Corpus ID: 220128140

MMF: A loss extension for feature learning in open set recognition

@article{Jia2020MMFAL,
  title={MMF: A loss extension for feature learning in open set recognition},
  author={Jingyun Jia and Philip K. Chan},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.15117}
}
  • Jingyun Jia, Philip K. Chan
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • Open set recognition (OSR) is the problem of classifying the known classes, meanwhile identifying the unknown classes when the collected samples cannot exhaust all the classes. There are many applications for the OSR problem. For instance, the frequently emerged new malware classes require a system that can classify the known classes and identify the unknown malware classes. In this paper, we propose an add-on extension for loss functions in neural networks to address the OSR problem. Our loss… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 25 REFERENCES
    Co-Representation Learning For Classification and Novel Class Detection via Deep Networks
    2
    Learning a Neural-network-based Representation for Open Set Recognition
    17
    Generative OpenMax for Multi-Class Open Set Classification
    51
    Open Set Domain Adaptation by Backpropagation
    90
    Unseen Class Discovery in Open-world Classification
    20
    Towards Open Set Deep Networks
    306
    Open Set Learning with Counterfactual Images
    36
    ODN: Opening the Deep Network for Open-Set Action Recognition
    10