On the Shift Invariance of Max Pooling Feature Maps in Convolutional Neural Networks.
Hubert LetermeKevin PolisanoValérie PerrierKarteek AlahariPublished in: CoRR (2022)
Keyphrases
- feature maps
- convolutional neural networks
- shift invariance
- wavelet transform
- shift invariant
- self organizing maps
- kernel function
- feature vectors
- correlation filters
- saliency map
- neural network
- feature space
- feature extraction
- wavelet domain
- multiscale
- dt cwt
- image compression
- subband
- rotation invariant
- image recognition
- wavelet coefficients
- training samples
- higher order
- computational complexity
- image sequences