Explaining Contrasting Categories (2018)

by Michael Pazzani, Amir Feghahati, Christian Shelton, and Aaron Seitz

Abstract: This paper describes initial progress in deep learning capable not only of fine-grained categorization tasks, such as whether an image of bird is a Western Grebe or a Clark’s Grebe, but also explaining contrasts to make them understandable. Knowledge-discovery in databases has been described as the process of identifying valid, novel, potentially useful, and ultimately understandable patterns in data [1]. In spite of this, much of machine learning has focused on “valid” and “useful” with little attention paid to “understandable” [2-6]. Recent work in deep learning has showed remarkable accuracy on a wide range of tasks [7], but produces models that are more difficult to interpret than most earlier approaches to artificial intelligence and machine learning. Our ultimate goal is to learn to annotate images to explain the difference between contrasting categories as found in bird guides or medical books.

Download Information

Michael Pazzani, Amir Feghahati, Christian Shelton, and Aaron Seitz (2018). "Explaining Contrasting Categories." IUI Workshop on Explainable Smart Systems.

Bibtex citation

@inproceedings{Pazetal18,
   author = "Michael Pazzani and Amir Feghahati and Christian Shelton and Aaron Seitz",
   title = "Explaining Contrasting Categories",
   booktitle = "IUI Workshop on Explainable Smart Systems",
   year = 2018,
}

---

full list