Augmentation-induced Consistency Regularization for Classification

被引:0
|
作者
Wu, Jianhan [1 ,2 ]
Si, Shijing [1 ]
Wang, Jianzong [1 ]
Xiao, Jing [1 ]
机构
[1] Ping Technol Shenzhen Co Ltd, Shenzhen, Peoples R China
[2] Univ Sci & Technol China, Hefei, Peoples R China
关键词
consistency regularization; data augmentation; over-fitting; stop-gradient;
D O I
10.1109/IJCNN55064.2022.9892448
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deep neural networks have become popular in many supervised learning tasks, but they may suffer from overfitting when the training dataset is limited. To mitigate this, many researchers use data augmentation, which is a widely used and effective method for increasing the variety of datasets. However, the randomness introduced by data augmentation causes inevitable inconsistency between training and inference, which leads to poor improvement. In this paper, we propose a consistency regularization framework based on data augmentation, called CR-Aug, which forces the output distributions of different sub models generated by data augmentation to be consistent with each other. Specifically, CR-Aug evaluates the discrepancy between the output distributions of two augmented versions of each sample, and it utilizes a stop-gradient operation to minimize the consistency loss. We implement CR-Aug to image and audio classification tasks and conduct extensive experiments to verify its effectiveness in improving the generalization ability of classifiers. Our CR-Aug framework is ready-to-use, it can be easily adapted to many state-of-the-art network architectures. Our empirical results show that CR-Aug outperforms baseline methods by a significant margin.
引用
收藏
页数:7
相关论文
共 50 条
  • [21] Conditional Consistency Regularization for Semi-Supervised Multi-Label Image Classification
    Wu, Zhengning
    He, Tianyu
    Xia, Xiaobo
    Yu, Jun
    Shen, Xu
    Liu, Tongliang
    IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 26 : 4206 - 4216
  • [22] Improved Consistency Regularization for GANs
    Zhao, Zhengli
    Singh, Sameer
    Lee, Honglak
    Zhang, Zizhao
    Odena, Augustus
    Zhang, Han
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 11033 - 11041
  • [23] White Blood Cell Classification Using Multi-Attention Data Augmentation and Regularization
    Bayat, Nasrin
    Davey, Diane D. D.
    Coathup, Melanie
    Park, Joon-Hyuk
    BIG DATA AND COGNITIVE COMPUTING, 2022, 6 (04)
  • [24] VARIABLE SELECTION FOR CLASSIFICATION WITH DERIVATIVE-INDUCED REGULARIZATION
    He, Xin
    Lv, Shaogao
    Wang, Junhui
    STATISTICA SINICA, 2020, 30 (04) : 2075 - 2103
  • [25] Local augmentation based consistency learning for semi-supervised pathology image classification
    Su, Lei
    Wang, Zhi
    Shi, Yi
    Li, Ao
    Wang, Minghui
    COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2023, 232
  • [26] EICO: Improving Few-Shot Text Classification via Explicit and Implicit Consistency Regularization
    Zhao, Lei
    Yao, Cheng
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), 2022, : 3582 - 3587
  • [27] Asthma phenotypes: Consistency of classification using induced sputum
    Hancox, Robert J.
    Cowan, Douglas C.
    Aldridge, Ruth E.
    Cowan, Jan O.
    Palmay, Rochelle
    Williamson, Avis
    Town, G. Ian
    Taylor, D. Robin
    RESPIROLOGY, 2012, 17 (03) : 461 - 466
  • [28] INTERMIX: AN INTERFERENCE-BASED DATA AUGMENTATION AND REGULARIZATION TECHNIQUE FOR AUTOMATIC DEEP SOUND CLASSIFICATION
    Sawhney, Ramit
    Neerkaje, Atula Tejaswi
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 3443 - 3447
  • [29] Graph contrastive learning with consistency regularization
    Lee, Soohong
    Lee, Sangho
    Lee, Jaehwan
    Lee, Woojin
    Son, Youngdoo
    PATTERN RECOGNITION LETTERS, 2024, 181 : 43 - 49
  • [30] Double Consistency Regularization for Transformer Networks
    Wan, Yuxian
    Zhang, Wenlin
    Li, Zhen
    ELECTRONICS, 2023, 12 (20)