Corpus ID: 221136065

RODEO: Replay for Online Object Detection

@article{Acharya2020RODEORF,
  title={RODEO: Replay for Online Object Detection},
  author={Manoj Acharya and T. Hayes and Christopher Kanan},
  journal={ArXiv},
  year={2020},
  volume={abs/2008.06439}
}
  • Manoj Acharya, T. Hayes, Christopher Kanan
  • Published 2020
  • Computer Science
  • ArXiv
  • Humans can incrementally learn to do new visual detection tasks, which is a huge challenge for today’s computer vision systems. Incrementally trained deep learning models lack backwards transfer to previously seen classes and suffer from a phenomenon known as “catastrophic forgetting.” In this paper, we pioneer online streaming learning for object detection, where an agent must learn examples one at a time with severe memory and computational constraints. In object detection, a system must… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 64 REFERENCES
    Fine-Grained Continual Learning
    • 13
    RILOD: near real-time incremental learning for object detection at the edge
    • 6
    You Only Look Once: Unified, Real-Time Object Detection
    • 8,756
    • PDF
    Incremental Learning of Object Detectors without Catastrophic Forgetting
    • 127
    • Highly Influential
    • PDF
    Incremental Deep Learning for Robust Object Detection in Unknown Cluttered Environments
    • 9
    • PDF
    Learning without Forgetting
    • 739
    • PDF
    An End-to-End Architecture for Class-Incremental Object Detection with Knowledge Distillation
    • 10
    Memory Efficient Experience Replay for Streaming Learning
    • 40
    • PDF
    SSD: Single Shot MultiBox Detector
    • 8,246
    • PDF
    The Pascal Visual Object Classes (VOC) Challenge
    • 8,171
    • PDF