Ensemble-based Adaptive Single-shot Multi-box Detector

@article{Thakar2018EnsemblebasedAS,
  title={Ensemble-based Adaptive Single-shot Multi-box Detector},
  author={Viral Thakar and Walid Ahmed and Mohammad M. Soltani and Jia Yuan Yu},
  journal={2018 International Symposium on Networks, Computers and Communications (ISNCC)},
  year={2018},
  pages={1-6}
}
  • Viral Thakar, Walid Ahmed, +1 author Jia Yuan Yu
  • Published 2018
  • Computer Science
  • 2018 International Symposium on Networks, Computers and Communications (ISNCC)
  • We propose two improvements to the SSD—single shot multibox detector. First, we propose an adaptive approach for default box selection in SSD. This uses data to reduce the uncertainty in the selection of best aspect ratios for the default boxes and improves performance of SSD for datasets containing small and complex objects (e.g., equipments at construction sites). We do so by finding the distribution of aspect ratios of the given training dataset, and then choosing representative values… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-2 OF 2 CITATIONS

    An Object Detection Technique For Blind People in Real-Time Using Deep Neural Network

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 21 REFERENCES

    SSD: Single Shot MultiBox Detector

    VIEW 2 EXCERPTS

    Feature-fused SSD: fast detection for small objects

    VIEW 1 EXCERPT

    Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors

    VIEW 2 EXCERPTS

    YOLO9000: Better, Faster, Stronger

    Training Region-Based Object Detectors with Online Hard Example Mining

    VIEW 1 EXCERPT

    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

    VIEW 2 EXCERPTS

    Hypercolumns for object segmentation and fine-grained localization

    Fast R-CNN

    • Ross B. Girshick
    • Computer Science
    • 2015 IEEE International Conference on Computer Vision (ICCV)
    • 2015
    VIEW 1 EXCERPT