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
  • [1] Fast Hierarchical Learning for Few-Shot Object Detection
    She, Yihang
    Bhat, Goutam
    Danelljan, Martin
    Yu, Fisher
    2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2022, : 1993 - 2000
  • [2] Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark
    Lee, Kibok
    Yang, Hao
    Chakraborty, Satyaki
    Cai, Zhaowei
    Swaminathan, Gurumurthy
    Ravichandran, Avinash
    Dabeer, Onkar
    COMPUTER VISION, ECCV 2022, PT XX, 2022, 13680 : 366 - 382
  • [3] A Few-Shot Object Detection Method for Endangered Species
    Yan, Hongmei
    Ruan, Xiaoman
    Zhu, Daixian
    Kong, Haoran
    Liu, Peixuan
    APPLIED SCIENCES-BASEL, 2024, 14 (11):
  • [4] Few-Shot Object Detection: A Survey
    Antonelli, Simone
    Avola, Danilo
    Cinque, Luigi
    Crisostomi, Donato
    Foresti, Gian Luca
    Galasso, Fabio
    Marini, Marco Raoul
    Mecca, Alessio
    Pannone, Daniele
    ACM COMPUTING SURVEYS, 2022, 54 (11S)
  • [5] Few-Shot Object Counting and Detection
    Thanh Nguyen
    Chau Pham
    Khoi Nguyen
    Minh Hoai
    COMPUTER VISION, ECCV 2022, PT XX, 2022, 13680 : 348 - 365
  • [6] Few-Shot Video Object Detection
    Fan, Qi
    Tang, Chi-Keung
    Tai, Yu-Wing
    COMPUTER VISION, ECCV 2022, PT XX, 2022, 13680 : 76 - 98
  • [7] Few-Shot Object Detection of drones
    Zou Weibao
    Liu Xindi
    Yang Jitao
    Qu Wei
    INTERNATIONAL CONFERENCE ON ELECTRICAL, COMPUTER AND ENERGY TECHNOLOGIES (ICECET 2021), 2021, : 1030 - 1034
  • [8] Few-Shot Object Detection Method Based on Knowledge Reasoning
    Wang, Jianwei
    Chen, Deyun
    ELECTRONICS, 2022, 11 (09)
  • [9] Few-shot Object Detection as a Semi-supervised Learning Problem
    Bailer, Werner
    Fassold, Hannes
    19TH INTERNATIONAL CONFERENCE ON CONTENT-BASED MULTIMEDIA INDEXING, CBMI 2022, 2022, : 131 - 135
  • [10] Multiscale Dynamic Attention and Hierarchical Spatial Aggregation for Few-Shot Object Detection
    An, Yining
    Song, Chunlin
    APPLIED SCIENCES-BASEL, 2025, 15 (03):