In defense of local descriptor-based few-shot object detection

被引:0
|
作者
Zhou, Shichao [1 ]
Li, Haoyan [1 ]
Wang, Zhuowei [1 ]
Zhang, Zekai [1 ]
机构
[1] Beijing Informat Sci & Technol Univ, Key Lab Informat & Commun Syst, Minist Informat Ind, Beijing, Peoples R China
基金
中国国家自然科学基金;
关键词
few-shot learning; local descriptors; contextual features; kernel method; visual similarity;
D O I
10.3389/fnins.2024.1349204
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
State-of-the-art image object detection computational models require an intensive parameter fine-tuning stage (using deep convolution network, etc). with tens or hundreds of training examples. In contrast, human intelligence can robustly learn a new concept from just a few instances (i.e., few-shot detection). The distinctive perception mechanisms between these two families of systems enlighten us to revisit classical handcraft local descriptors (e.g., SIFT, HOG, etc.) as well as non-parametric visual models, which innately require no learning/training phase. Herein, we claim that the inferior performance of these local descriptors mainly results from a lack of global structure sense. To address this issue, we refine local descriptors with spatial contextual attention of neighbor affinities and then embed the local descriptors into discriminative subspace guided by Kernel-InfoNCE loss. Differing from conventional quantization of local descriptors in high-dimensional feature space or isometric dimension reduction, we actually seek a brain-inspired few-shot feature representation for the object manifold, which combines data-independent primitive representation and semantic context learning and thus helps with generalization. The obtained embeddings as pattern vectors/tensors permit us an accelerated but non-parametric visual similarity computation as the decision rule for final detection. Our approach to few-shot object detection is nearly learning-free, and experiments on remote sensing imageries (approximate 2-D affine space) confirm the efficacy of our model.
引用
收藏
页数:10
相关论文
共 50 条
  • [21] Open-World Few-Shot Object Detection
    Chen, Wei
    Zhang, Shengchuan
    ADVANCED INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS, ICIC 2023, PT I, 2023, 14086 : 556 - 567
  • [22] Few-Shot Learning for Monocular Depth Estimation based on Local Object Relationship
    Li, Shuai
    Shi, Jiaying
    Song, Wenfeng
    Hao, Aimin
    Qin, Hong
    2019 IEEE 31ST INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2019), 2019, : 1221 - 1228
  • [23] Few-Shot Object Detection with Memory Contrastive Proposal Based on Semantic Priors
    Xiao, Linlin
    Xu, Huahu
    Xiao, Junsheng
    Huang, Yuzhe
    ELECTRONICS, 2023, 12 (18)
  • [24] Dual representations network for few-shot learning based on local descriptor importance: integrating global and local features
    Chen, Xiaoying
    Ye, Weijie
    VISUAL COMPUTER, 2025, 41 (05) : 3143 - 3154
  • [25] FRDet: Few-shot object detection via feature reconstruction
    Chen, Zhihao
    Mao, Yingchi
    Qian, Yong
    Pan, Zhenxiang
    Xu, Shufang
    IET IMAGE PROCESSING, 2023, 17 (12) : 3599 - 3615
  • [26] FEW-SHOT OBJECT DETECTION WITH FOREGROUND AUGMENT AND BACKGROUND ATTENUATION
    Zeng, Ying
    Yuan, Haoliang
    PROCEEDINGS OF 2022 INTERNATIONAL CONFERENCEON WAVELET ANALYSIS AND PATTERN RECOGNITION (ICWAPR), 2022, : 42 - 47
  • [27] Making Few-Shot Object Detection Simpler and Less Frustrating
    Bailer, Werner
    MULTIMEDIA MODELING, MMM 2022, PT II, 2022, 13142 : 445 - 451
  • [28] Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild
    Xiao, Yang
    Lepetit, Vincent
    Marlet, Renaud
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (03) : 3090 - 3106
  • [29] Few-Shot Object Detection with Anti-Confusion Grouping
    Peng, Liang
    Hu, Fei
    Ye, Long
    FOURTEENTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2021), 2022, 12084
  • [30] Understanding Negative Proposals in Generic Few-Shot Object Detection
    Yan, Bowei
    Lang, Chunbo
    Cheng, Gong
    Han, Junwei
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (07) : 5818 - 5829