Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Testing DNN Image Classifiers for Confusion & Bias Errors
Ist Teil von
2020 IEEE/ACM 42nd International Conference on Software Engineering: Companion Proceedings (ICSE-Companion), 2020, p.304-305
Ort / Verlag
ACM
Erscheinungsjahr
2020
Link zum Volltext
Quelle
ACM Digital Library (Association for Computing Machinery)
Beschreibungen/Notizen
We found that many of the reported erroneous cases in popular DNN image classifiers occur because the trained models confuse one class with another or show biases towards some classes over others. Most existing DNN testing techniques focus on per-image violations, so fail to detect class-level confusions or biases. We developed a testing technique to automatically detect class-based confusion and bias errors in DNN-driven image classification software. We evaluated our implementation, DeepInspect, on several popular image classifiers with precision up to 100% (avg. 72.6%) for confusion errors, and up to 84.3% (avg. 66.8%) for bias errors.