Constructing adversarial examples to investigate the plausibility of explanations in deep audio and image classifiers.
Katharina HoedtVerena PraherArthur FlexerGerhard WidmerPublished in: Neural Comput. Appl. (2023)
Keyphrases
- input image
- image data
- image content
- single image
- multiscale
- image retrieval
- image features
- image segmentation
- low level
- region of interest
- template matching
- image collections
- image regions
- image analysis
- edge detection
- multimedia
- image classification
- segmentation algorithm
- spatial information
- signal processing
- feature points
- multi class
- high resolution
- similarity measure
- medical images
- segmentation method
- image database
- image registration
- multi agent
- image set
- visual data
- audio visual
- extracted features
- visual concepts
- labeled images