Corpus ID: 4714433

YOLOv3: An Incremental Improvement

@article{Redmon2018YOLOv3AI,
  title={YOLOv3: An Incremental Improvement},
  author={Joseph Redmon and Ali Farhadi},
  journal={ArXiv},
  year={2018},
  volume={abs/1804.02767}
}
  • Joseph Redmon, Ali Farhadi
  • Published 2018
  • Computer Science
  • ArXiv
  • We present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network that's pretty swell. It's a little bigger than last time but more accurate. It's still fast though, don't worry. At 320x320 YOLOv3 runs in 22 ms at 28.2 mAP, as accurate as SSD but three times faster. When we look at the old .5 IOU mAP detection metric YOLOv3 is quite good. It achieves 57.9 mAP@50 in 51 ms on a Titan X, compared to 57.5 mAP@50 in 198 ms by RetinaNet… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 2,672 CITATIONS, ESTIMATED 82% COVERAGE

    Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors

    VIEW 9 EXCERPTS
    CITES BACKGROUND, RESULTS & METHODS
    HIGHLY INFLUENCED

    SS-YOLO: An Object Detection Algorithm based on YOLOv3 and ShuffleNet

    • Yong Li, Can Lv
    • Computer Science
    • 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)
    • 2020
    VIEW 1 EXCERPT
    CITES METHODS

    YOLACT: Real-Time Instance Segmentation

    VIEW 5 EXCERPTS
    CITES BACKGROUND, RESULTS & METHODS
    HIGHLY INFLUENCED

    Mini-YOLOv3: Real-Time Object Detector for Embedded Applications

    VIEW 8 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    YOLACT++: Better Real-time Instance Segmentation

    VIEW 15 EXCERPTS
    CITES RESULTS, METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Scale-Aware Trident Networks for Object Detection

    SOLOv2: Dynamic, Faster and Stronger

    VIEW 1 EXCERPT
    HIGHLY INFLUENCED

    Real-time Instance Segmentation

    VIEW 10 EXCERPTS
    CITES BACKGROUND, RESULTS & METHODS
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2016
    2020

    CITATION STATISTICS

    • 605 Highly Influenced Citations

    • Averaged 887 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 23 REFERENCES

    YOLO9000: Better, Faster, Stronger

    VIEW 3 EXCERPTS

    Deep Residual Learning for Image Recognition

    Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors

    Feature Pyramid Networks for Object Detection

    VIEW 2 EXCERPTS

    Focal Loss for Dense Object Detection

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Microsoft COCO: Common Objects in Context

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL