Timezone: »

 
Poster
Cross Attention Network for Few-shot Classification
Ruibing Hou · Hong Chang · Bingpeng MA · Shiguang Shan · Xilin Chen

Wed Dec 11 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #19
in Algorithms -- Few-Shot Learning »

Few-shot classification aims to recognize unlabeled samples from unseen classes given only few labeled samples. The unseen classes and low-data problem make few-shot classification very challenging. Many existing approaches extracted features from labeled and unlabeled samples independently, as a result, the features are not discriminative enough. In this work, we propose a novel Cross Attention Network to address the challenging problems in few-shot classification. Firstly, Cross Attention Module is introduced to deal with the problem of unseen classes. The module generates cross attention maps for each pair of class feature and query sample feature so as to highlight the target object regions, making the extracted feature more discriminative. Secondly, a transductive inference algorithm is proposed to alleviate the low-data problem, which iteratively utilizes the unlabeled query set to augment the support set, thereby making the class features more representative. Extensive experiments on two benchmarks show our method is a simple, effective and computationally efficient framework and outperforms the state-of-the-arts.

Keywords: Meta-Learning · Algorithms · Few-Shot Learning
[ Paper]  [ Poster] 

Author Information

Ruibing Hou (Institute of Computing Technology，Chinese Academy)
Hong Chang (Institute of Computing Technology, Chinese Academy of Sciences)
Bingpeng MA (University of Chinese Academy of Sciences)
Shiguang Shan (Chinese Academy of Sciences)
Xilin Chen (Institute of Computing Technology, Chinese Academy of Sciences)

More from the Same Authors