SIDU: Similarity Difference and Uniqueness Method for Explainable AI

@article{Muddamsetty2020SIDUSD,
  title={SIDU: Similarity Difference and Uniqueness Method for Explainable AI},
  author={Satya M. Muddamsetty and M. S. Jahromi and T. Moeslund},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.03122}
}
  • Satya M. Muddamsetty, M. S. Jahromi, T. Moeslund
  • Published 2020
  • Mathematics, Computer Science
  • ArXiv
  • A new brand of technical artificial intelligence ( Explainable AI ) research has focused on trying to open up the 'black box' and provide some explainability. This paper presents a novel visual explanation method for deep learning networks in the form of a saliency map that can effectively localize entire object regions. In contrast to the current state-of-the art methods, the proposed method shows quite promising visual explanations that can gain greater trust of human expert. Both… 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 19 REFERENCES
    Learning Deep Features for Discriminative Localization
    • 2,602
    • PDF
    RISE: Randomized Input Sampling for Explanation of Black-box Models
    • 121
    • Highly Influential
    • PDF
    Understanding Deep Networks via Extremal Perturbations and Smooth Masks
    • 35
    • PDF
    Visualizing and Understanding Convolutional Networks
    • 8,439
    • PDF
    Optimizing for Interpretability in Deep Neural Networks with Tree Regularization
    • 4
    • PDF
    From captions to visual concepts and back
    • 939
    • PDF
    Embodied Question Answering
    • 222
    • PDF
    Deep Residual Learning for Image Recognition
    • 51,641
    • PDF