CLEVR-XAI: A benchmark dataset for the ground truth evaluation of neural network explanations.
Leila ArrasAhmed OsmanWojciech SamekPublished in: Inf. Fusion (2022)
Keyphrases
- benchmark datasets
- ground truth
- neural network
- gold standard
- neural network model
- artificial neural networks
- pattern recognition
- prediction model
- pedestrian detection
- evaluation method
- objective evaluation
- back propagation
- quantitative evaluation
- face detection
- training data
- data sets
- feed forward
- machine learning
- evaluation methods
- evaluation model