Enriching Visual with Verbal Explanations for Relational Concepts – Combining LIME with Aleph
| Autor: | Hannah Deininger, Ute Schmid, Michael Siebers, Johannes Rabold |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Class (computer programming)
Relation (database) business.industry Computer science 02 engineering and technology computer.software_genre Spatial relation Inductive logic programming 020204 information systems 0202 electrical engineering electronic engineering information engineering Feature (machine learning) 020201 artificial intelligence & image processing Relevance (information retrieval) Artificial intelligence Rule of inference business computer Classifier (UML) Natural language processing |
| Zdroj: | Machine Learning and Knowledge Discovery in Databases ISBN: 9783030438227 PKDD/ECML Workshops (1) |
| DOI: | 10.1007/978-3-030-43823-4_16 |
| Popis: | With the increasing number of deep learning applications, there is a growing demand for explanations. Visual explanations provide information about which parts of an image are relevant for a classifier’s decision. However, highlighting of image parts (e.g., an eye) cannot capture the relevance of a specific feature value for a class (e.g., that the eye is wide open). Furthermore, highlighting cannot convey whether the classification depends on the mere presence of parts or on a specific spatial relation between them. Consequently, we present an approach that is capable of explaining a classifier’s decision in terms of logic rules obtained by the Inductive Logic Programming system Aleph. The examples and the background knowledge needed for Aleph are based on the explanation generation method LIME. We demonstrate our approach with images of a blocksworld domain. First, we show that our approach is capable of identifying a single relation as important explanatory construct. Afterwards, we present the more complex relational concept of towers. Finally, we show how the generated relational rules can be explicitly related with the input image, resulting in richer explanations. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|