonomous driving relies on trusty visual recognition of surrounding objects. few-shot image classification is used in autonomous driving to help recognize objects that are rarely seen. Successful embedding and metric-learning approaches to this task normally learn a feature comparison framework between an unseen image and the labeled images. However, these approaches usually have problems with ambiguous feature embedding because they tend to ignore important local visual and semantic information when extracting intra-class common features from the images. In this paper, we introduce a Semantic-Aligned Attention (SAA) mechanism to refine feature embedding and it can be applied to most of the existing embedding and metric-learning approaches. The mechanism highlights pivotal local visual information with attention mechanism and aligns the attentive map with semantic information to refine the extracted features. Incorporating the proposed mechanism into the prototypical network, evaluation results reveal competitive improvements in both few-shot and zero-shot classification tasks on various benchmark datasets.

关键词： Semantics Task analysis Visualization Training Feature extraction Autonomous vehicles Real-time systems Autonomous driving few-shot image classification zero-shot image classification attention mechanism visual-semantic alignment

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Matching Prototypical Network for few-shot image classification

引用

IEEE SIGNAL PROCESSING LETTERS 2022年 29卷 982-986页

作者： Fu, Wen Zhou, Li Chen, Jie Chinese Acad Sci Inst Microelect Beijing 100029 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

few-shot image classification (FSIC) is the task of generalizing a model to unknown categories by learning from a small number of labeled samples of some given categories. Recently, metric-based approaches have received lots of attention for their simplicity and effectiveness, but they often only use support set to generate inaccurate prototypes matching query set, ignoring the rich information contained in queries and the reversibility of the matching relationship between the two. In this letter, we propose a new simple and effective metric-based method called Bidirectional Matching Prototypical Network (BMPN), which has three innovations:1)It has an additional reverse matching process. This process uses queries to generate more accurate prototypes to improve the model's performance while also forcing the model to learn features far from the decision boundary to enhance generalization capabilities;2)It has a lightweight coordinate attention feature extractor (CAFE). This module not only captures long-term dependence along one spatial direction but also saving the accurate position information of the other spatial direction, helping the model to locate the region of interest more accurately;3)It has a joint loss function, including forward matching loss and reverse matching loss, and a progressive weighting strategy is used in the training process to balance the importance of the two. Our model is trained end-to-end, and the experimental results show that we have reached the most advanced performance on the two benchmark datasets.

关键词： Prototypes Training Feature extraction image classification Task analysis Predictive models Measurement Bidirectional matching deep learning few-shot image classification metric-based method

来源：评论

学校读者我要写书评

暂无评论

Multi-Level Correlation Network For few-shot image classification

Multi-Level Correlation Network For Few-Shot Image Classific...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Dang, Yunkai Sun, Meijun Zhang, Min Chen, Zhengyu Zhang, Xinliang Wang, Zheng Wang, Donglin Tianjin Univ Coll Intelligence & Comp Tianjin Peoples R China Westlake Univ AI Div Sch Engn Hangzhou Peoples R China

ISBN: (纸本)9781665468916

few-shot image classification(FSIC) aims to recognize novel classes given few labeled images from base classes. Recent works have achieved promising classification performance, especially for metric-learning methods, where a measure at only image feature level is usually used. In this paper, we argue that measure at such a level may not be effective enough to generalize from base to novel classes when using only a few images. Instead, a multi-level descriptor of an image is taken for consideration in this paper. We propose a multi-level correlation network (MLCN) for FSIC to tackle this problem by effectively capturing local information. Concretely, we present the self-correlation module and cross-correlation module to learn the semantic correspondence relation of local information based on learned representations. Moreover, we propose a pattern-correlation module to capture the pattern of fine-grained images and find relevant structural patterns between base classes and novel classes. Extensive experiments and analysis show the effectiveness of our proposed method on four widely-used FSIC benchmarks.

关键词： few-shot image classification Metric Learning

来源：评论

学校读者我要写书评

暂无评论

FeatEMD: Better Patch Sampling and Distance Metric for few-shot image classification 1

引用

32nd International Conference on Artificial Neural Networks (ICANN)

作者： Deng, Shisheng Liao, Dongping Gao, Xitong Zhao, Juanjuan Ye, Kejiang Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen 518000 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Univ Macau Macau 999078 Peoples R China

ISBN: (数字)9783031442070

ISBN: (纸本)9783031442063;9783031442070

few-shot image classification (FSIC) studies the problem of classifying images when given only a few training samples, which presents a challenge for deep learning models to generalize well on unseen image categories. To learn FSIC tasks effectively, recent metric-based methods leverage the similarity measures of deep feature representations with minimum matching costs, introducing a new paradigm in addressing the FSIC challenge. Recent metric-learning techniques, e.g., DeepEMD, measure the distance between features with the earth mover's distance (EMD), and it is currently the state-of-the-art (SOTA) approach for FSIC. In this paper, we however identify two fundamental limitations in DeepEMD. First, it brings high computational cost, as it randomly samples image patches to extract features. This process is often wasteful due to suboptimal sampling strategies. Second, its accuracy is also limited by the use of optimal-transport costs based on cosine similarity, which only measures directional discrepancies. To mitigate the above shortcomings, we propose an improved method, which we call FeatEMD. First, it introduces a feature saliency-based cropping (FeatCrop) to construct image patches that concentrates computations on object-salient regions. Second, it proposes a Direction-Distance Similarity (DDS) a more effective distance criterion in capturing subtle differences in latent space features. We conduct comprehensive experiments and ablations to validate our method. Experimental results show FeatEMD establishes new SOTA on two mainstream benchmark datasets. Remarkably, when compared with DeepEMD, FeatEMD reduces up to 36% computational costs. Our code is available at https://***/SethDeng/FeatEMD.

关键词： few-shot image classification metric learning saliency-based cropping

来源：评论

学校读者我要写书评

暂无评论

Research on Transductive few-shot image classification Methods Based on Metric Learning 7

Research on Transductive Few-Shot Image Classification Metho...

引用

7th International Conference on Communication and Information Systems, ICCIS 2023

作者： Li, Shuai Jin, Jingxuan Li, De Wang, Peng College of Engineering Yanbian University Yanji China

ISBN: (纸本)9798350330540

In fields such as medical image analysis, autonomous driving, and military reconnaissance, obtaining a large number of shots is difficult or costly, resulting in a limited amount of data. Therefore, researching and addressing the challenge of classifying images with limited training shots is of significant practical importance. Metric learning approaches have demonstrated their effectiveness. Recently, the Ensemble Augmented-shot Y -shaped Learning (EASY) algorithm has achieved promising classification results, consisting of a feature extraction segment and a classifier segment. Backbone of the feature extraction segment is ResNet-12, a lightweight general image classification network suitable for few-shot image classification. However, its low parameter count leads to limited global perception capability, and it lacks task-specific sensitivity, making it less effective in discriminating fine-grained details. To overcome these constraints, this study introduces an innovative feature extraction network called SEYNet, which incorporates SE attention mechanism into the ResNet-12 backbone. This integration brings global context information into the feature extraction process, aiding in a better understanding of semantic information across the entire image. By enhancing the weights of specific channels, SEYNet captures subtle differences between shots and extracts more discriminative features. Additionally, the paper adopts an unsupervised discriminant subspace learning method to learn the similarity among features of the support set and unlabeled query set, and then performs linear projection to improve the performance of transductive few-shot image classification. Compared to EASY, the proposed method achieves improved classification accuracy of 2.36% and 1.65% in scenarios of 5-way 1-shot and 5-way 5-shot on FC100 dataset. The outcomes of the experiments demonstrate that the proposed method effectively enhances classification accuracy. © 2023 IEEE.

关键词： Attention Mechanism few-shot image classification Metric Learning Similarity Matrix unsupervised discriminant subspace learning

来源：评论

学校读者我要写书评

暂无评论

Low-Dimensional Feature Representation with Hybrid Attention for few-shot image classification 29

Low-Dimensional Feature Representation with Hybrid Attention...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Yao, Xin-Wei Yuan, Zhi-Heng Fang, Yu-Li He, Chuan Zhang, Yu-Chen Li, Qiang Zhejiang University of Technology College of Computer Science and Technology Hangzhou China Zhejiang University of Technology Taizhou Research Institute Taizhou China Zhejiang University of Technology Institute for Frontier and Interdisciplinary Sciences Hangzhou China

ISBN: (纸本)9798350330717

Learning effective image representation and constructing a suitable metric space are two main challenges in few-shot image classification. Existing methods normally consider the joint characteristic distribution of the image to improve the image representation ability, but it also brings high computational cost and produces high-dimensional embedding vectors, which limit their real-world applicability. In this paper, in order to reduce computational complexity and embedding dimension, we propose an effectively low-dimensional feature representation module (LDFR), which introduces a window mechanism to make the model focus on the correlation between local channels by using Brownian Distance Covariance. Furthermore, we combine LDFR with Hybrid Attention (LDFR-HA) to solve the problem of unbalanced sample features in few-shot image classification. Specifically, weighted average is adopted in the Hybrid Attention to construct the metric space and perform classification. Numerous experiments are conducted on two standard few-shot image classification benchmarks, i.e., general object recognition and fine-grained categorization. Extensive evaluations demonstrate that LDFR-HA significantly outperforms existing approaches. On popular datasets miniimageNet and CUB, LDFR-HA achieves 3.52 percentage point(pp)/2.29pp and 2.1pp/1.45pp gains over the state-of-the-art method on 5-way 1-shot/5-shot tasks, respectively. © 2023 IEEE.

关键词： Brownian Distance Covariance few-shot image classification Hybrid Attention Low-Dimensional Feature

来源：评论

学校读者我要写书评

暂无评论

KLSANet: Key local semantic alignment Network for few-shot image classification

引用

NEURAL NETWORKS 2024年 178卷 106456页

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

few-shot image classification involves recognizing new classes with a limited number of labeled samples. Current local descriptor-based methods, while leveraging consistent low-level features across visible and invisible classes, face challenges including redundant adjacent information, irrelevant partial representation, and limited interpretability. This paper proposes KLSANet, a few-shot image classification approach based on key local semantic alignment network, which aligns key local semantics for accurate classification. Furthermore, we introduce a key local screening module to mitigate the influence of semantically irrelevant image parts on classification. KLSANet demonstrates superior performance on three benchmark datasets (CUB, Stanford Dogs, Stanford Cars), outperforming state -of -the -art methods in 1-shot and 5-shot settings with average improvements of 3.95% and 2.56% respectively. Visualization experiments demonstrate the interpretability of KLSANet predictions. Code is available at: https://***/ZitZhengWang/KLSANet.

关键词： few-shot image classification Key local semantic alignment network Key local screening module Semantic similarity measurement module

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：