YOLO9000: Better, Faster, Stronger

@article{Redmon2017YOLO9000BF,
  title={YOLO9000: Better, Faster, Stronger},
  author={Joseph Redmon and Ali Farhadi},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={6517-6525}
}
  • Joseph Redmon, Ali Farhadi
  • Published 2017
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • We introduce YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories. [...] Key Method The improved model, YOLOv2, is state-of-the-art on standard detection tasks like PASCAL VOC and COCO. Using a novel, multi-scale training method the same YOLOv2 model can run at varying sizes, offering an easy tradeoff between speed and accuracy. At 67 FPS, YOLOv2 gets 76.8 mAP on VOC 2007. At 40 FPS, YOLOv2 gets 78.6 mAP, outperforming state-of-the-art methods like Faster…Expand Abstract
    Focal Loss for Dense Object Detection
    • 2,407
    • Highly Influenced
    • Open Access
    R-FCN-3000 at 30fps: Decoupling Detection and Classification
    • 41
    • Highly Influenced
    • Open Access
    An object detection system based on YOLO in traffic scene
    • 12
    • Highly Influenced
    Focal Loss for Dense Object Detection
    • 1,957
    • Open Access
    DetNet: A Backbone network for Object Detection
    • 94
    • Highly Influenced
    • Open Access
    YOLOv3: An Incremental Improvement
    • 3,186
    • Open Access
    Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors
    • 1,337
    • Open Access
    EfficientDet: Scalable and Efficient Object Detection
    • 100
    • Open Access

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 26 REFERENCES
    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
    • 18,216
    • Highly Influential
    • Open Access
    SSD: Single Shot MultiBox Detector
    • 8,150
    • Open Access
    ImageNet classification with deep convolutional neural networks
    • 51,801
    • Open Access
    ImageNet Classification with Deep Convolutional Neural Networks
    • 51,801
    • Open Access
    Deep Residual Learning for Image Recognition
    • 49,720
    • Open Access
    Fast R-CNN
    • 8,732
    • Highly Influential
    • Open Access
    Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
    • 4,669
    • Open Access
    Microsoft COCO: Common Objects in Context
    • 10,178
    • Open Access
    The Pascal Visual Object Classes (VOC) Challenge
    • 8,114
    • Open Access