Machine Learning Seminar presentation
Topic: Concept-based explanations for convolutional neural networks.
Speaker: Andres Posada Moreno, Institute for Data Science in Mechanical Engineering at the RWTH Aachen University
Time: Wednesday, 2022.11.30 10:00 am CET
How to join: Please contact Jakub Lengiewicz
Format: 30′ presentation + 30′ discussion
Convolutional neural networks (CNNs) are increasingly being used in critical systems, where robustness and alignment are crucial. In this context, the field of explainable artificial intelligence has proposed the generation of high-level explanations of the prediction process of CNNs through concept extraction. While these methods can detect whether or not a concept is present in an image, they are unable to determine its location. What is more, a fair comparison of such approaches is difficult due to a lack of proper validation procedures. In this talk, we discuss a novel method for automatic concept extraction and localization based on representations obtained through pixel-wise aggregations of CNN activation maps. Further, we introduce a process for the validation of concept-extraction techniques based on synthetic datasets with pixel-wise annotations of their main components, reducing the need for human intervention.
Video recording: https://youtu.be/7G8irCS7RpA
– powerpoint slideshow: https://drive.google.com/file/d/1u_kgBZ5VEdbTjdwCfwPU6JEcrQljnQTo/view?usp=share_link
Reference paper: https://arxiv.org/abs/2206.04531