Project Presentation about "The Object-Centric Concept Learner - An Interpretable Framework for Learning Relational Visual Concepts" by David Tafler

Project Presentation about "The Object-Centric Concept Learner - An Interpretable Framework for Learning Relational Visual Concepts" by David Tafler

napisao/la Bettina Finzel -
Number of replies: 0
Dear all,

you are cordially invited to join the final project presentation of David Tafler on 14.11.2022 at 16 s.t. . You can join via Zoom as indicated in the course details.


Topic: The Object-Centric Concept Learner - An Interpretable Framework for Learning Relational Visual Concepts

Abstract:
Learning relational visual concepts in an interpretable fashion is a challenge for pure deep learning approaches. This paper proposes a framework as part of a solution to this problem by combining deep learning methods of object detection with inductive logic programming (ILP) to train a visual concept learner. Object detection provides the basis for object-centric representations of images that are then used to inductively learn a classification rule. The paper further presents algorithms to explain any classification of the trained model by visualizing what a nearby example of the opposite class in the decision space could look like. An example concept from the domain of Kandinsky-Patterns is used to explain the framework and to provide a first evaluation in terms of performance, interpretability, and data-efficiency.