Novelty Detection via Network Saliency in Visual-Based Deep Learning

@article{Chen2019NoveltyDV,
  title={Novelty Detection via Network Saliency in Visual-Based Deep Learning},
  author={V. Chen and Man-Ki Yoon and Z. Shao},
  journal={2019 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)},
  year={2019},
  pages={52-57}
}
  • V. Chen, Man-Ki Yoon, Z. Shao
  • Published 2019
  • Computer Science, Mathematics
  • 2019 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)
  • Machine-learning driven safety-critical autonomous systems, such as self-driving cars, must be able to detect situations where its trained model is not able to make a trustworthy prediction. Often viewed as a black-box, it is non-obvious to determine when a model will make a safe decision and when it will make an erroneous, perhaps life-threatening one. Prior work on novelty detection deal with highly structured data and do not translate well to dynamic, real-world situations. This paper… CONTINUE READING
    2 Citations
    Task-Aware Novelty Detection for Visual-based Deep Learning in Autonomous Systems
    • Highly Influenced
    • PDF
    Non-Markov Policies to Reduce Sequential Failures in Robot Bin Picking
    • 3
    • PDF

    References

    SHOWING 1-10 OF 16 REFERENCES
    Safe Visual Navigation via Deep Learning and Novelty Detection
    • 99
    • Highly Influential
    • PDF
    VisualBackProp: Efficient Visualization of CNNs for Autonomous Driving
    • 21
    • Highly Influential
    End to End Learning for Self-Driving Cars
    • 1,985
    • PDF
    DeepTest: Automated Testing of Deep-Neural-Network-Driven Autonomous Cars
    • 466
    • PDF
    Adversarially Learned One-Class Classifier for Novelty Detection
    • 196
    • PDF
    On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
    • 1,276
    • PDF
    A Rotation and a Translation Suffice: Fooling CNNs with Simple Transformations
    • 208
    • PDF
    A Novelty Detection Approach to Classification
    • 374
    • PDF
    Adversarial examples in the physical world
    • 2,186
    • PDF