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
  • [31] Registration Based Few-Shot Anomaly Detection
    Huang, Chaoqin
    Guan, Haoyan
    Jiang, Aofan
    Zhang, Ya
    Spratling, Michael
    Wang, Yan-Feng
    COMPUTER VISION, ECCV 2022, PT XXIV, 2022, 13684 : 303 - 319
  • [32] Few-shot Insulator Defect Detection Based on Deep Information of Local Features
    Bai X.
    Xie Y.
    Zhao M.
    Wu H.
    Zhang W.
    Tan Y.
    Ye L.
    Dianwang Jishu/Power System Technology, 2024, 48 (02): : 740 - 749
  • [33] Meta-learning-based few-shot object detection for remote sensing images
    Li, Hongguang
    Wang, Yufeng
    Yang, Lichun
    Beijing Hangkong Hangtian Daxue Xuebao/Journal of Beijing University of Aeronautics and Astronautics, 2024, 50 (08): : 2503 - 2513
  • [34] Self-supervised Prototype Conditional Few-Shot Object Detection
    Kobayashi, Daisuke
    IMAGE ANALYSIS AND PROCESSING, ICIAP 2022, PT II, 2022, 13232 : 681 - 692
  • [35] GFENet: Generalization Feature Extraction Network for Few-Shot Object Detection
    Ke, Xiao
    Chen, Qiuqin
    Liu, Hao
    Guo, Wenzhong
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (12) : 12741 - 12755
  • [36] Few-Shot Object Detection via Back Propagation and Dynamic Learning
    You, Dianlong
    Wang, Peng
    Zhang, Yi
    Wang, Ling
    Jin, Shunfu
    2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME, 2023, : 2903 - 2908
  • [37] Arbitrary Oriented Few-Shot Object Detection in Remote Sensing Images
    Wu, Wei
    Jiang, Chengeng
    Yang, Liao
    Wang, Weisheng
    Chen, Quanjun
    Zhang, Junjian
    Yang, Haiping
    Chen, Zuohui
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2024, 17 : 17930 - 17944
  • [38] 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
  • [39] Few-Shot Object Detection via Transfer Learning and Contrastive Reweighting
    Wu, Zhen
    Li, Haowei
    Zhang, Dongyu
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2023, PT VII, 2023, 14260 : 78 - 87
  • [40] 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