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
  • [41] Few-Shot Object Detection via Metric Learning
    Zhu Min
    Zhang Chongyang
    FOURTEENTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2021), 2022, 12084
  • [42] Multiple knowledge embedding for few-shot object detection
    Gong, Xiaolin
    Cai, Youpeng
    Wang, Jian
    SIGNAL IMAGE AND VIDEO PROCESSING, 2023, 17 (05) : 2231 - 2240
  • [43] Explicit Margin Equilibrium for Few-Shot Object Detection
    Liu, Chang
    Li, Bohao
    Shi, Mengnan
    Chen, Xiaozhong
    Ye, Qixiang
    Ji, Xiangyang
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024,
  • [44] Restoring Negative Information in Few-Shot Object Detection
    Yang, Yukuan
    Wei, Fangyun
    Shi, Miaojing
    Li, Guoqi
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
  • [45] Few-Shot Object Detection via Knowledge Transfer
    Kim, Geonuk
    Jung, Hong-Gyu
    Lee, Seong-Whan
    2020 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2020, : 3564 - 3569
  • [46] Weakly Supervised Few-Shot Object Detection With DETR
    Zhang, Chenbo
    Zhang, Yinglu
    Zhang, Lu
    Zhao, Jiajia
    Guan, Jihong
    Zhou, Shuigeng
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 7, 2024, : 7015 - 7023
  • [47] Few-shot object detection via baby learning
    Vu, Anh-Khoa Nguyen
    Nguyen, Nhat-Duy
    Nguyen, Khanh-Duy
    Nguyen, Vinh-Tiep
    Ngo, Thanh Duc
    Do, Thanh-Toan
    Nguyen, Tam V.
    IMAGE AND VISION COMPUTING, 2022, 120
  • [48] Efficient Feature Enhancement for Few-Shot Object Detection
    Li, Lin
    Lei, Zhou
    Chen, Shengbo
    Xu, Qingguo
    2022 IEEE 6TH ADVANCED INFORMATION TECHNOLOGY, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (IAEAC), 2022, : 1206 - 1210
  • [49] Few-shot Object Detection with Refined Contrastive Learning
    Shangguan, Zeyu
    Huai, Lian
    Liu, Tong
    Jiang, Xingqun
    2023 IEEE 35TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, ICTAI, 2023, : 991 - 996
  • [50] Proposal Distribution Calibration for Few-Shot Object Detection
    Li, Bohao
    Liu, Chang
    Shi, Mengnan
    Chen, Xiaozhong
    Ji, Xiangyang
    Ye, Qixiang
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2025, 36 (01) : 1911 - 1918