.png){kind=icon}
返回
SLTRN: Sample-level transformer-based relation network for few-shot classification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2024.106344.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 classification recognizes novel categories with limited labeled samples. The classic Relation Network (RN) compares support-query sample pairs for few-shot classification but overlooks support set contextual information, limiting its comparison capabilities. This work reformulates learning the relationship between query samples and each support class as a seq2seq problem. We introduce a Sample-level Transformer-based Relation Network (SLTRN) that utilizes sample-level self-attention to enhance the comparison ability of the relationship module by mining potential relationships among support classes. SLTRN demonstrates comparable performance with state-of-the-art methods on benchmarks, particularly excelling in the 1-shot setting with 52.11% and 67.55% accuracy on miniImageNet and CUB, respectively. Extensive ablation experiments validate the effectiveness and optimal settings of SLTRN. The experimental code for this work is available at https://github.com/ ZitZhengWang/SLTRN.
Keyword:
Few-shot learning
SLTRN
SLTRM
Transformer
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
引用论文
Few-shot learning via relation network based on coarse-grained granulation.png)
APPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
分享收藏Few-shot learning based on hierarchical classification via multi-granularity relation networks基于多粒度关系网络分层分类的少样本学习
PREAI
分享收藏Unsupervised descriptor selection based meta-learning networks for few-shot classificationPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Few-shot learning with deformable convolution for multiscale lesion detection in mammographyMEDICAL PHYSICS
MEDICAL PHYSICSIF3.2
PREAI
分享收藏SaberNet: Self-attention based effective relation network for few-shot learningSaberNet: 基于自我注意的少镜头学习有效关系网络PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
没有更多内容
没有更多内容