Hierarchical Few-Shot Object Detection: Problem, Benchmark and Method

被引:6
|
作者
Zhang, Lu [1 ]
Wang, Yang [2 ]
Zhou, Jiaogen [3 ]
Zhang, Chenbo [1 ]
Zhang, Yinglu [1 ]
Guan, Jihong [2 ]
Bian, Yatao [4 ]
Zhou, Shuigeng [1 ]
机构
[1] Fudan Univ, Shanghai, Peoples R China
[2] Tongji Univ, Shanghai, Peoples R China
[3] Huaiyin Normal Univ, Sch Urban & Environm Sci, Huaian, Peoples R China
[4] Tencent AI Lab, Shenzhen, Peoples R China
关键词
Few-shot object detection; hierarchical few-shot object detection; Benchmark; hierarchical classification;
D O I
10.1145/3503161.3548412
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Few-shot object detection (FSOD) is to detect objects with a few examples. However, existing FSOD methods do not consider hierarchical fine-grained category structures of objects that exist widely in real life. For example, animals are taxonomically classified into orders, families, genera and species etc. In this paper, we propose and solve a new problem called hierarchical few-shot object detection (Hi-FSOD), which aims to detect objects with hierarchical categories in the FSOD paradigm. To this end, on the one hand, we build the first large-scale and high-quality Hi-FSOD benchmark dataset HiFSOD-Bird, which contains 176,350 wild-bird images falling to 1,432 categories. All the categories are organized into a 4-level taxonomy, consisting of 32 orders, 132 families, 572 genera and 1,432 species. On the other hand, we propose the first Hi-FSOD method HiCLPL, where a hierarchical contrastive learning approach is developed to constrain the feature space so that the feature distribution of objects is consistent with the hierarchical taxonomy and the model's generalization power is strengthened. Meanwhile, a probabilistic loss is designed to enable the child nodes to correct the classification errors of their parent nodes in the taxonomy. Extensive experiments on the benchmark dataset HiFSOD-Bird show that our method HiCLPL outperforms the existing FSOD methods.
引用
收藏
页码:2002 / 2011
页数:10
相关论文
共 50 条
  • [21] Industrial few-shot fractal object detection
    Haoran Huang
    Xiaochuan Luo
    Chen Yang
    Neural Computing and Applications, 2023, 35 : 21055 - 21069
  • [22] Transformation Invariant Few-Shot Object Detection
    Li, Aoxue
    Li, Zhenguo
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 3093 - 3101
  • [23] Few-Shot Object Detection with Weight Imprinting
    Dingtian Yan
    Jitao Huang
    Hai Sun
    Fuqiang Ding
    Cognitive Computation, 2023, 15 : 1725 - 1735
  • [24] Few-Shot Object Detection with Foundation Models
    Han, Guangxing
    Lim, Ser-Nam
    2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2024, : 28608 - 28618
  • [25] Few-Shot Object Detection in Unseen Domains
    Guirguis, Karim
    Eskandar, George
    Kayser, Matthias
    Yang, Bin
    Beyerer, Juergen
    2022 16TH INTERNATIONAL CONFERENCE ON SIGNAL-IMAGE TECHNOLOGY & INTERNET-BASED SYSTEMS, SITIS, 2022, : 98 - 107
  • [26] Focus the Overlapping Problem on Few-Shot Object Detection via Multiple Predictions
    Guan, Mandan
    Yu, Wenqing
    Guo, Yurong
    Huang, Keyan
    Zhang, Jiaxun
    Liang, Kongming
    Ma, Zhanyu
    PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT II, 2024, 14426 : 427 - 439
  • [27] IMPROVING FEW-SHOT OBJECT DETECTION WITH OBJECT PART PROPOSALS
    Chevalley, Arthur
    Tomoiaga, Ciprian
    Detyniecki, Marcin
    Russwurm, Marc
    Tuia, Devis
    IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2023, : 6502 - 6505
  • [28] Few-Shot Object Detection via Association and DIscrimination
    Cao, Yuhang
    Wang, Jiaqi
    Jin, Ying
    Wu, Tong
    Chen, Kai
    Liu, Ziwei
    Lin, Dahua
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [29] Dynamic relevance learning for few-shot object detection
    Liu, Weijie
    Cai, Xiaojie
    Wang, Chong
    Li, Haohe
    Yu, Shenghao
    SIGNAL IMAGE AND VIDEO PROCESSING, 2025, 19 (04)
  • [30] A Survey on Recent Advances in Few-Shot Object Detection
    Shi Y.-Y.
    Shi D.-X.
    Qiao Z.-T.
    Zhang Y.
    Liu Y.-Y.
    Yang S.-W.
    Jisuanji Xuebao/Chinese Journal of Computers, 2023, 46 (08): : 1753 - 1780