Feature Fusion from Head to Tail for Long-Tailed Visual Recognition

被引:0
|
作者
Li, Mengke [1 ,2 ]
Hu, Zhikai [3 ]
Lu, Yang [4 ]
Lan, Weichao [3 ]
Cheung, Yiu-ming [3 ]
Huang, Hui [2 ]
机构
[1] Guangdong Lab Artificial Intelligence & Digital E, Shenzhen, Peoples R China
[2] Shenzhen Univ, Coll Comp Sci & Software Engn, Shenzhen, Peoples R China
[3] Hong Kong Baptist Univ, Dept Comp Sci, Hong Kong, Peoples R China
[4] Xiamen Univ, Sch Informat, Fujian Key Lab Sensing & Comp Smart City, Xiamen, Peoples R China
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
The imbalanced distribution of long-tailed data presents a considerable challenge for deep learning models, as it causes them to prioritize the accurate classification of head classes but largely disregard tail classes. The biased decision boundary caused by inadequate semantic information in tail classes is one of the key factors contributing to their low recognition accuracy. To rectify this issue, we propose to augment tail classes by grafting the diverse semantic information from head classes, referred to as head-to-tail fusion (H2T). We replace a portion of feature maps from tail classes with those belonging to head classes. These fused features substantially enhance the diversity of tail classes. Both theoretical analysis and practical experimentation demonstrate that H2T can contribute to a more optimized solution for the decision boundary. We seamlessly integrate H2T in the classifier adjustment stage, making it a plug-and-play module. Its simplicity and ease of implementation allow for smooth integration with existing long-tailed recognition methods, facilitating a further performance boost. Extensive experiments on various long-tailed benchmarks demonstrate the effectiveness of the proposed H2T. The source code is available at https://github.com/Keke921/H2T.
引用
收藏
页码:13581 / 13589
页数:9
相关论文
共 50 条
  • [1] Feature fusion network for long-tailed visual recognition
    Zhou, Xuesong
    Zhai, Junhai
    Cao, Yang
    PATTERN RECOGNITION, 2023, 144
  • [2] Semantic Transfer from Head to Tail: Enlarging Tail Margin for Long-Tailed Visual Recognition
    Zhang, Shan
    Ni, Yao
    Du, Jinhao
    Liu, Yanxia
    Koniusz, Piotr
    2024 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION, WACV 2024, 2024, : 1339 - 1349
  • [3] Feature calibration and feature separation for long-tailed visual recognition
    Wang, Qianqian
    Zhou, Fangyu
    Zhao, Xiangge
    Lin, Yangtao
    Ye, Haibo
    NEUROCOMPUTING, 2025, 637
  • [4] Attentive Feature Augmentation for Long-Tailed Visual Recognition
    Wang, Weiqiu
    Zhao, Zhicheng
    Wang, Pingyu
    Su, Fei
    Meng, Hongying
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 32 (09) : 5803 - 5816
  • [5] Feature Re-Balancing for Long-Tailed Visual Recognition
    Zhao, Yan
    Chen, Weicong
    Huang, Kai
    Zhu, Jihong
    2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
  • [6] FCC: Feature Clusters Compression for Long-Tailed Visual Recognition
    Li, Jian
    Meng, Ziyao
    Shi, Daqian
    Song, Rui
    Diao, Xiaolei
    Wang, Jingwen
    Xu, Hao
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 24080 - 24089
  • [7] A Survey on Long-Tailed Visual Recognition
    Yang, Lu
    Jiang, He
    Song, Qing
    Guo, Jun
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2022, 130 (07) : 1837 - 1872
  • [8] A Survey on Long-Tailed Visual Recognition
    Lu Yang
    He Jiang
    Qing Song
    Jun Guo
    International Journal of Computer Vision, 2022, 130 : 1837 - 1872
  • [9] Exploiting the Tail Data for Long-Tailed Face Recognition
    Song, Guo
    Liu, Rujie
    Wang, Mengjiao
    Meng, Zhang
    Nie, Shijie
    Lina, Septiana
    Abe, Narishige
    IEEE ACCESS, 2022, 10 : 97945 - 97953
  • [10] Shrink, Separate and Aggregate: A Feature Balancing Method for Long-tailed Visual Recognition
    Yang J.-X.
    Yu M.-M.
    Li H.-Y.
    Li S.-H.
    Fan L.-Y.
    Zhang J.
    Zidonghua Xuebao/Acta Automatica Sinica, 2024, 50 (05): : 898 - 910