Opto-Electronic Engineering, Volume. 50, Issue 1, 220180(2023)

Few-shot object detection via online inferential calibration

Hao Peng1...2, Wanqi Wang1,2, Long Chen1,2, Xianrong Peng1,*, Jianlin Zhang1, Zhiyong Xu1, Yuxing Wei1 and Meihui Li1 |Show fewer author(s)
Author Affiliations
  • 1Institute of Optics and Electronics, Chinese Academy of Science, Chengdu, Sichuan 610209, China
  • 2University of Chinese Academy of Science, Beijing 100049, China
  • show less
    Figures & Tables(15)
    Faster R-CNN network architecture
    FSOIC network architecture
    Detection results based on TFA
    Attention-FPN network architecture
    Channel attention module
    FSOIC algorithm class template generation module
    Feature metric space
    Performance comparison of the detection results
    Detection results under the occlusion conditions in the 10 shot task
    10 shot task detection results. (a) Detection results of the Faster R-CNN network based on TFA; (b) Detection results of the Faster R-CNN net work using the online inference calibration module; (c) Detection results of the Faster R-CNN network using the online inference calibration module and adding the Attention-FPN network
    • Table 1. Hierarchical freezing mechanism

      View table
      View in Article

      Table 1. Hierarchical freezing mechanism

      ShotBackboneRegressorClassiferAttention-FPNRPNROI
      1××××
      2×××
      3×
      5
      10
    • Table 2. Experimental settings of the dataset

      View table
      View in Article

      Table 2. Experimental settings of the dataset

      DatasetShotNumber of categoriesInitial learning rateBatch_sizeDecay ratio of learning rateNumber of attenuationIterations
      VOC1200.001160.116000
      20.117000
      30.128000
      50.529000
      100.5213000
      COCO10800.001160.3130000
      3040000
    • Table 3. Performance analysis and comparison of the few shot object detection algorithm in VOC new class partition sets

      View table
      View in Article

      Table 3. Performance analysis and comparison of the few shot object detection algorithm in VOC new class partition sets

      MethodYearNovel Set 1Novel Set 2Novel Set 3
      123510123510123510
      LSTD[26]AAAI 188.21.012.429.138.511.43.85.015.731.012.68.515.027.336.3
      MetaDet[40]ICCV 1918.920.630.236.849.621.823.127.831.743.020.623.929.443.944.1
      Meta R-CNN[15]ICCV 1919.925.535.045.751.510.419.429.634.845.414.318.227.541.248.1
      RepMet[28]CVPR 1926.132.934.438.641.317.222.123.428.335.827.531.131.534.437.2
      FSRW[37]ICCV 1914.815.526.733.947.215.715.322.730.140.521.325.628.442.845.9
      FSDetView[42]ECCV 2024.235.342.249.157.421.624.631.937.045.721.230.037.243.849.6
      TFA w/cos[44]ICML 2039.836.144.755.756.023.526.934.135.139.130.834.842.849.549.8
      MPSR[51]ECCV 2041.7-51.455.261.824.4-39.239.947.835.6-42.348.049.7
      TFA w/cos+Halluc[18]CVPR 2145.144.044.755.055.923.227.535.134.939.030.535.141.449.049.3
      TIP[41]CVPR 2127.736.543.350.259.622.730.133.840.946.921.730.638.144.550.9
      FSCE[25]CVPR 2144.243.851.461.963.427.329.543.544.250.237.241.947.554.658.5
      Retentive R-CNN[45]CVPR 2142.445.845.953.756.121.727.835.237.040.330.237.643.049.750.1
      Meta-DETR[38]IEEE 2235.149.053.257.462.027.932.338.443.251.834.941.847.154.158.2
      AGCM[33]IEEE 2240.3--58.559.927.5--49.350.642.1--54.258.2
      FSOIC(Ours)46.653.456.662.064.525.730.543.845.953.342.444.949.556.658.8
    • Table 4. Performance analysis and comparison of few shot object detection algorithms in the COCO datasets

      View table
      View in Article

      Table 4. Performance analysis and comparison of few shot object detection algorithms in the COCO datasets

      MethodYearNovel AP
      1030
      LSTD [26]AAAI 183.26.7
      FSRW [37]ICCV 195.69.1
      MPSR[51]ECCV 209.814.1
      TFA w/cos [44]ICML 2010.013.7
      Retentive R-CNN [45]CVPR 2110.513.8
      FSCE[25]CVPR 2111.916.4
      FSOIC(Ours)12.716.7
    • Table 5. Comparison of the ablation experimental performance

      View table
      View in Article

      Table 5. Comparison of the ablation experimental performance

      MethodFPN+4*ROIFinetune RPNOnline calibrationAttention of channelNovel Set1
      1310
      TFA w/cos[44]----39.844.756.0
      FSOIC(Ours)×××43.652.262.5
      FSOIC(Ours)××44.153.063.2
      FSOIC(Ours)×45.754.264.2
      FSOIC(Ours)×46.254.962.8
      FSOIC(Ours)×44.754.061.7
      FSOIC(Ours)46.656.664.5
    Tools

    Get Citation

    Copy Citation Text

    Hao Peng, Wanqi Wang, Long Chen, Xianrong Peng, Jianlin Zhang, Zhiyong Xu, Yuxing Wei, Meihui Li. Few-shot object detection via online inferential calibration[J]. Opto-Electronic Engineering, 2023, 50(1): 220180

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Article

    Received: Jul. 27, 2022

    Accepted: Dec. 29, 2022

    Published Online: Feb. 27, 2023

    The Author Email: Peng Xianrong (peng_xr@ioe.ac.cn)

    DOI:10.12086/oee.2023.220180

    Topics