Laser & Optoelectronics Progress, Volume. 58, Issue 2, 0215003(2021)

Multiscale Feature Fusion-Based Object Detection Algorithm

Tao Zhang and Le Zhang*
Author Affiliations
  • School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
  • show less
    Figures & Tables(10)
    Network structure based on multi-scale feature fusion
    Network structure of different feature fusion modules. (a) FPN module; (b) LFF module; (c) HFF module
    Loss function curves before and after adding feature fusion module. (a) Before adding; (b) after adding
    Detection results before and after adding feature fusion module. (a) Before adding; (b) after adding
    • Table 1. mAP values of different detection algorithms on PASCAL VOC dataset

      View table

      Table 1. mAP values of different detection algorithms on PASCAL VOC dataset

      AlgorithmBackbone networkmAP /%
      SSD300VGG-1669.7
      RetinaNetResNet-5070.2
      Libra RetinaNetResNet-5070.4
      Proposed algorithmResNet-5072.6
    • Table 2. AP values of different categories unit: %

      View table

      Table 2. AP values of different categories unit: %

      CategorySSD300RetinaNetLibra RetinaNetProposed algorithm
      Aero75.775.475.477.4
      Bike78.480.279.680.1
      Bird67.272.172.173.5
      Boat64.460.764.867.3
      Bottle38.939.437.943.1
      Bus79.978.979.481.1
      Car83.379.079.080.3
      Cat84.686.485.187.4
      Chair49.552.552.654.9
      Cow67.164.168.074.1
      CategorySSD300RetinaNetLibra RetinaNetProposed algorithm
      Table63.767.766.568.5
      Dog79.280.180.582.2
      Horse80.579.478.981.4
      Mbike79.778.278.179.7
      Person75.274.274.575.6
      Plant37.243.042.345.3
      Sheep69.968.470.470.9
      Sofa68.571.371.372.0
      Train81.683.183.784.1
      TV69.370.368.872.7
    • Table 3. Results of ablation study

      View table

      Table 3. Results of ablation study

      HFF moduleLFF modulemAP /%
      70.4
      72.0
      72.2
      72.6
    • Table 4. AP values of each category after ablation learning unit: %

      View table

      Table 4. AP values of each category after ablation learning unit: %

      CategoryLFF moduleHFF module
      Aero76.577.9
      Bike80.280.5
      Bird74.172.6
      Boat66.066.6
      Bottle40.741.9
      Bus78.782.4
      Car80.279.4
      Cat86.186.8
      Chair54.953.2
      Cow70.969.2
      Table70.268.3
      Dog82.282.2
      Horse82.582.5
      CategoryLFF moduleHFF module
      Mbike79.280.5
      Person75.075.0
      Plant44.745.0
      Sheep69.870.7
      Sofa73.573.3
      Train83.983.4
      TV70.571.6
    • Table 5. AP values of different detection algorithms on MSCOCO dataset unit: %

      View table

      Table 5. AP values of different detection algorithms on MSCOCO dataset unit: %

      AlgorithmBackboneAPAP50AP75APSAPMAPL
      SSD512VGG-1625.744.126.69.229.039.0
      RetinaNetResNet-5035.655.638.120.839.546.1
      Libra RetinaNetResNet-5037.556.939.922.441.449.2
      Proposed algorithmResNet-5038.858.541.322.942.650.4
      RetinaNetResNet-10137.857.540.820.942.149.6
      Libra RetinaNetResNet-10139.158.641.722.643.851.4
      Proposed algorithmResNet-10140.359.942.923.144.853.3
    • Table 6. Results after ablation learning on COCO val-2017 unit: %

      View table

      Table 6. Results after ablation learning on COCO val-2017 unit: %

      HFF moduleLFF moduleAPAP50AP75APSAPMAPL
      37.556.939.922.441.449.2
      38.558.341.022.442.650.2
      38.558.440.923.842.449.7
      38.858.541.322.942.650.4
    Tools

    Get Citation

    Copy Citation Text

    Tao Zhang, Le Zhang. Multiscale Feature Fusion-Based Object Detection Algorithm[J]. Laser & Optoelectronics Progress, 2021, 58(2): 0215003

    Download Citation

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

    Category: Machine Vision

    Received: Jun. 2, 2020

    Accepted: Jul. 3, 2020

    Published Online: Jan. 11, 2021

    The Author Email: Zhang Le (Polaris963@163.com)

    DOI:10.3788/LOP202158.0215003

    Topics