Inproceedings332: Unterschied zwischen den Versionen
Ns1888 (Diskussion | Beiträge) |
He9318 (Diskussion | Beiträge) |
||
Zeile 12: | Zeile 12: | ||
}} | }} | ||
{{Inproceedings | {{Inproceedings | ||
− | |Referiert= | + | |Referiert=Ja |
|Title=Right for the Right Reasons: Making Image Classification Intuitively Explainable | |Title=Right for the Right Reasons: Making Image Classification Intuitively Explainable | ||
|Year=2021 | |Year=2021 | ||
|Month=Januar | |Month=Januar | ||
− | |Booktitle=43rd | + | |Booktitle=Proceedings of the 43rd European Conferene on Information Retrieval (ECIR'21) |
|Publisher=Springer | |Publisher=Springer | ||
}} | }} | ||
Zeile 27: | Zeile 27: | ||
{{Forschungsgebiet Auswahl | {{Forschungsgebiet Auswahl | ||
|Forschungsgebiet=Semantic Web | |Forschungsgebiet=Semantic Web | ||
+ | }} | ||
+ | {{Forschungsgebiet Auswahl | ||
+ | |Forschungsgebiet=Künstliche Intelligenz | ||
+ | }} | ||
+ | {{Forschungsgebiet Auswahl | ||
+ | |Forschungsgebiet=Maschinelles Lernen | ||
}} | }} |
Version vom 13. Januar 2021, 12:00 Uhr
Right for the Right Reasons: Making Image Classification Intuitively Explainable
Right for the Right Reasons: Making Image Classification Intuitively Explainable
Published: 2021
Januar
Buchtitel: Proceedings of the 43rd European Conferene on Information Retrieval (ECIR'21)
Verlag: Springer
Referierte Veröffentlichung
BibTeX
Kurzfassung
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.
Download: Media:ObAlEx.pdf
Weitere Informationen unter: Link
Maschinelles Lernen, Künstliche Intelligenz, Semantic Web