.png){kind=icon}
返回
Adaptive Hypersphere Data Description for few-shot one-class classification
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-024-05836-w.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Few-shot one-class classification (FS-OCC) is an important and challenging problem involving the recognition of a class using a limited number of positive training samples. Data description is essential for solving the FS-OCC problem as it delineates a region that separates positive data from other classes in the feature space. This paper introduces an effective FS-OCC model named Adaptive Hypersphere Data Description (AHDD). AHDD utilizes hypersphere-based data description with a learnable radius to determine the appropriate region for positive samples in the feature space. Both the radius and the feature network are learned concurrently using meta-learning. We propose a loss function for AHDD that enables the mutual adaptation of the radius and feature within a single FS-OCC task. AHDD significantly outperforms other state-of-the-art FS-OCC methods across various benchmarks and demonstrates strong performance on test sets with extreme class imbalance rates. Experimental results indicate that AHDD learns a robust feature representation, and the implementation of an adaptive radius can also improve the existing FS-OCC baselines.
Keyword:
Few-shot one-class classification
Hypersphere-based data description
Data description
Meta-learning
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
Y-GAN: Learning dual data representations for anomaly detection in imagesY-gan: 学习用于图像异常检测的双重数据表示
OAAI
OAAI分享收藏Self-supervised anomaly detection in computer vision and beyond: A survey and outlook计算机视觉及以后的自监督异常检测: 综述和展望.png)
NEURAL NETWORKSOAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏Network constraints and multi-objective optimization for one-class classificationNEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏分享收藏Service-Related Exposures and Physical Health Trajectories Among Aging Veteran Men老年退伍军人中与服务相关的暴露和身体健康轨迹
OAAI
OAAI分享收藏
查看更多内容