The SVD of Convolutional Weights: A CNN Interpretability Framework. (arXiv:2208.06894v1 [cs.CV])

Deep neural networks used for image classification often use convolutional
filters to extract distinguishing features before passing them to a linear
classifier. Most interpretability literature focuses on providing semantic
meaning to convolutional filters to explain a model's reasoning process and
confirm its use of relevant information from the input domain. Fully connected
layers can be studied by decomposing their weight matrices using a singular
value decomposition, in effect studying the correlations between the rows in
each matrix to discover the …

arxiv cnn cv framework interpretability svd