SVEA: A Small-scale Benchmark for Validating the Usability of Post-hoc Explainable AI Solutions in Image and Signal Recognition.
Sam SattarzadehMahesh SudhakarKonstantinos N. PlataniotisPublished in: ICCVW (2021)
Keyphrases
- small scale
- image data
- single image
- input image
- image matching
- image features
- template matching
- image classification
- segmentation method
- image analysis
- image retrieval
- post hoc
- high resolution
- signal processing
- recognition rate
- feature extractor
- image content
- multiscale
- object recognition
- larger scale
- feature extraction
- artificial intelligence
- expert systems
- image regions
- feature points
- low frequency
- optimal solution
- preprocessing stage
- pixel intensities
- three dimensional objects
- zero crossing
- pixel values
- partial occlusion
- image representation
- test images
- segmentation algorithm
- frequency domain
- high frequency