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
  • [41] Prototype-based classifier learning for long-tailed visual recognition
    Wei, Xiu-Shen
    Xu, Shu-Lin
    Chen, Hao
    Xiao, Liang
    Peng, Yuxin
    SCIENCE CHINA-INFORMATION SCIENCES, 2022, 65 (06)
  • [42] Class-Difficulty Based Methods for Long-Tailed Visual Recognition
    Sinha, Saptarshi
    Ohashi, Hiroki
    Nakamura, Katsuyuki
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2022, 130 (10) : 2517 - 2531
  • [43] Mutual Learning for Long-Tailed Recognition
    Park, Changhwa
    Yim, Junho
    Jun, Eunji
    2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 2674 - 2683
  • [44] Dual-branch network with hypergraph feature augmentation and adaptive logits adjustment for long-tailed visual recognition
    Han, Jia-yi
    Liu, Jian-wei
    Xu, Jing-dong
    APPLIED SOFT COMPUTING, 2024, 167
  • [45] Multimodal Framework for Long-Tailed Recognition
    Chen, Jian
    Zhao, Jianyin
    Gu, Jiaojiao
    Qin, Yufeng
    Ji, Hong
    APPLIED SCIENCES-BASEL, 2024, 14 (22):
  • [46] Improving Calibration for Long-Tailed Recognition
    Zhong, Zhisheng
    Cui, Jiequan
    Liu, Shu
    Jia, Jiaya
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 16484 - 16493
  • [47] bt-vMF Contrastive and Collaborative Learning for Long-Tailed Visual Recognition
    Du, Jinhao
    Luo, Guibo
    Zhu, Yuesheng
    Bai, Zhiqiang
    2023 IEEE 35TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, ICTAI, 2023, : 573 - 577
  • [48] Handling Long-tailed Feature Distribution in AdderNets
    Dong, Minjing
    Wang, Yunhe
    Chen, Xinghao
    Xu, Chang
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [49] NCL plus plus : Nested Collaborative Learning for long-tailed visual recognition
    Tan, Zichang
    Li, Jun
    Du, Jinhao
    Wan, Jun
    Lei, Zhen
    Guo, Guodong
    PATTERN RECOGNITION, 2024, 147
  • [50] Bag of Tricks for Long-Tailed Visual Recognition with Deep Convolutional Neural Networks
    Zhang, Yongshun
    Wei, Xiu-Shen
    Zhou, Boyan
    Wu, Jianxin
    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 : 3447 - 3455