Corpus ID: 212725404

Explainable Deep Classification Models for Domain Generalization

@article{Zunino2020ExplainableDC,
  title={Explainable Deep Classification Models for Domain Generalization},
  author={Andrea Zunino and Sarah Adel Bargal and Riccardo Volpi and Mehrnoosh Sameki and Jian-ming Zhang and Stan Sclaroff and Vittorio Murino and Kate Saenko},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.06498}
}
  • Andrea Zunino, Sarah Adel Bargal, +5 authors Kate Saenko
  • Published in ArXiv 2020
  • Computer Science
  • Conventionally, AI models are thought to trade off explainability for lower accuracy. We develop a training strategy that not only leads to a more explainable AI system for object classification, but as a consequence, suffers no perceptible accuracy degradation. Explanations are defined as regions of visual evidence upon which a deep classification network makes a decision. This is represented in the form of a saliency map conveying how much each pixel contributed to the network's decision. Our… 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 45 REFERENCES

    Microsoft COCO: Common Objects in Context

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    VisDA: The Visual Domain Adaptation Challenge

    VIEW 5 EXCERPTS

    Addressing Model Vulnerability to Distributional Shifts Over Image Transformation Sets

    Domain Generalization by Solving Jigsaw Puzzles

    Episodic Training for Domain Generalization

    VIEW 1 EXCERPT

    Predicting Intentions from Motion: The Subject-Adversarial Adaptation Approach

    VIEW 1 EXCERPT

    Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded

    Adversarial Complementary Learning for Weakly Supervised Object Localization

    VIEW 1 EXCERPT