Contrasting augmented features for domain adaptation with limited target domain data

被引:7
作者
Yu, Xi [1 ]
Gu, Xiang [1 ]
Sun, Jian [1 ]
机构
[1] Xi An Jiao Tong Univ, Sch Math & Stat, Xian, Shaanxi, Peoples R China
关键词
Domain adaptation; Limited target domain data; Contrasting augmented features;
D O I
10.1016/j.patcog.2023.110145
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Domain adaptation aims to alleviate distribution gaps between source and target domains. However, when the available target domain data are scarce for training, learning generalizable representations for domain adaptation is challenging. We propose a novel approach, dubbed Contrasting Augmented Features (CAF), to tackle the challenge of insufficient target domain data for domain adaptation, by generating and contrasting augmented features. We introduce a semantic feature generator to generate augmented features by replacing the instance-level feature statistics of one domain with another domain. With the augmented features, we further design the reweighted instance contrastive loss and category contrastive loss to improve feature discrimination and align feature distributions of source and target domains. CAF can be applied to few-shot domain adaptation and unsupervised domain adaptation with limited unlabeled target domain data. Despite its simplicity, extensive experiments show promising results for both applications. In addition, experiments demonstrate that CAF is more robust to the number of target domain data and also effective in vanilla unsupervised domain adaptation setting with full target domain data.
引用
收藏
页数:10
相关论文
共 50 条
  • [1] Blitzer J., 2006, P 2006 C EMPIRICAL M, P120
  • [2] Chen Yang, 2021, ACM MM
  • [3] Randaugment: Practical automated data augmentation with a reduced search space
    Cubuk, Ekin D.
    Zoph, Barret
    Shlens, Jonathon
    Le, Quoc, V
    [J]. 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2020), 2020, : 3008 - 3017
  • [4] Deng J, 2009, PROC CVPR IEEE, P248, DOI 10.1109/CVPRW.2009.5206848
  • [5] Du Yuntao, 2022, Intermediate prototype contrast for unsupervised domain adaptation
  • [6] Ganin Y, 2015, PR MACH LEARN RES, V37, P1180
  • [7] Gu X, 2020, PROC CVPR IEEE, P9098, DOI 10.1109/CVPR42600.2020.00912
  • [8] Deep Residual Learning for Image Recognition
    He, Kaiming
    Zhang, Xiangyu
    Ren, Shaoqing
    Sun, Jian
    [J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 770 - 778
  • [9] Supervised Domain Adaptation: A Graph Embedding Perspective and a Rectified Experimental Protocol
    Hedegaard, Lukas
    Sheikh-Omar, Omar Ali
    Iosifidis, Alexandros
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 30 : 8619 - 8631
  • [10] Adversarial Feature Augmentation for Cross-domain Few-Shot Classification
    Hu, Yanxu
    Ma, Andy J.
    [J]. COMPUTER VISION, ECCV 2022, PT XX, 2022, 13680 : 20 - 37