A method that applies Fourier, wavelet, and median filter transforms to full images to detect whether a CNN's accuracy is driven by dataset background bias rather than object features.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Identifying Bias in Deep Neural Networks Using Image Transforms
A method that applies Fourier, wavelet, and median filter transforms to full images to detect whether a CNN's accuracy is driven by dataset background bias rather than object features.