Multi-level Metric Learning for Few-Shot Image Recognition

Chen, Haoxing; Li, Huaxiong; Li, Yaohui; Chen, Chunlin

doi:10.1007/978-3-031-15919-0_21

Cited by 13 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Squared root of the euclidean distance and the norm distance (SEN) [35] is proposed to improve the discriminative ability of widely used Euclidean distance. DN4 [36], Deep Earth mover’s distance (EMD) [37] and Multi‐level metric learning (MML) [38] obtain richer similarity by directly computing on local image descriptors.…”

Section: Related Workmentioning

confidence: 99%

Few‐shot classification using Gaussianisation prototypical classifier

Fan

Yang

2022

IET Computer Vision

View full text Add to dashboard Cite

Few‐shot classification (FSC) aims at classifying query samples into correct classes given only a few labelled samples. Prototypical Classifier (PC) can be chosen to be an ideal classifier for settling this problem, as it has good properties of low‐capacity and parameter‐free. However, the mean‐based prototypes suffer from the issue of deviating from its ground‐truth centre. In order to solve such problem of prototype bias, Gaussianisation Prototypical Classifier (GPC) is proposed, which is a kind of one‐step prototype rectification method. Specifically, the authors first perform Gaussianisation operation over the feature extracted from the backbone network so that the features fit the particular Gaussian distribution. Second, the authors use prototype feature of the base class as prior information and employs Maximum a Posteriori estimation method to obtain the reliable prototype for each novel class. Finally, the query sample of novel class is classified to be its nearest prototype with non‐parametric classifiers. Extensive experiments have been conducted on multiple FSC benchmarks. Comparative results also demonstrate that the authors’ method is superior to existing state‐of‐the‐art FSC methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Few‐shot classification using Gaussianisation prototypical classifier

Fan

Yang

2022

IET Computer Vision

View full text Add to dashboard Cite

show abstract

“…The metric-based method embeds instances in the feature vector space [34][35][36] and uses distance calculation via the metric form to classify unlabelled cases based on their similarity to labelled samples. The optimization-based method focuses on the training parameters of the model, optimizing the model initialization parameters to make the model quickly converge and achieve the desired effect [37][38][39].…”

Section: Few-shot Learningmentioning

confidence: 99%

Few‐shot object detection based on global context and implicit knowledge decoupled head

Li,

Yang,

Liu

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

The acquisition cycle of remote sensing images is slow, and the labelling process encounters challenges, which have become prominent with the rapid development of remote sensing image object detection research. Therefore, this article provides a way to make the model better capture the diversity and contextual relationships in the data, and solve this problem by more than just data augmentation. Specifically, this method is a few‐shot object detection method for remote sensing based on global context combined with implicit knowledge decoupled head (GC‐IKDH). This method first uses a segmentation strategy to convert high‐resolution images into low‐resolution images and expands the sample size through a generative model. Secondly, GC attention is introduced to generate a GC vector by weighting and averaging the information of each position in the input sequence, which helps the model better understand the semantics of the input sequence. Finally, an IKDH is added to improve the model head, which is used to learn specific features in the data so that the model can better handle the diversity in the data. Experimental results show that GC attention and IKDH boosting provide a good performance boost to the baseline model. Compared with other few‐shot samples, this method achieves state‐of‐the‐art performance under different shot settings and highly competitive results on two benchmark datasets (NWPU VHR‐10 and DIOR).

show abstract

“…Employing the multi-metric method to calculate the similarity of samples can reduce the bias of the network to a certain category and increase the robustness of the network. Chen H. et al ( 2022 ) design a fusion module to simultaneously integrate three distinct level similarities: the pixel-level similarity, the similarity of part-level features and global-level features. The query images within a class classified by three distinct level similarity metrics can be more tightly distributed in a smaller feature space, which produce more discriminative feature maps.…”

Section: Metric-based Few-shot Image Classificationmentioning

confidence: 99%

Learning with few samples in deep learning for image classification, a mini-review

Zhang

Liu

2023

Front. Comput. Neurosci.

View full text Add to dashboard Cite

Deep learning has achieved enormous success in various computer tasks. The excellent performance depends heavily on adequate training datasets, however, it is difficult to obtain abundant samples in practical applications. Few-shot learning is proposed to address the data limitation problem in the training process, which can perform rapid learning with few samples by utilizing prior knowledge. In this paper, we focus on few-shot classification to conduct a survey about the recent methods. First, we elaborate on the definition of the few-shot classification problem. Then we propose a newly organized taxonomy, discuss the application scenarios in which each method is effective, and compare the pros and cons of different methods. We classify few-shot image classification methods from four perspectives: (i) Data augmentation, which contains sample-level and task-level data augmentation. (ii) Metric-based method, which analyzes both feature embedding and metric function. (iii) Optimization method, which is compared from the aspects of self-learning and mutual learning. (iv) Model-based method, which is discussed from the perspectives of memory-based, rapid adaptation and multi-task learning. Finally, we conduct the conclusion and prospect of this paper.

show abstract

Multi-level Metric Learning for Few-Shot Image Recognition

Cited by 13 publications

References 25 publications

Few‐shot classification using Gaussianisation prototypical classifier

Few‐shot classification using Gaussianisation prototypical classifier

Few‐shot object detection based on global context and implicit knowledge decoupled head

Learning with few samples in deep learning for image classification, a mini-review

Contact Info

Product

Resources

About