Inproceedings332: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
(kein Unterschied)

Aktuelle Version vom 2. Juli 2021, 11:57 Uhr

Right for the Right Reasons: Making Image Classification Intuitively Explainable

Right for the Right Reasons: Making Image Classification Intuitively Explainable

Published: 2021 März

Buchtitel: Advances in Information Retrieval. ECIR 2021. Lecture Notes in Computer Science
Ausgabe: 12657
Verlag: Springer, Cham

Referierte Veröffentlichung


The effectiveness of Convolutional Neural Networks (CNNs) in classifying image data has been thoroughly demonstrated. In order to explain the classification to humans, methods for visualizing classification evidence have been developed in recent years. These explanations reveal that sometimes images are classified correctly, but for the wrong reasons, i.e., based on incidental evidence. Of course, it is desirable that images are classified correctly for the right reasons, i.e., based on the actual evidence. To this end, we propose a new explanation quality metric to measure object aligned explanation in image classification which we refer to as the ObAlEx metric. Using object detection approaches, explanation approaches, and ObAlEx, we quantify the focus of CNNs on the actual evidence. Moreover, we show that additional training of the CNNs can improve the focus of CNNs without decreasing their accuracy.

ISBN: 978-3-030-72240-1
Download: Media:ObAlEx.pdf
Weitere Informationen unter: Link
DOI Link: 10.1007/978-3-030-72240-1_32


Web Science


Maschinelles Lernen, Künstliche Intelligenz, Semantic Web