.png){kind=icon}
返回
Semantic-Based Implicit Feature Transform for Few-Shot Classification
.png){kind=icon}
PRE
AI
DOI：10.1007/s11263-024-02113-8.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 learning aims to recognize instances from previously unseen classes based on a very limited number of examples. However, models often face the challenge of overfitting due to the biased distribution computed from extremely scarce training data. This work proposes a Semantic-based Implicit Feature Transform (SIFT) method to implicitly generate high-quality features for few-shot learning tasks. In this method, we employ an encode-transform-decode pipeline to facilitate the direct transfer of feature instances from base classes to novel classes via semantic transformation, ensuring the generation of semantically meaningful features. Additionally, a compactness constraint is imposed on the generated features, with novel class prototypes serving as anchors, to ensure that the features are distributed around the class centers. Furthermore, we integrate the cluster centers of the query set with the initial prototypes computed from the support set to produce less biased class prototypes, which can serve as better anchors for feature reconstruction. The experimental results reveal that our method outperforms the baselines by substantial margins and achieves state-of-the-art few-shot classification performance on the miniImageNet and CIFAR-FS datasets in both inductive and transductive settings, demonstrating the superiority of our method. Furthermore, the comprehensive ablation studies provide additional validation of its effectiveness. The code is available at: https://github.com/pmhDL/SIFT.git.
Keyword:
Implicit feature transform
Tied weight
Cluster assignments
Path planning problem
期刊
IF:
9.3
论文数:
3.9K
被引数:
2.8W
机构
引用论文
Quantitative Evaluation of Collagen Crosslinks and Corresponding Tensile Mechanical Properties in Mouse Cervical Tissue during Normal Pregnancy.png)
PLoS ONE
OAAI
PLoS ONEIF0
OAAI分享收藏Investigation of Ti mesh-supported anodes for direct borohydride fuel cells直接硼氢化物燃料电池用钛网支撑阳极的研究
PREAI
分享收藏Cobalt and Copper Composite Oxides as Efficient Catalysts for Preferential Oxidation of CO in H2-Rich Stream钴和铜复合氧化物作为H2-Rich流中CO优先氧化的有效催化剂
PREAI
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