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
  • [21] Balanced Contrastive Learning for Long-Tailed Visual Recognition
    Zhu, Jianggang
    Wang, Zheng
    Chen, Jingjing
    Chen, Yi-Ping Phoebe
    Jiang, Yu-Gang
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 6898 - 6907
  • [22] Exploring the auxiliary learning for long-tailed visual recognition
    Zhang, Junjie
    Liu, Lingqiao
    Wang, Peng
    Zhang, Jian
    NEUROCOMPUTING, 2021, 449 : 303 - 314
  • [23] Feature Bias Correction: A Feature Augmentation Method for Long-tailed Recognition
    Yang, Jiaxin
    Li, Xiaofei
    Zhang, Jun
    Li, Shuohao
    2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME, 2023, : 558 - 563
  • [24] Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distribution
    Chen, Jiahao
    Su, Bing
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 19978 - 19987
  • [25] Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective
    Xu, Zhengzhuo
    Chai, Zenghao
    Yuan, Chun
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021,
  • [26] Key Point Sensitive Loss for Long-Tailed Visual Recognition
    Li, Mengke
    Cheung, Yiu-Ming
    Hu, Zhikai
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (04) : 4812 - 4825
  • [27] Dynamic Learnable Logit Adjustment for Long-Tailed Visual Recognition
    Zhang, Enhao
    Geng, Chuanxing
    Li, Chaohua
    Chen, Songcan
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (09) : 7986 - 7997
  • [28] Balanced clustering contrastive learning for long-tailed visual recognition
    Kim, Byeong-il
    Ko, Byoung Chul
    PATTERN ANALYSIS AND APPLICATIONS, 2025, 28 (01)
  • [29] Adaptive Logit Adjustment Loss for Long-Tailed Visual Recognition
    Zhao, Yan
    Chen, Weicong
    Tan, Xu
    Huang, Kai
    Zhu, Jihong
    THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 3472 - 3480
  • [30] Hierarchical block aggregation network for long-tailed visual recognition
    Pang, Shanmin
    Wang, Weiye
    Zhang, Renzhong
    Hao, Wenyu
    NEUROCOMPUTING, 2023, 549