Cross Attention Network for Few-shot Classification

被引:0
|
作者
Hou, Ruibing [1 ,2 ]
Chang, Hong [1 ,2 ]
Ma, Bingpeng [2 ]
Shan, Shiguang [1 ,2 ,3 ]
Chen, Xilin [1 ,2 ]
机构
[1] Chinese Acad Sci, Chinese Acad Sci CAS, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing, Peoples R China
[2] Univ Chinese Acad Sci, Beijing, Peoples R China
[3] Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing, Peoples R China
基金
北京市自然科学基金; 国家重点研发计划;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页数:12
相关论文
共 50 条
  • [1] Cross-channel spatial attention network for few-shot classification
    Jia, Yunwei
    Wang, Chao
    Zhu, Wanshan
    Lu, Keke
    Wang, Tianyang
    Yu, Kaiying
    [J]. JOURNAL OF ELECTRONIC IMAGING, 2023, 32 (05)
  • [2] Transductive Graph-Attention Network for Few-shot Classification
    Pan, Lili
    Liu, Weifeng
    [J]. 2022 16TH IEEE INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING (ICSP2022), VOL 1, 2022, : 190 - 195
  • [3] Total Relation Network with Attention for Few-Shot Image Classification
    Li, Xiao-Xu
    Liu, Zhong-Yuan
    Wu, Ji-Jie
    Cao, Jie
    Ma, Zhan-Yu
    [J]. Jisuanji Xuebao/Chinese Journal of Computers, 2023, 46 (02): : 371 - 384
  • [4] PANet: Pluralistic Attention Network for Few-Shot Image Classification
    Cao, Wenming
    Li, Tianyuan
    Liu, Qifan
    He, Zhiquan
    [J]. NEURAL PROCESSING LETTERS, 2024, 56 (04)
  • [5] Cross Attention with Deep Local Features for Few-Shot Image Classification
    Chu, Tengfei
    Shen, Hao
    Lv, Jing
    Yang, Ming
    [J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2023, PART X, 2023, 14263 : 98 - 110
  • [6] Multiscale attention for few-shot image classification
    Zhou, Tong
    Dong, Changyin
    Song, Junshu
    Zhang, Zhiqiang
    Wang, Zhen
    Chang, Bo
    Chen, Dechun
    [J]. COMPUTATIONAL INTELLIGENCE, 2024, 40 (02)
  • [7] Few-shot classification with Fork Attention Adapter
    Sun, Jieqi
    Li, Jian
    [J]. PATTERN RECOGNITION, 2024, 156
  • [8] TAAN: Task-Aware Attention Network for Few-shot Classification
    Wang, Zhe
    Liu, Li
    Li, FanZhang
    [J]. 2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 9130 - 9136
  • [9] Self-Calibrated Cross Attention Network for Few-Shot Segmentation
    Xu, Qianxiong
    Zhao, Wenting
    Lin, Guosheng
    Long, Cheng
    [J]. 2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, 2023, : 655 - 665
  • [10] Spatial Attention Network for Few-Shot Learning
    He, Xianhao
    Qiao, Peng
    Dou, Yong
    Niu, Xin
    [J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2019: DEEP LEARNING, PT II, 2019, 11728 : 567 - 578